스틸 55샷 실패 0. 각 샷: ① 배경·밑그림이 만들어진 과정 (플레이트=공간참조➜3롤➜선정➜수정 / 야외 레인1=base 맵➜스케치 / PREV=앞 샷 확정본) → ② 인물·소품 재료 → ③ 스틸 생성 (첨부➜롤➜VLM 판정➜i2i 수정⇒최종). 모든 프롬프트=클릭해서 펼침.
A/B 4택1 18샷(콘티승 10/무콘티승 8) · PREV 14 · 배경 전용 14 · 레인1(맵 기반) 1 · 일반 8
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 1 - camera_cell: [3, 5] - look_at_unit: 2 - look_at_cell: [8, 2] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use the advertised broad view from unit 1 toward unit 2 to retain the committed unit and marker context while allowing the consuming shot to place its subjects close in the foreground.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show the view originating in unit 1 and directed toward unit 2, with broad coverage sufficient to retain the committed context of target units 1, 2, and 3 where they fall inside the 90-degree cone. Include opening marker 4 and fixed markers 7, 9, 10, and 13 according to their floor-plan positions. - camera_framing_directive: Frame from camera unit 1 at cell [3,5] toward look-at unit 2 at cell [7,2] with the wide 90-degree lens cone. Maintain broad background coverage while accommodating the committed eye-level close foreground composition, with the primary profile in the right half and the secondary subject soft but recognizable at the left edge. - subject_position_directive: At eye level, place the primary subject in close left-facing profile in the right half, leaning back with the widened eye and cheek emphasized. Keep the second subject across the conversation axis at the left edge, three-quarter right, soft but recognizable, with transient marker 14 held forward near the background shelving context. - state_cue_directive: Carry transient marker 14 as the committed temporary state cue and retain numbered elements 1, 2, 3, 4, 7, 9, 10, and 13. The background is not designated clean, but no additional state cue beyond the surfaced shot staging and marker 14 should be invented. - negative_continuity_directive: Do not introduce unlisted numbered elements, uncommitted state overlays, or units and openings outside the chosen unit-1-to-unit-2 view cone. Keep the fixed placement relationships of markers 4, 7, 9, 10, and 13 consistent with the floor-plan geometry, and do not replace transient marker 14 with an invented cue. 2026년 대한민국 서해안권 도시의 대형 마트 매장 진열 구역을 실제 카메라로 촬영한 다큐멘터리 풍 사진. 해 질 무렵에도 영업 중인 현실적인 현대 한국 대형 마트 내부이며, 배경 이미지에는 직원과 고객을 포함한 사람이 전혀 없다. 사람 대신 일부 열린 골판지 상품 상자, 접힌 포장재, 바퀴 달린 상품 보충 카트, 통로 가장자리에 잠시 세워 둔 쇼핑카트, 진열 중인 묶음 상품과 약간 비어 있는 선반 칸으로 활발한 상품 보충과 고객 순환의 흔적을 보여 준다. 서쪽 중앙 통로 진열대 가까이에서 카메라를 두고 넓은 판매 구역을 가로질러 동쪽 중앙 통로 진열대를 대각선으로 바라본 구도. 동쪽 중앙 통로 진열대와 그 바로 옆의 보조 진열 요소가 함께 보이며, 깊은 배경에는 전면 행사 진열대, 계산대 섬, 유리 자동 출입문 구역이 명확하게 읽힌다. 자동 출입문 너머에는 해 질 무렵의 차가운 청회색 자연광만 은은하게 보이고, 실내에는 현대식 선형 LED 천장 조명이 켜져 있어 낮고 균일한 상업 조도를 만든다. 계산대 주변의 소형 안내 표지, 전자식 또는 인쇄식 가격표, 일반적인 한국어 매장 안내판, 천장형 보안 카메라, 냉장 진열 케이스와 생활용품·포장식품 진열을 현실적인 수준으로 배치하되 특정 상표나 읽기 어려운 가짜 문구를 강조하지 않는다. 차분한 해안 도시의 중성색 바닥과 흰색·회색 금속 진열대, 제한적인 짙은 적색 행사 표지와 작은 금색 가격 강조 요소. 바닥에는 카트 바퀴 자국과 닦인 얼룩, 선반 금속에는 미세한 긁힘과 사용 흔적, 골판지에는 눌림과 찢긴 테이프 자국, 비닐 포장에는 실제 반사광이 보인다. 지나치게 정돈된 광고 사진이 아니라 영업 중인 실제 장소의 생활감과 일상적인 마모가 남은 사실적인 현장 기록 사진. 실제 DSLR 또는 미러리스 카메라, 28mm 광각 렌즈, 서 있는 성인의 눈높이 약 1.6m, 자연스러운 원근감과 깊이감, 과장되지 않은 자연스러운 피사계 심도. 실제 콘크리트계 바닥 마감, 분체도장 금속, 투명 유리, 골판지, 비닐과 종이 가격표의 재질을 정확하게 표현한다. 후처리 없는 담담한 실제 장소 참고 사진으로, 삽화나 3D 렌더, 건축 시각화, 평면도, 위에서 내려다본 시점이 아니다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Rotate the checkout counters on the left and the central freezer display 90 degrees so they run parallel to the background entrance doors. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 대형 마트 매장 내부 SHOT TEXT (authoritative, Korean): 마트 남자 직원과 마주 본 상태로 눈을 동그랗게 뜬 수리영의 측면 CARRIED STATE (persist exactly): Su-ri-yeong’s bicycle remains parked outside the mart, and she still has her mobile phone with her. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 남자 직원과 마주 본 상태로 눈을 동그랗게 뜬 수리영의 측면 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she still has her mobile phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 남자 직원과 마주 본 상태로 눈을 동그랗게 뜬 수리영의 측면 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she still has her mobile phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight side-profile close-up at eye level, with Su-ri-yeong’s face dominating the image and her fixed eyeline aimed just beyond the frame toward the employee. Keep her anatomically natural eyes sharply focused and opened wide through performance, with restrained tension in her brow, lips, and jaw. Use shallow depth of field and soft dusk-neon spill to isolate the instant of startled recognition while the supermarket environment falls into subdued blur. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 남자 직원과 마주 본 상태로 눈을 동그랗게 뜬 수리영의 측면 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she still has her mobile phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph Su-ri-yeong in a wider side-on composition from slightly below shoulder height, placing her to one side of the frame and leaving charged negative space in the direction of the employee she faces off camera. Preserve visible depth through the supermarket entrance, aisles, and stocking areas, with dusk and neon illumination layering the foreground and background. Keep her profile and widened, natural-eyed reaction clearly readable while the surrounding commercial bustle gives the confrontation a grounded, immediate scale. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 남자 직원과 마주 본 상태로 눈을 동그랗게 뜬 수리영의 측면 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she still has her mobile phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight side-profile close-up at eye level, with Su-ri-yeong’s face dominating the image and her fixed eyeline aimed just beyond the frame toward the employee. Keep her anatomically natural eyes sharply focused and opened wide through performance, with restrained tension in her brow, lips, and jaw. Use shallow depth of field and soft dusk-neon spill to isolate the instant of startled recognition while the supermarket environment falls into subdued blur. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 남자 직원과 마주 본 상태로 눈을 동그랗게 뜬 수리영의 측면 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she still has her mobile phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph Su-ri-yeong in a wider side-on composition from slightly below shoulder height, placing her to one side of the frame and leaving charged negative space in the direction of the employee she faces off camera. Preserve visible depth through the supermarket entrance, aisles, and stocking areas, with dusk and neon illumination layering the foreground and background. Keep her profile and widened, natural-eyed reaction clearly readable while the surrounding commercial bustle gives the confrontation a grounded, immediate scale. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the man from the left foreground completely so that only Su-ri-yeong remains in the frame, keeping her eyeline directed just beyond the edge of the screen. - Remove all letters and text from the pink neon sign and the cardboard boxes in the background, leaving them blank. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.








STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows the SAME physical room as this background, from a different camera angle or framing. Inherit the exact architecture, floor, walls, windows, fixed furniture and lighting of that room — this is literally the same space, only the viewpoint changes. REFERENCE PLAN: mode='same_physical_space_view' - selected_refs[0]: ref_bg_id='L12B04' physical_space_id='ps_fp_l12_stairs_connected_approach' CAMERA DECISION (exact, from validated plan): - camera_unit: 6 - camera_cell: [3, 6] - look_at_unit: 3 - look_at_cell: [3, 4] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Place the camera in unit 6 at cell [3,6] and aim toward unit 3 using listed look-at cell [3,4]. The normal lens supports the committed close subject framing while allowing the descending sequence of units 5 through 1 to supply background depth.' RENDER GUIDANCE (from validated plan): - visible_space_directive: From camera unit 6, look toward unit 3 and show the descending connected structure through units 5, 4, 3, 2, and 1 as framing permits, with unit 7 remaining the fixed upper continuity link to reference L12B04. Preserve marker 7 and its structural relationship to unit 6 in the same position established by the floor plan and reference. - camera_framing_directive: Use camera unit 6 at cell [3,6], looking toward unit 3 at cell [3,4] with a normal 50-degree field of view. Hold close, neutral coverage around the committed subject while the descending unit sequence forms converging depth behind and below the subject. - subject_position_directive: Place the single committed subject in the middle center and midground, paused mid-step with the nose covered. Keep the body angled by the climb, the face oriented toward the camera, and the upward gaze passing toward the upper approach beyond the camera, as committed by S11_Shot3. - state_cue_directive: Carry transient markers 15 and 16 together with the committed numbered structural elements 1 through 7. Do not add any state cue beyond those listed markers and the state-facing staging for S11_Shot3. - negative_continuity_directive: Exclude marker 17 and do not carry its overlay state from reference L12B04 into this view. Do not redraw reference-specific transient cues, invent additional subjects or state overlays, or expose units 8 and 9 and markers 10 through 14 as though they were inside this downward-facing composition. 2026년 대한민국 서해안권 도시 또는 섬마을의 사람이 실제 거주하는 낡은 저층 주택, 마당에서 옥상으로 이어지는 좁은 외부 전환식 콘크리트 계단의 깊은 밤. 아래쪽 계단참 가까이에서 위를 바라보며, 중간 계단을 따라 작은 꺾인 참과 다시 올라가는 위쪽 계단이 연속되지만 높은 벽과 계단의 꺾임 때문에 옥상은 거의 보이지 않는다. 옥상 방의 문은 시야 밖에 두어 절대 노출하지 않는다. 약 1.6미터의 서 있는 사람 눈높이, 실제 28밀리미터 광각 렌즈를 장착한 디지털 일안 반사식 또는 미러리스 카메라로 촬영한 구도. 좁고 가파른 상승감과 막힌 시야를 강조하되 과도한 왜곡은 없다. 주택 외벽은 이 지역의 오래된 저층 주거에서 흔한 붉은 벽돌과 부분적인 회색 화강석 타일, 거칠게 보수한 시멘트 면이 섞여 있다. 콘크리트 계단과 계단참에는 미끄럼 방지 줄눈, 오래된 물때, 빗물 자국, 해풍과 습기로 생긴 검은 얼룩이 있으며 위쪽 가장자리에는 바랜 녹색 우레탄 방수 도장과 덧칠 흔적이 조금 보인다. 금속 난간은 여러 번 칠한 회색 페인트가 벗겨지고 이음부에 염분성 붉은 녹이 배어 있다. 알루미늄 새시 창과 방범창, 외벽을 따라 노출된 가스 배관과 계량기, 에어컨 실외기와 배관 덮개, 작은 화분, 생활용 양동이, 느슨한 빨랫줄이 층층이 배치되어 실제 거주 흔적을 만든다. 마당 가장자리에는 젖은 배수구와 정리되지 않은 생활 잡동사니가 일부 보인다. 위쪽의 보이는 계단 구간에는 축축하게 번진 오염 자국과 벽 아래에 놓인 검은 종량제 쓰레기봉투 몇 개가 있어 갑작스러운 불쾌한 냄새의 가능성을 현실적으로 암시하지만, 냄새를 연기·안개·초자연적 기운처럼 시각화하지 않고 원인도 완전히 드러내지 않는다. 시신, 피, 인물, 얼굴은 없다. 작은 벽부형 보안등의 누렇게 바랜 빛과 아래 마당에서 올라오는 약한 백색 생활 조명이 섞인 낮은 밝기의 야간 환경이며, 깊은 그림자 속에서도 실제 재료 표면이 자연스럽게 식별된다. 멀리 보이는 주변은 비슷한 붉은 벽돌과 타일 외벽의 저층 주택이 밀집한 동네로, 좁은 골목의 일부, 전신주와 늘어진 전선, 이웃집 실외기와 창문 불빛이 제한적으로 보인다. 대상 주택이 고립된 요새나 감옥처럼 보이지 않게 한다. 실제 카메라로 촬영한 다큐멘터리 풍 사진, 실제 장소 답사 기록처럼 담담한 사진, 자연스러운 야간 노출과 현실적인 명암, 정확한 콘크리트 질감·금속 녹·직물 짜임·벽돌과 목재 결, 일상적인 마모와 얼룩, 자연스러운 심도. 깨끗한 광고 사진이 아니며 후처리 느낌이 없고, 컴퓨터 그래픽·삽화·건축 시각화·평면도·도면·상부 수직 시점이 아니다. 16:9 가로 비율, 실제 카메라 촬영본 One attached image is a PHOTOREAL RENDER of the SAME building/site this scene belongs to — it may show the outside while this scene is inside, or another part of the same place. Treat it as the BUILDING IDENTITY reference. Keep this render consistent with it: the same era, age and state of repair, the same palette and material quality, the same window and door frame styles, and anything visible through openings (windows, doorways, passages) must belong to that same building and its surroundings. Signage follows the place's nature: a commercial or public facility keeps its signage present and legible; a residential or private place has none unless the prompt says so. Reproduce any signage visible in the reference EXACTLY — same lettering, same design, same position; never invent different sign text from render to render. Lighting and time of day follow THIS prompt. Do NOT copy the reference's composition, framing or camera angle; only the building's physical identity carries over. The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Add faded green urethane waterproofing paint marks along the upper edges of the concrete stairs and landings. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 옥탑방 빌라 외부 마당과 계단 SHOT TEXT (authoritative, Korean): 계단 중간에 서서 한 손으로 코를 막은 수리영의 정면 얼굴 CARRIED STATE (persist exactly): Su-ri-yeong’s bicycle remains hastily parked in the rear of the courtyard, and her mobile phone remains with her. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 계단 중간에 서서 한 손으로 코를 막은 수리영의 정면 얼굴 LOCATION (lock): A narrow residential alley and the courtyard of a low-rise multi-unit building, with a secluded bicycle parking spot and an exterior stairway leading to the rooftop apartment and its half-open metal door. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains hastily parked in the rear of the courtyard, and her mobile phone remains with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 계단 중간에 서서 한 손으로 코를 막은 수리영의 정면 얼굴 LOCATION (lock): A narrow residential alley and the courtyard of a low-rise multi-unit building, with a secluded bicycle parking spot and an exterior stairway leading to the rooftop apartment and its half-open metal door. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains hastily parked in the rear of the courtyard, and her mobile phone remains with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight, eye-level frontal close-up with her face and the hand covering her nose as the dominant visual information. Use a gently compressed perspective and very shallow focus, holding both eyes and the gripping fingers crisp while the stairway falls into soft nocturnal abstraction behind her. Keep the composition still, centered, and claustrophobic, with soft off-axis light shaping her youthful features without glamour. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 계단 중간에 서서 한 손으로 코를 막은 수리영의 정면 얼굴 LOCATION (lock): A narrow residential alley and the courtyard of a low-rise multi-unit building, with a secluded bicycle parking spot and an exterior stairway leading to the rooftop apartment and its half-open metal door. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains hastily parked in the rear of the courtyard, and her mobile phone remains with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her from close range with a wider perspective, keeping her face fully frontal while allowing the stair geometry to cut diagonally through the frame and recede with pronounced depth. Place her slightly off-center in a waist-up composition, with the hand over her nose clearly readable and the surrounding stairway remaining spatially present. Use restrained handheld immediacy, deeper focus, and uneven motivated night illumination to make the moment feel abruptly observed rather than posed. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 계단 중간에 서서 한 손으로 코를 막은 수리영의 정면 얼굴 LOCATION (lock): A narrow residential alley and the courtyard of a low-rise multi-unit building, with a secluded bicycle parking spot and an exterior stairway leading to the rooftop apartment and its half-open metal door. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains hastily parked in the rear of the courtyard, and her mobile phone remains with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight, eye-level frontal close-up with her face and the hand covering her nose as the dominant visual information. Use a gently compressed perspective and very shallow focus, holding both eyes and the gripping fingers crisp while the stairway falls into soft nocturnal abstraction behind her. Keep the composition still, centered, and claustrophobic, with soft off-axis light shaping her youthful features without glamour. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 계단 중간에 서서 한 손으로 코를 막은 수리영의 정면 얼굴 LOCATION (lock): A narrow residential alley and the courtyard of a low-rise multi-unit building, with a secluded bicycle parking spot and an exterior stairway leading to the rooftop apartment and its half-open metal door. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains hastily parked in the rear of the courtyard, and her mobile phone remains with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her from close range with a wider perspective, keeping her face fully frontal while allowing the stair geometry to cut diagonally through the frame and recede with pronounced depth. Place her slightly off-center in a waist-up composition, with the hand over her nose clearly readable and the surrounding stairway remaining spatially present. Use restrained handheld immediacy, deeper focus, and uneven motivated night illumination to make the moment feel abruptly observed rather than posed. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Position the character so she is standing halfway up the flight of stairs instead of at the bottom. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.









STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows the SAME physical room as this background, from a different camera angle or framing. Inherit the exact architecture, floor, walls, windows, fixed furniture and lighting of that room — this is literally the same space, only the viewpoint changes. REFERENCE PLAN: mode='same_physical_space_view' - selected_refs[0]: ref_bg_id='L12B01' physical_space_id='fp_l12_yard_space_1' CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [7, 3] - look_at_unit: 4 - look_at_cell: [2, 8] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Use neutral coverage from unit 2 toward unit 4, allowing the fixed structure around units 4 and 6 to support both the centered medium staging of S13_Shot2 and the tighter continuity background required by S13_Shot5.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show the view from unit 2 toward unit 4, retaining the required fixed context from units 1, 3, 4, 6, 7, 8, 9, 10, and 11 as permitted by the normal cone, with opening marker 5 included only where the selected framing exposes it. Maintain shared markers 1, 9, 10, and 11 in the same physical positions established by L12B01. - camera_framing_directive: Frame from camera unit 2 at cell [7,3], looking toward unit 4 through look-at cell [2,8], with a normal 50-degree field of view and neutral coverage. Supply enough fixed background context for the centered medium composition in S13_Shot2 while allowing the background to reduce to an indistinct trace in the close framing of S13_Shot5. - subject_position_directive: For S13_Shot2, place the committed subject near middle-center at medium distance directly before the unit-4 context, motionless and facing the camera. For S13_Shot5, support the committed close subject at eye level with the prior subject cleared from the final composition and the fixed unit-4 and unit-6 context reduced behind the face. - state_cue_directive: Include committed transient markers 14, 15, and 16, with marker 16 functioning as the moving or intermittent light accent specified by the surfaced shots. Preserve only the state cues listed for this BG and do not add marker 17 or 18. - negative_continuity_directive: Exclude ignored overlay markers 17 and 18. Keep the fixed positions of shared markers 1, 9, 10, and 11 consistent with reference L12B01, do not import L12B01's transient cues, and do not invent spaces outside the selected camera cone or unlisted scenario-specific elements. 2026년 대한민국 서해안권 도시의 오래된 저층 다세대 빌라 외부 마당을 밤에 실제 미러리스 카메라로 촬영한 다큐멘터리 풍 사진. 카메라는 거리 대문 바로 안쪽, 서 있는 사람의 눈높이 약 1.6미터에 놓고 28밀리미터 광각 렌즈로 좁은 마당을 대각선 방향으로 바라본다. 전경에는 대문 쪽에 막 들어와 비스듬히 정차한 현대 대한민국의 일반적인 경찰 순찰차 일부와 현실적인 적색·청색 경광등이 보이며, 강한 빛은 차량 주변의 마당 바닥과 담장, 건물 하부에만 국소적으로 번지고 반사된다. 마당을 가로질러 건물 입구의 계단 아래참, 노출된 외부 계단, 빌라 전면부가 명확히 이어져 이동 경로를 쉽게 파악할 수 있어야 한다. 한쪽 벽 아래에는 소박한 자전거 보관 공간과 실제 사용 중인 자전거가 있다. 건물은 대한민국 서해안권의 밀집한 구도심 주택가에서 흔히 볼 수 있는 3~4층 규모의 생활형 빌라로, 빛바랜 붉은 벽돌 외벽과 하부의 회색 화강석 타일, 오래된 알루미늄 새시 창, 일부 창문의 금속 방범창, 작은 현관 차양을 갖춘다. 외벽에는 층마다 에어컨 실외기와 노출 배관, 도시가스 배관과 계량기, 빗물 배수관, 현관 부근의 소형 감시카메라가 실용적으로 설치되어 있다. 옥상 가장자리에는 낡고 덧칠된 녹색 우레탄 방수층과 물탱크 일부가 자연스럽게 보인다. 작은 화분, 접어 둔 빨래건조대, 빨랫줄과 일상적인 세탁물, 벽가의 생활 잡동사니처럼 실제 거주 흔적을 절제해 배치한다. 건물을 감옥이나 고립된 콘크리트 요새처럼 만들지 않는다. 대문 너머로는 비슷한 붉은 벽돌·석재 타일 빌라가 붙어 있는 좁은 골목, 전신주와 늘어진 전선, 주차된 생활 차량의 일부가 보여 실제 동네와 연결된 인상을 준다. 밤의 낮은 주변 조도 아래 현관등과 계단등은 평범한 백색 조명으로 켜져 있고, 경찰차의 적색·청색 빛이 서로 다른 표면에서 현실적으로 약해지며 섞인다. 해안 도시 특유의 습기와 염분으로 금속 난간과 배관에 가벼운 부식과 얼룩이 있고, 콘크리트 마당에는 오래된 균열, 배수 흔적, 타이어 자국과 약간 젖은 부분이 있다. 실제 콘크리트 입자, 금속의 산화와 반사, 벽돌 줄눈, 석재 타일의 오염, 세탁물의 직물 짜임, 자전거 고무와 도장의 마모를 정확하게 표현한다. 과도하게 정돈된 광고 사진이 아니라 사람이 계속 살아온 장소의 자연스러운 사용감과 불균일함을 유지한다. 인물, 얼굴, 시신, 혈흔은 전혀 없으며 도착 직후 잠시 비어 있는 배경 공간만 담는다. 자연스러운 심도와 실제 야간 노출, 과장 없는 색, 후처리 없는 실제 장소 기록 사진. 하향 시점, 평면도, 건축 도면, 삽화, 합성 그래픽이 아닌 실제 카메라 촬영. 16:9 가로 비율, 실제 카메라 촬영본. One attached image is a PHOTOREAL RENDER of this SAME place — the same physical location, possibly seen from a different angle or at a different moment. Treat it as the PLACE IDENTITY reference. Keep this render consistent with it: the same spatial layout and architecture, the same surface materials and colors, and the same permanently installed fixtures, furniture and signage. Signage follows the place's nature: a commercial or public facility keeps its signage present and legible; a residential or private place has none unless the prompt says so. Reproduce any signage visible in the reference EXACTLY — same lettering, same design, same position; never invent different sign text from render to render. Camera angle, framing, lighting, time of day and weather follow THIS prompt — do NOT copy the reference's composition or mood; only the place's physical identity carries over. One attached image is a PHOTOREAL RENDER of the SAME building/site this scene belongs to — it may show the outside while this scene is inside, or another part of the same place. Treat it as the BUILDING IDENTITY reference. Keep this render consistent with it: the same era, age and state of repair, the same palette and material quality, the same window and door frame styles, and anything visible through openings (windows, doorways, passages) must belong to that same building and its surroundings. Signage follows the place's nature: a commercial or public facility keeps its signage present and legible; a residential or private place has none unless the prompt says so. Reproduce any signage visible in the reference EXACTLY — same lettering, same design, same position; never invent different sign text from render to render. Lighting and time of day follow THIS prompt. Do NOT copy the reference's composition, framing or camera angle; only the building's physical identity carries over. The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Add blue light casting and reflections on the ground and surrounding surfaces to mix realistically with the red light. - Add a clothesline with hanging daily laundry near the folded laundry rack. - Replace the slanted green roof structure above the first floor with a flat rooftop edge showing worn green urethane waterproofing. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 옥탑방 빌라 외부 마당과 계단 SHOT TEXT (authoritative, Korean): 경찰차의 붉은 경광등 불빛을 받으며 초점을 잃고 멍하니 서 있는 수리영의 상체. CARRIED STATE (persist exactly): Su-ri-yeong still has the old photograph she removed from Minsuk’s hand. Upstairs, Minsuk’s seated corpse, the blood traces, and the red wall circle remain until the subsequent unexplained cleanup. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 경찰차의 붉은 경광등 불빛을 받으며 초점을 잃고 멍하니 서 있는 수리영의 상체. LOCATION (lock): The exterior of a rooftop apartment building, including the rooftop exit, steep connecting stairs, lower courtyard, and nearby vehicle access where responders arrive. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still has the old photograph she removed from Minsuk’s hand. Upstairs, Minsuk’s seated corpse, the blood traces, and the red wall circle remain until the subsequent unexplained cleanup. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 경찰차의 붉은 경광등 불빛을 받으며 초점을 잃고 멍하니 서 있는 수리영의 상체. LOCATION (lock): The exterior of a rooftop apartment building, including the rooftop exit, steep connecting stairs, lower courtyard, and nearby vehicle access where responders arrive. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still has the old photograph she removed from Minsuk’s hand. Upstairs, Minsuk’s seated corpse, the blood traces, and the red wall circle remain until the subsequent unexplained cleanup. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her in a tight, eye-level chest-up close-up, nearly frontal and held with unnerving stillness. Use shallow focus to isolate her youthful face and unfixed gaze, with the police beacon’s red light raking across one side of her face and clothing while the rooftop exterior dissolves into subdued night blur. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 경찰차의 붉은 경광등 불빛을 받으며 초점을 잃고 멍하니 서 있는 수리영의 상체. LOCATION (lock): The exterior of a rooftop apartment building, including the rooftop exit, steep connecting stairs, lower courtyard, and nearby vehicle access where responders arrive. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still has the old photograph she removed from Minsuk’s hand. Upstairs, Minsuk’s seated corpse, the blood traces, and the red wall circle remain until the subsequent unexplained cleanup. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame an oblique upper-body portrait from a distinctly elevated viewpoint, keeping her smaller and off-center within the hard descending geometry of the rooftop exit and steep stairs. Preserve more environmental depth and texture than in an intimate close-up; let the red emergency light spread unevenly across her and the surrounding surfaces, making her rigid, vacant stillness feel exposed within the night exterior. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 경찰차의 붉은 경광등 불빛을 받으며 초점을 잃고 멍하니 서 있는 수리영의 상체. LOCATION (lock): The exterior of a rooftop apartment building, including the rooftop exit, steep connecting stairs, lower courtyard, and nearby vehicle access where responders arrive. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still has the old photograph she removed from Minsuk’s hand. Upstairs, Minsuk’s seated corpse, the blood traces, and the red wall circle remain until the subsequent unexplained cleanup. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her in a tight, eye-level chest-up close-up, nearly frontal and held with unnerving stillness. Use shallow focus to isolate her youthful face and unfixed gaze, with the police beacon’s red light raking across one side of her face and clothing while the rooftop exterior dissolves into subdued night blur. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 경찰차의 붉은 경광등 불빛을 받으며 초점을 잃고 멍하니 서 있는 수리영의 상체. LOCATION (lock): The exterior of a rooftop apartment building, including the rooftop exit, steep connecting stairs, lower courtyard, and nearby vehicle access where responders arrive. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still has the old photograph she removed from Minsuk’s hand. Upstairs, Minsuk’s seated corpse, the blood traces, and the red wall circle remain until the subsequent unexplained cleanup. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame an oblique upper-body portrait from a distinctly elevated viewpoint, keeping her smaller and off-center within the hard descending geometry of the rooftop exit and steep stairs. Preserve more environmental depth and texture than in an intimate close-up; let the red emergency light spread unevenly across her and the surrounding surfaces, making her rigid, vacant stillness feel exposed within the night exterior. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the domed warning light on the bottom left into a standard modern police car lightbar. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows the SAME physical room as this background, from a different camera angle or framing. Inherit the exact architecture, floor, walls, windows, fixed furniture and lighting of that room — this is literally the same space, only the viewpoint changes. REFERENCE PLAN: mode='same_physical_space_view' - selected_refs[0]: ref_bg_id='L14B02' physical_space_id='fp_l14_detective_office_space_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 1 - camera_cell: [3, 6] - look_at_unit: 2 - look_at_cell: [7, 8] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Use the listed unit-1 camera cell facing unit 2 with neutral coverage, supporting the doorway-facing and shared-space relations committed across S16_Shot1 and S16_Shot4.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show the same fixed physical space as L14B02 from unit 1 toward unit 2. Keep markers 4, 5, 6, and 7 and openings 10 and 11 in the same established positions, with opening 10 supporting the entrance relation and the unit-1 fixed elements supporting the deeper shared-space view. - camera_framing_directive: Frame from camera unit 1 at [3,6] toward look-at unit 2 at [7,5] with a normal 50-degree field of view, using neutral coverage for the committed medium entrance relation and the tighter shared-space relation. - subject_position_directive: For S16_Shot1, stage the committed entering subject in the midground at middle-left while moving toward the interior, with the opening relation behind that movement. For S16_Shot4, preserve the committed foreground height relation between the central leaning subject and the lower-right shoulder-edge subject; add no other subjects. - state_cue_directive: No committed state cue beyond clean residential space applies because clean_background_expected is true and no transient markers are listed; refrain from inventing additional cues and do not redraw ignored overlay markers 12 or 13. - negative_continuity_directive: Keep overlay markers 12 and 13 absent, do not move fixed markers inherited from L14B02, do not introduce unlisted scenario-specific elements, and omit any unit or opening that falls outside the selected unit-1-to-unit-2 view cone. 2026년 대한민국 서해안권 도시의 실제 경찰 관서 안에 있는 형사과 사무실, 늦은 밤의 한산한 당직 상태. 실제 카메라로 촬영한 다큐멘터리 풍 사진이며, 실제 장소 기록 사진처럼 꾸밈없고 후처리 없는 사실적인 모습. 카메라는 형사과 출입문 안쪽 가까이에 서서 바닥에서 약 1.6미터 높이의 사람 눈높이로 촬영하고, 35밀리미터급 광각 렌즈를 사용해 공용 업무 구역의 책상 열 너머로 당직 업무 책상과 북쪽 창문들을 대각선 방향으로 바라본다. 위에서 내려다본 시점, 평면도, 건축 도면, 투시도 표현이 아니다. 공용 업무 구역에는 회색과 옅은 베이지색의 실용적인 사무용 책상, 낮은 칸막이, 검은 회전 의자, 데스크톱 모니터와 키보드, 유선 전화기, 소형 프린터, 금속 서류함이 현실적인 간격으로 놓여 있다. 주변 책상 대부분은 사용자가 없는 채 정돈과 어수선함이 섞여 있고, 가장자리의 종이 더미, 빈 문서 받침, 평범한 머그잔, 쓰레기통 등 야간 사무실의 소박한 생활 흔적만 남아 있다. 값비싸거나 미래적인 장비는 없으며, 오래 사용한 책상 모서리의 마모, 칸막이 천의 미세한 얼룩, 의자 팔걸이의 광택, 금속 서류함의 작은 긁힘, 장판 또는 비닐 타일 바닥의 눌린 자국을 정확히 표현한다. 당직 업무 책상만 현재 사용 중임을 암시하도록 모니터 한 대와 책상 조명이 켜져 있고 전화기, 키보드, 메모지와 필기구가 놓여 있으나 사람이나 얼굴은 전혀 없다. 의자는 책상 가까이에 자연스럽게 비어 있어 당직자가 잠시 자리를 비운 듯한 정도만 나타낸다. 모니터에는 식별 가능한 사건 정보가 없는 평범한 행정 업무 창이나 잠금 화면만 희미하게 보이며, 범죄 사진, 사건 현장 사진, 인물 사진, 감시 영상 속 사람, 위성 지도, 위치 추적 결과 또는 위치 정보 화면은 절대 표시하지 않는다. 벽 게시판도 일반 근무표와 무지 서식 정도로 제한하고 식별 가능한 고유 명칭이나 사건 자료는 넣지 않는다. 천장에는 현대 한국 공공기관에서 흔한 백색 발광다이오드 패널 조명이 일부만 켜져 있어 당직 책상 주변은 낮은 중간 밝기, 멀리 있는 책상 열은 더 어둡게 남는다. 차갑고 중성적인 실내광과 북쪽 창문 너머의 짙은 밤빛이 자연스럽게 섞인다. 창문은 실용적인 알루미늄 새시와 부분적으로 내려온 블라인드로 구성하고, 유리에는 사무실 조명이 약하게 반사된다. 창밖에는 서해안권 도시의 어두운 공공청사 주변과 멀리 떨어진 항만 또는 도로의 작은 생활 불빛만 흐릿하게 보여야 하며 과장된 경관은 피한다. 전체 색감은 회색, 바랜 베이지색, 짙은 남청색 같은 절제된 해안 도시의 중성색을 중심으로 하고, 적갈색 문서철 표지나 작은 비상 설비 정도의 제한된 짙은 붉은색만 포함한다. 실제 콘크리트 벽의 도장 질감, 금속의 미세한 산화와 손자국, 직물 칸막이의 섬유결, 합판 책상의 나뭇결, 플라스틱 장비의 일상적인 마모를 세밀하고 자연스럽게 표현한다. 공간은 지나치게 깨끗한 광고 사진이 아니라 실제 야간 근무가 이어지는 공공기관 사무실처럼 보여야 한다. 현실적인 노출, 정확한 원근감, 자연스러운 깊이감과 피사계 심도, 과도한 색 보정이나 인공적인 광원 효과 없음. 인물, 얼굴, 시신, 피, 초자연적 형상, 붉은 상징, 장식적 마법 문양은 없다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the camera framing to a diagonal angle looking across the desks toward the duty desk and windows, instead of a straight-on view. - Turn on the ceiling lights above the duty desk on the right and turn off the ones over the far desks to make the distant area darker. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 경찰서 형사과 사무실 SHOT TEXT (authoritative, Korean): 핸드폰을 귀에 댄 채 미간을 찌푸린 얼굴로 형사과 사무실 문을 밀며 한 발짝 내디딘 자세의 혜수 상체. CARRIED STATE (persist exactly): Hye-su holds her mobile phone to her ear while calling Minsuk, who remains unreachable. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, office lighting unspecified. SHOT TEXT (authoritative, Korean): 핸드폰을 귀에 댄 채 미간을 찌푸린 얼굴로 형사과 사무실 문을 밀며 한 발짝 내디딘 자세의 혜수 상체. LOCATION (lock): A police station office arranged with desks, computers, telephones, and duty workstations, largely empty except for the overnight officer. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Hye-su holds her mobile phone to her ear while calling Minsuk, who remains unreachable. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, office lighting unspecified. SHOT TEXT (authoritative, Korean): 핸드폰을 귀에 댄 채 미간을 찌푸린 얼굴로 형사과 사무실 문을 밀며 한 발짝 내디딘 자세의 혜수 상체. LOCATION (lock): A police station office arranged with desks, computers, telephones, and duty workstations, largely empty except for the overnight officer. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Hye-su holds her mobile phone to her ear while calling Minsuk, who remains unreachable. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from inside the office at eye level in a frontal medium close-up, catching Hye-su’s upper body as she crosses the doorway. Use a gently wide perspective so the door edge frames her while the desks and duty workstations recede behind her in layered depth; keep her furrowed face and properly held phone crisp, with restrained night-office illumination giving the entrance immediate urgency. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, office lighting unspecified. SHOT TEXT (authoritative, Korean): 핸드폰을 귀에 댄 채 미간을 찌푸린 얼굴로 형사과 사무실 문을 밀며 한 발짝 내디딘 자세의 혜수 상체. LOCATION (lock): A police station office arranged with desks, computers, telephones, and duty workstations, largely empty except for the overnight officer. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Hye-su holds her mobile phone to her ear while calling Minsuk, who remains unreachable. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Place the camera close beside the doorway for a tight oblique profile view, compressing Hye-su’s phone, furrowed face, and door-pushing gesture into one tense plane. Use a longer-lens feel and shallow depth of field, letting the police-office workstations fall softly out of focus while a narrow sideward wash of office light models her mature features and emphasizes her distracted forward step. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, office lighting unspecified. SHOT TEXT (authoritative, Korean): 핸드폰을 귀에 댄 채 미간을 찌푸린 얼굴로 형사과 사무실 문을 밀며 한 발짝 내디딘 자세의 혜수 상체. LOCATION (lock): A police station office arranged with desks, computers, telephones, and duty workstations, largely empty except for the overnight officer. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Hye-su holds her mobile phone to her ear while calling Minsuk, who remains unreachable. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from inside the office at eye level in a frontal medium close-up, catching Hye-su’s upper body as she crosses the doorway. Use a gently wide perspective so the door edge frames her while the desks and duty workstations recede behind her in layered depth; keep her furrowed face and properly held phone crisp, with restrained night-office illumination giving the entrance immediate urgency. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, office lighting unspecified. SHOT TEXT (authoritative, Korean): 핸드폰을 귀에 댄 채 미간을 찌푸린 얼굴로 형사과 사무실 문을 밀며 한 발짝 내디딘 자세의 혜수 상체. LOCATION (lock): A police station office arranged with desks, computers, telephones, and duty workstations, largely empty except for the overnight officer. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Hye-su holds her mobile phone to her ear while calling Minsuk, who remains unreachable. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Place the camera close beside the doorway for a tight oblique profile view, compressing Hye-su’s phone, furrowed face, and door-pushing gesture into one tense plane. Use a longer-lens feel and shallow depth of field, letting the police-office workstations fall softly out of focus while a narrow sideward wash of office light models her mature features and emphasizes her distracted forward step. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the extra right arm and reassign the actions so the character has exactly one right arm and one left arm. - Redraw the hand pushing the door so the thumb is oriented correctly, pointing upwards. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows a related part of the same dwelling, not the current room. Inherit the overall material and lighting identity only; the new space is its own architectural room and must read as the same home. REFERENCE PLAN: mode='related_style_new_space' - selected_refs[0]: ref_bg_id='L05B02' physical_space_id='ps_shared_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 5 - camera_cell: [6, 6] - look_at_unit: 4 - look_at_cell: [2, 7] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Use neutral coverage from unit 5 toward unit 4, looking at listed cell [2,7] associated with base marker 23 and retaining the applicable connection markers 9, 10, and 13 where visible.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show the unit-4-facing portion of target units 4 and 5, with unit 2 included only through the applicable connection. Use base markers 9, 10, 13, 19, and 23 as the committed structural and placement anchors. - camera_framing_directive: Use neutral 50-degree coverage from camera unit 5 at [6,6] toward unit 4 at [2,7]. Center the fixed marker-23 area for the committed medium framing while preserving enough surrounding structure for applicable markers 9, 10, and 13. - subject_position_directive: Place the single committed subject upright and centered at medium scale on the frontal axis associated with marker 23, with the applicable opening visible behind or beside the subject. Do not add other subjects. - state_cue_directive: No committed state cue beyond clean residential space applies. Keep markers 2, 4, 5, 9, 10, 13, 19, and 23 in their persistent state and refrain from inventing additional cues. - negative_continuity_directive: Carry over only the shared dwelling finish and lighting character from L05B02; do not copy its unit-1, unit-2, or unit-3 furniture layout into this distinct space. Exclude overlay markers 27 through 39 and avoid units outside targets 2, 4, and 5. 2026년 대한민국 서해안권 도시의 소형 옥탑 주거 내부, 안방과 조용한 집 안을 실제 카메라로 촬영한 다큐멘터리 풍 사진. 카메라는 안방 침대 가까운 곳의 앉은 사람 눈높이 약 1.2m에 놓이고, 실제 풀프레임 DSLR 또는 미러리스 카메라와 35mm급 중간 광각 렌즈로 열린 안방 문을 통해 공용 거실 겸 식사 공간을 바라본다. 시선 끝에는 딸의 닫힌 방문이 프레임의 핵심으로 또렷하게 자리하며, 안방 문틀과 거실 가구가 자연스러운 깊이의 층을 만든다. 절대로 위에서 내려다본 평면도 시점이나 건축 도식이 아닌 실제 실내 관찰 시점이다. 잠 못 이룬 밤이 지난 고요한 낮. 사람은 전혀 없고 집은 대체로 단정하지만, 안방 침대의 면 침구와 베개에 밤새 뒤척인 듯한 자연스러운 주름이 남아 있으며 작은 협탁 위에는 평범한 물잔과 꺼진 침대 조명이 있다. 열린 안방 문 너머의 작은 공용 공간에는 현대 한국의 소형 주거에서 흔한 간결한 식탁과 의자, 수납장이 정돈되어 있다. 가장 중요한 닫힌 방문은 보통의 현대식 목재 무늬 문과 평범한 금속 손잡이를 갖추고 완전히 닫혀 있으며, 문틈에서 비현실적인 빛이나 형상이 나오지 않는다. 창에는 실용적인 새시와 얇은 직물 커튼이 있고, 흐린 해안 지역의 낮빛이 부드럽게 스며든다. 천장에는 일반적인 소형 LED 조명이 있으나 낮에는 꺼져 있다. 오프화이트 벽지, 사용감 있는 밝은 목재 무늬 바닥, 회색과 베이지 중심의 차분한 해안색, 침구나 작은 생활용품에만 절제된 짙은 적색 포인트. 실제 벽지 이음선, 천의 직조, 목재 무늬, 금속 손잡이의 미세한 손때, 바닥의 작은 긁힘과 생활 얼룩을 정확히 보여준다. 지나치게 깨끗한 견본 주택이나 광고용 스톡 사진처럼 보이지 않으며, 실제 사람이 살아온 흔적은 있으나 잡동사니가 과도하지 않다. 흐린 자연광의 낮은 밝기와 현실적인 실내 노출, 긴 밤 뒤의 무거운 정적, 자연스러운 그림자와 깊이감, 과장 없는 색과 자연스러운 피사계 심도. 인물, 얼굴, 신체, 환영, 초자연적 형상, 문자, 룬, 붉은 원형 표식은 없다. 실제 장소 참고용으로 촬영한 담담한 사진, 후처리 없는 사실적 카메라 촬영, 삽화나 3D 건축 시각화가 아님. 16:9 가로 비율, 실제 카메라 촬영본. This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Attach an open wooden door panel to the empty hinges on the left side of the large doorway frame. - Flatten and fill the dark rectangular recessed area in the floor next to the cabinet so it matches the continuous flat floor pattern. - Add a thin fabric curtain to the window on the right wall of the foreground bedroom. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 오래된 빌라 옥탑방 내부 SHOT TEXT (authoritative, Korean): 두 눈을 번쩍 뜨고 상체를 꼿꼿이 세운 채 긴장한 표정으로 멈춘 수리영의 정면 상체. CARRIED STATE (persist exactly): The rooftop room remains unnaturally clean and empty of Minsuk, and Su-ri-yeong still has her mobile phone nearby after waiting through the night. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 두 눈을 번쩍 뜨고 상체를 꼿꼿이 세운 채 긴장한 표정으로 멈춘 수리영의 정면 상체. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains unnaturally clean and empty of Minsuk, and Su-ri-yeong still has her mobile phone nearby after waiting through the night. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 두 눈을 번쩍 뜨고 상체를 꼿꼿이 세운 채 긴장한 표정으로 멈춘 수리영의 정면 상체. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains unnaturally clean and empty of Minsuk, and Su-ri-yeong still has her mobile phone nearby after waiting through the night. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight, straight-on upper-body close-up at eye level, with her face held near the center in restrained symmetry. Use shallow depth of field to isolate the sharply focused eyes and rigid posture, while soft early-morning ambient light gives the stillness an immediate, intimate tension. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 두 눈을 번쩍 뜨고 상체를 꼿꼿이 세운 채 긴장한 표정으로 멈춘 수리영의 정면 상체. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains unnaturally clean and empty of Minsuk, and Su-ri-yeong still has her mobile phone nearby after waiting through the night. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her frontally in a wider medium close-up from slightly below chest level, preserving more space around her upright torso so the rigid vertical posture dominates the composition. Keep the surrounding room legible with deeper focus and let directional early-morning light create controlled planes across her face, making her frozen alertness feel exposed within the unnatural quiet. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 두 눈을 번쩍 뜨고 상체를 꼿꼿이 세운 채 긴장한 표정으로 멈춘 수리영의 정면 상체. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains unnaturally clean and empty of Minsuk, and Su-ri-yeong still has her mobile phone nearby after waiting through the night. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight, straight-on upper-body close-up at eye level, with her face held near the center in restrained symmetry. Use shallow depth of field to isolate the sharply focused eyes and rigid posture, while soft early-morning ambient light gives the stillness an immediate, intimate tension. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 두 눈을 번쩍 뜨고 상체를 꼿꼿이 세운 채 긴장한 표정으로 멈춘 수리영의 정면 상체. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains unnaturally clean and empty of Minsuk, and Su-ri-yeong still has her mobile phone nearby after waiting through the night. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her frontally in a wider medium close-up from slightly below chest level, preserving more space around her upright torso so the rigid vertical posture dominates the composition. Keep the surrounding room legible with deeper focus and let directional early-morning light create controlled planes across her face, making her frozen alertness feel exposed within the unnatural quiet. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Open the character's eyes wide to clearly show a tense, startled expression. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [7, 5] - look_at_unit: 1 - look_at_cell: [3, 3] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use the listed unit-2 camera cell and look toward unit 1 with broad coverage suitable for the committed medium staging and the target-unit set [1, 2, 3].' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show unit 2 in relation to unit 1 from the selected wide view, preserve fixed markers 4, 5, 6, and 7 in their committed positions, and include unit 3 plus fixed markers 8 and 9 and openings 10 and 11 only where they fall inside the broad view cone. - camera_framing_directive: Frame from camera unit 2 at [7,5] toward look-at unit 1 at [3,6] with a wide 90-degree field of view, giving broad coverage around the committed midground subject position and the surrounding fixed markers. - subject_position_directive: For S21_Shot5, place the committed subject at seated eye level in the midground, slightly right of center and perched forward, while keeping the other committed seating cues visibly unoccupied and separated; introduce no additional subjects. - state_cue_directive: No committed state cue beyond clean residential space applies because clean_background_expected is true and no transient markers are listed; refrain from inventing additional cues and keep overlay markers 12 and 13 absent. - negative_continuity_directive: Exclude ignored overlay markers 12 and 13, do not add unlisted scenario-specific elements, and do not depict units or openings outside the chosen view cone; treat the geometry visibility lists as supersets rather than mandatory inclusions. 2026년 현대 대한민국 서해안권 도시의 공공기관 내부에 있는 형사과 사무실 좌석 구역. 실제 미러리스 또는 DSLR 카메라로 촬영한 다큐멘터리 풍 사진이며, 출입문 바로 안쪽의 서 있는 사람 눈높이 약 1.6m에서 28mm 광각 렌즈로 촬영한다. 문턱과 소규모 민원인 대기 좌석 구역을 전경에 두고, 그 너머의 공용 업무 구역에 여러 개의 실용적인 책상과 낮은 파티션, 검은색 사무용 의자, 데스크톱 모니터, 키보드, 마우스, 유선 전화기, 문서 트레이가 이어지는 넓은 설정 구도. 프레임 한쪽에는 철제 캐비닛과 개방형 선반, 공용 프린터가 놓인 서비스·수납 구역이 자연스럽게 보인다. 형사들이 낮 시간 회의 호출을 받고 급히 빠져나간 직후처럼 모든 좌석은 비어 있고, 의자 몇 개가 책상에서 약간 뒤로 밀려 있으며, 평범한 무지 머그잔과 닫힌 서류철 정도만 남아 있다. 사건 관련 사진, 수사 지도, 이름, 개인정보, 읽을 수 있는 문서 내용은 전혀 보이지 않으며 모든 모니터는 꺼져 있거나 식별 가능한 정보가 없는 빈 대기 상태다. 사람, 얼굴, 신체는 없다. 현대 한국 공공기관 사무실에서 흔한 흰색 도장 벽, 회색 계열 바닥 타일, 흠집과 손때가 남은 합판 또는 금속 사무 가구, 약간 누렇게 사용감이 밴 낮은 파티션 패브릭, 실제 플라스틱과 분체도장 금속의 질감을 정확히 표현한다. 천장은 흡음 텍스와 매립형 직사각 LED 조명으로 구성되고, 창문 블라인드 사이로 흐린 해안 도시의 낮 자연광이 들어와 실내 조명과 현실적으로 섞인다. 벽시계, 휴지통, 간단한 옷걸이 등 일상적인 업무 흔적을 절제해 배치한다. 지나치게 정돈된 홍보용 사무실이나 깨끗한 스톡 사진이 아니라, 모서리의 미세한 먼지, 바퀴 자국, 책상 표면의 잔흠집, 케이블 정리의 불균일함이 남은 실제 사용 공간이다. 자연스러운 화이트 밸런스와 사실적인 중간 밝기, 현실적인 그림자, 정확한 재료 질감, 과장되지 않은 자연스러운 심도, 무보정에 가까운 현장 기록 사진. CGI, 일러스트, 건축 시각화, 평면도, 도식, 하향 시점이 아닌 실제 장소 참고 사진. 16:9 가로 비율, 실제 카메라 촬영본. This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the screens of all three illuminated desktop monitors to be completely black and turned off. - Remove the framed notice board with documents from the far left wall and the printed paper pinned to the right partition. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 경찰서 형사과 사무실 SHOT TEXT (authoritative, Korean): 텅 빈 사무실 의자에 홀로 앉아 있는 수리영의 상체. CARRIED STATE (persist exactly): Su-ri-yeong remains alone in the office with her doll-adorned backpack and phone, while the enlarged murder-scene photographs stay scattered across Hye-su’s desk. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 텅 빈 사무실 의자에 홀로 앉아 있는 수리영의 상체. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong remains alone in the office with her doll-adorned backpack and phone, while the enlarged murder-scene photographs stay scattered across Hye-su’s desk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 텅 빈 사무실 의자에 홀로 앉아 있는 수리영의 상체. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong remains alone in the office with her doll-adorned backpack and phone, while the enlarged murder-scene photographs stay scattered across Hye-su’s desk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame her upper body in a restrained, eye-level medium close-up, held nearly frontal and centered while the surrounding office geometry falls softly out of focus. Use gentle directional interior light across her face with subdued contrast, letting layered desk edges and monitors create a compressed enclosure around her still posture. Keep the visual emphasis on the quiet weight of her solitary presence. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 텅 빈 사무실 의자에 홀로 앉아 있는 수리영의 상체. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong remains alone in the office with her doll-adorned backpack and phone, while the enlarged murder-scene photographs stay scattered across Hye-su’s desk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her upper body from an elevated oblique angle across the clustered workstations, placing her off-center within broad negative space and rigid desk lines. Use a wider, deeper-focus composition so the office structure and the spread photographs remain legible as layered context without competing with her. Cool, even interior illumination and restrained color create a detached, observational mood. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 텅 빈 사무실 의자에 홀로 앉아 있는 수리영의 상체. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong remains alone in the office with her doll-adorned backpack and phone, while the enlarged murder-scene photographs stay scattered across Hye-su’s desk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame her upper body in a restrained, eye-level medium close-up, held nearly frontal and centered while the surrounding office geometry falls softly out of focus. Use gentle directional interior light across her face with subdued contrast, letting layered desk edges and monitors create a compressed enclosure around her still posture. Keep the visual emphasis on the quiet weight of her solitary presence. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 텅 빈 사무실 의자에 홀로 앉아 있는 수리영의 상체. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong remains alone in the office with her doll-adorned backpack and phone, while the enlarged murder-scene photographs stay scattered across Hye-su’s desk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her upper body from an elevated oblique angle across the clustered workstations, placing her off-center within broad negative space and rigid desk lines. Use a wider, deeper-focus composition so the office structure and the spread photographs remain legible as layered context without competing with her. Cool, even interior illumination and restrained color create a detached, observational mood. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 6 - camera_cell: [9, 4] - look_at_unit: 3 - look_at_cell: [4, 4] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Wide coverage from unit 6 toward unit 3, centered on look-at cell [4,4], supports the full-figure depth arrangement and forward movement axis committed for S28_Shot9.' RENDER GUIDANCE (from validated plan): - visible_space_directive: From unit 6 looking toward unit 3, show the floor-plan-supported forward axis through unit 1 and toward unit 3, with units 4 and 5 available at the lateral edges under the wide view. Keep openings 7 and 8 and fixed markers 9, 10, 11, and 12 in their committed floor-plan positions. - camera_framing_directive: Frame from camera unit 6 at cell [9,4] toward unit 3 through look-at cell [4,4] with a wide 90-degree field of view. Use broad coverage along the unit-6-to-unit-3 axis so the lower-center foreground, middle-center depth plane, and upper-center destination remain legible together. - subject_position_directive: For S28_Shot9, retain one committed full-body subject back to camera in the lower center, lunging forward with an extended arm, and a second back-to-camera subject in the middle-center background moving along the same axis toward unit 3. Preserve the rear spacing and wide-frame depth separation committed by the staging. - state_cue_directive: No committed state cue beyond a clean residential space applies because clean_background_expected is true and no transient markers are listed. Refrain from inventing additional state cues. - negative_continuity_directive: Exclude ignored markers 14 and 15. Do not introduce unlisted transient markers, do not alter the fixed positions of markers 7, 8, 9, 10, 11, or 12, and do not depict units outside the floor-plan-supported view cone as committed visible space. 2026년 대한민국 서해안에서 실제 운항하는 소형 연안 작업선의 외부 갑판. 선미 설비 구역 가까이에 선 카메라가 선미 작업 갑판을 따라 전방의 조타실 출입문을 바라보는 구도이며, 카메라 높이는 갑판에서 약 1.6미터인 성인 눈높이, 28밀리미터 광각 렌즈에 해당하는 자연스러운 원근감이다. 선미에서 조타실 문까지 짧고 막힘없는 이동 경로가 화면의 중심축을 이루고, 양쪽에는 난간과 선체 구조 사이로 이어지는 좁은 측면 통로가 보인다. 조타실 출입문은 급히 드나들 수 있도록 열려 있고, 내부는 저녁의 희미한 실내등과 계기판에서 새어 나오는 약한 빛만 보여 구체적인 화면 정보나 사람은 보이지 않는다. 지도와 사진은 전경의 별도 물체로 두지 않는다. 현대 한국 서해안 소형 선박의 현실적인 구조와 사용 흔적: 바닷물과 작업화로 닳아 미끄럼 방지 무늬가 부분적으로 마모된 도장 강철 갑판, 용접 자국이 남은 금속 난간, 염분 얼룩과 가벼운 녹이 밴 볼라드와 소형 윈치, 안전하게 가장자리로 정리된 굵은 밧줄, 벽면의 구명환, 낮은 방수 갑판등, 알루미늄 새시 조타실 창, 고무 패킹이 닳은 금속 출입문, 지붕 위 통신 안테나와 항해 설비를 사실적으로 표현한다. 이동 중심부에는 발을 걸 만한 장애물이 없고, 작업 장비는 양옆으로 밀려 정리되어 있다. 지나치게 새롭거나 깔끔한 관광선이 아니라 매일 쓰이는 연안 작업선다운 물때, 빗물 자국, 벗겨진 도장, 금속의 염분 부식, 고무와 밧줄의 거친 섬유 질감이 자연스럽게 축적되어 있다. 해 질 무렵의 갑작스러운 소동 상태. 서쪽 하늘의 남은 차가운 청회색 자연광이 갑판과 조타실 외벽에 낮게 퍼지고, 막 켜진 따뜻한 백색 갑판등이 문 주변과 젖은 금속 표면에 제한적으로 반사된다. 바다는 난간 너머로 어둡고 낮게 보이며, 수평선과 멀리 떨어진 항만의 희미한 생활 불빛만 배경에 남는다. 강한 폭풍이나 과장된 파도 없이 실제 서해안 저녁의 습기와 바람, 약간 흔들린 밧줄 끝과 열린 문으로 긴박함을 암시한다. 사람, 얼굴, 신체, 시체, 피, 초자연적 형상은 전혀 배치하지 않는다. 실제 미러리스 또는 디지털 일안 카메라로 촬영한 다큐멘터리 풍 사진, 실제 장소 기록 사진처럼 담담한 촬영, 자연스러운 노출과 색, 후처리 없는 현실적인 저조도 표현, 정확한 금속 녹과 도장 박리, 실제 유리 반사, 고무 패킹, 밧줄 섬유, 젖은 강철의 질감, 과장되지 않은 자연스러운 심도. 정면의 조타실 문까지 공간 관계가 명확하되 완전한 무한 초점처럼 평평하지 않게 표현한다. 깨끗한 광고용 사진, 삽화, 컴퓨터 그래픽, 건축 시각화, 평면도, 하향 시점이 아닌 실제 현장 사진. 16:9 가로 비율, 실제 카메라 촬영본 The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Add the horizontal railing crossing the lower foreground deck to connect the side rails, corresponding to marker 11. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 소형 어선 갑판 SHOT TEXT (authoritative, Korean): 눈을 크게 뜨고 당황한 표정으로 굳어버린 인우의 얼굴 클로즈업. CARRIED STATE (persist exactly): The old photograph remains in Su-ri-yeong’s hand after she shows it to In-woo, while her backpack and other maps remain aboard. The wheelhouse’s numerous circular marks are already present. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 눈을 크게 뜨고 당황한 표정으로 굳어버린 인우의 얼굴 클로즈업. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The old photograph remains in Su-ri-yeong’s hand after she shows it to In-woo, while her backpack and other maps remain aboard. The wheelhouse’s numerous circular marks are already present. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 눈을 크게 뜨고 당황한 표정으로 굳어버린 인우의 얼굴 클로즈업. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The old photograph remains in Su-ri-yeong’s hand after she shows it to In-woo, while her backpack and other maps remain aboard. The wheelhouse’s numerous circular marks are already present. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph In-woo in an intense, eye-level frontal close-up, his face held nearly centered in a rigid, claustrophobic composition. Use a compressed lens feel and extremely shallow focus so his naturally widened eyes and frozen facial tension are razor-sharp while the boat setting falls into soft abstraction. Cool, diffuse dusk light models his features gently, preserving the stunned stillness of the beat. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 눈을 크게 뜨고 당황한 표정으로 굳어버린 인우의 얼굴 클로즈업. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The old photograph remains in Su-ri-yeong’s hand after she shows it to In-woo, while her backpack and other maps remain aboard. The wheelhouse’s numerous circular marks are already present. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Place the camera very close to In-woo at a slight low, off-axis angle, using a broader perspective that gives the close-up immediate, unsettled energy without distorting his anatomy. Frame his face asymmetrically, with a narrow trace of the fishing boat environment receding behind him to create tense depth. Let the remaining dusk light rake softly across one side of his face, emphasizing his arrested expression and fixed, startled gaze. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 눈을 크게 뜨고 당황한 표정으로 굳어버린 인우의 얼굴 클로즈업. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The old photograph remains in Su-ri-yeong’s hand after she shows it to In-woo, while her backpack and other maps remain aboard. The wheelhouse’s numerous circular marks are already present. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph In-woo in an intense, eye-level frontal close-up, his face held nearly centered in a rigid, claustrophobic composition. Use a compressed lens feel and extremely shallow focus so his naturally widened eyes and frozen facial tension are razor-sharp while the boat setting falls into soft abstraction. Cool, diffuse dusk light models his features gently, preserving the stunned stillness of the beat. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 눈을 크게 뜨고 당황한 표정으로 굳어버린 인우의 얼굴 클로즈업. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The old photograph remains in Su-ri-yeong’s hand after she shows it to In-woo, while her backpack and other maps remain aboard. The wheelhouse’s numerous circular marks are already present. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Place the camera very close to In-woo at a slight low, off-axis angle, using a broader perspective that gives the close-up immediate, unsettled energy without distorting his anatomy. Frame his face asymmetrically, with a narrow trace of the fishing boat environment receding behind him to create tense depth. Let the remaining dusk light rake softly across one side of his face, emphasizing his arrested expression and fixed, startled gaze. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Add the navy beanie from the character reference onto In-woo's head. - Remove the landmass and city lights from the right horizon to show only open water. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 3 - camera_cell: [8, 2] - look_at_unit: 1 - look_at_cell: [1, 5] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Use neutral coverage from unit 3 toward unit 1, centered on the committed forward fixed elements while retaining sufficient depth for the close two-subject composition in S29_Shot9.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show the view from unit 3 toward unit 1, with units 1 and 2 available along the geometry-supported sightline. Establish base markers 1, 2, 3, 4, 5, 7, and 9, prioritizing fixed marker 4, furniture marker 5, and the committed openings 7 and 9. - camera_framing_directive: Frame from camera unit 3 at cell [8,2] toward look-at unit 1 at cell [1,5] with a normal 50-degree lens, giving neutral coverage and enough depth for the close foreground and midground relationship committed by S29_Shot9. - subject_position_directive: For S29_Shot9, place the foreground subject in the lower middle-center and the second subject across the first subject's shoulder in the upper-right midground, keeping both on the same restrained focal plane as committed by the staging. - state_cue_directive: No committed state cue beyond clean residential space applies because clean_background_expected is true and no transient markers are listed; refrain from inventing additional state cues. - negative_continuity_directive: Exclude overlay markers 10, 11, and 12 and avoid introducing scenario-specific objects or spaces outside the unit 3 toward unit 1 view. Keep the positions of fixed markers 4 and 5 and committed openings 7 and 9 stable. 2026년 대한민국 서해안에서 실제 운항하는 소형 어선의 비좁은 조타실 내부. 전방 우현의 조타 콘솔 가까이에 선 카메라가 후방을 향해 조타실 중앙의 비어 있는 동선 구역과 후방 출입 문턱, 출입문을 바라본 구도다. 화면 한쪽 전경에는 사용감 있는 조타 콘솔 가장자리와 작은 선박용 조타륜, 스로틀 레버, 나침반, 아날로그 계기와 현대식 GPS 항해 디스플레이, VHF 무전기, 낡은 스위치 패널 일부가 공간 기준점으로 보인다. 중앙 바닥은 두 명의 서 있는 인물을 나중에 배치할 수 있도록 넉넉히 비우고, 배경 사진 자체에는 사람이나 신체를 전혀 넣지 않는다. 후방에는 금속 문턱과 실용적인 출입문, 좁은 통로가 분명히 이어지며, 문 주변의 손잡이와 손때, 긁힘, 염분 얼룩이 자연스럽다. 한국 연안 소형 어선에서 흔한 실용적 구조로, 흰색 또는 옅은 회색으로 칠한 금속·유리섬유 내벽, 오래된 실란트가 보이는 알루미늄 새시 창, 전방 유리창과 와이퍼, 노출된 전선과 케이블 고정구, 작은 수납함, 고정식 선장 의자, 천장의 낮은 방수형 조명이 있다. 깨끗한 신조선이나 관광용 보트가 아니라 실제 작업선답게 도장 벗겨짐, 미세한 녹, 젖은 장화 자국, 기름때, 먼지, 소금기 어린 유리, 반복 사용으로 닳은 플라스틱과 금속 표면을 사실적으로 표현한다. 장비는 2026년의 통상적인 한국 소형 어선 수준이며 미래형 인터페이스나 홀로그램은 없다. 해 질 무렵의 차갑고 흐린 청회색 바깥빛이 창을 통해 약하게 들어오고, 낮은 천장 조명의 둔한 황백색 빛이 일부 계기와 금속 가장자리를 비춘다. 바깥 창 너머로는 어두워지는 서해의 수평선과 흐릿한 항만 또는 해상 빛이 과장 없이 희미하게만 보인다. 직전에 긴박한 일이 벌어진 듯한 답답하고 긴장된 정적은 조명과 비좁은 공간감으로만 전달하되, 파손이나 피, 시신, 사람, 얼굴은 표현하지 않는다. 일시적 사진, 붉은 원형 오버레이, 붉은 표식, 문자, 룬, 마법진, 환영도 넣지 않는다. 실제 미러리스 또는 DSLR 카메라와 35mm급 중간 광각 렌즈로 촬영한 다큐멘터리 풍 사진. 카메라 높이는 서 있는 사람의 눈높이인 약 1.6m이며, 위에서 내려다보는 시점이나 평면도, 건축 도해가 아니다. 실제 콘솔 플라스틱, 금속의 산화와 녹, 고무 패킹, 유리의 염분 얼룩, 직물과 페인트의 마모를 정확하게 보여 주고, 자연스러운 원근과 깊이, 과하지 않은 자연 심도, 현실적인 노출을 유지한다. 실제 장소 기록 사진처럼 담담하고 후처리하지 않은 결과이며, 깔끔한 스톡 사진, 삽화, 3D 렌더, 건축 시각화가 아니다. 16:9 가로 비율, 실제 카메라 촬영본. This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Reverse the camera view to shoot from the rear threshold (Unit 3) looking forward toward the steering console (Unit 1). - Add a fixed captain's chair in the center of the wheelhouse floor. - Move the steering console from the side wall to the front wall to match the floor plan layout. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 소형 어선 조타실 SHOT TEXT (authoritative, Korean): 빛바랜 사진 속 한 여자아이의 얼굴을 손가락 끝으로 짚은 채 멈춘 수리영의 손 클로즈업. CARRIED STATE (persist exactly): Su-ri-yeong holds the same faded photograph and points to the child identified as her mother. The wheelhouse walls remain covered with numerous circular marks, and her backpack stays with her. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 빛바랜 사진 속 한 여자아이의 얼굴을 손가락 끝으로 짚은 채 멈춘 수리영의 손 클로즈업. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong holds the same faded photograph and points to the child identified as her mother. The wheelhouse walls remain covered with numerous circular marks, and her backpack stays with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 빛바랜 사진 속 한 여자아이의 얼굴을 손가락 끝으로 짚은 채 멈춘 수리영의 손 클로즈업. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong holds the same faded photograph and points to the child identified as her mother. The wheelhouse walls remain covered with numerous circular marks, and her backpack stays with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the hand and faded photograph in a tight, near-overhead close-up aligned close to Su-ri-yeong’s viewing axis, keeping the photograph’s front naturally facing her while clearly revealing the girl’s face beneath the arrested fingertip. Hold both fingertip texture and the worn photographic surface in crisp focus, with the wheelhouse falling into a restrained blur of dim dusk tones and soft circular forms. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 빛바랜 사진 속 한 여자아이의 얼굴을 손가락 끝으로 짚은 채 멈춘 수리영의 손 클로즈업. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong holds the same faded photograph and points to the child identified as her mother. The wheelhouse walls remain covered with numerous circular marks, and her backpack stays with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a low, oblique close-up skimming across the plane of the faded photograph, placing Su-ri-yeong’s motionless fingertip prominently in the near foreground and the girl’s face immediately beyond it. Let focus settle on the exact point of contact while the rest falls away quickly, with cool dusk window light grazing the hand and photograph and the wheelhouse’s circular shapes dissolving into distant highlights. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 빛바랜 사진 속 한 여자아이의 얼굴을 손가락 끝으로 짚은 채 멈춘 수리영의 손 클로즈업. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong holds the same faded photograph and points to the child identified as her mother. The wheelhouse walls remain covered with numerous circular marks, and her backpack stays with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the hand and faded photograph in a tight, near-overhead close-up aligned close to Su-ri-yeong’s viewing axis, keeping the photograph’s front naturally facing her while clearly revealing the girl’s face beneath the arrested fingertip. Hold both fingertip texture and the worn photographic surface in crisp focus, with the wheelhouse falling into a restrained blur of dim dusk tones and soft circular forms. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 빛바랜 사진 속 한 여자아이의 얼굴을 손가락 끝으로 짚은 채 멈춘 수리영의 손 클로즈업. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong holds the same faded photograph and points to the child identified as her mother. The wheelhouse walls remain covered with numerous circular marks, and her backpack stays with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a low, oblique close-up skimming across the plane of the faded photograph, placing Su-ri-yeong’s motionless fingertip prominently in the near foreground and the girl’s face immediately beyond it. Let focus settle on the exact point of contact while the rest falls away quickly, with cool dusk window light grazing the hand and photograph and the wheelhouse’s circular shapes dissolving into distant highlights. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Move the pointing fingertip down so it rests directly on the face of the girl in the photograph. - Rotate the photograph so its front side naturally faces the eyes of the character holding it. - Add numerous circular marks to the visible wheelhouse walls in the blurred background. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 1 - camera_cell: [7, 2] - look_at_unit: 2 - look_at_cell: [2, 3] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use the listed unit-1 camera cell and broad coverage toward unit 2, centering the look-at cell associated with base marker 19 while retaining context for target units 1, 2, and 3.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show target units 1, 2, and 3 from unit 1 toward unit 2, with base markers 7, 8, 9, 10, 14, 15, 19, 20, 21, and 22 positioned according to the floor-plan readback. Treat the geometry's other visible units and openings only as supersets, not mandatory content. - camera_framing_directive: Use broad 90-degree coverage from camera unit 1 at cell [7,2], looking toward unit 2 at cell [2,3]; preserve enough surrounding context for target units 1, 2, and 3 while allowing the consuming shots to crop toward their committed close and insert scales. - subject_position_directive: For S5_Shot9, reserve the close foreground for two committed subjects in side-profile alignment, with one slightly forward on the left and the other on the right near frame center. For S5_Shot10, permit an insert crop around the committed forearm and wrist detail; add no other subjects. - state_cue_directive: No committed state cue beyond clean residential space applies. Keep the base elements in their persistent state and refrain from inventing additional cues. - negative_continuity_directive: Exclude overlay markers 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, and 39. Do not add spaces beyond target units 1, 2, and 3 or alter the fixed positions of base markers 7, 8, 9, 10, 14, 15, 19, 20, 21, and 22. 2026년 대한민국 서해안권 도시의 저층 주택 옥상에 증축된 소형 옥탑방 내부. 현관 문턱 가까이에 카메라를 두고 약 1.6m의 서 있는 사람 눈높이에서, 거실 겸 식사 공간을 가로질러 식탁과 간이 주방의 싱크대, TV, 작은 거실 창을 대각선으로 바라본다. 풀프레임 DSLR 또는 미러리스 카메라와 28mm 광각 렌즈로 촬영한 자연스러운 시야이며, 과도한 왜곡 없이 좁은 공간의 실제 비례를 유지한다. 침실 출입문들은 프레임 가장자리에만 부분적으로 보이게 하여 중심 공간을 방해하지 않는다. 작은 식탁과 서로 맞지 않는 실용적인 식탁 의자, 스테인리스 싱크대와 낡은 합판 무늬 하부장, 짧은 조리대, 소형 냉장고, 낮은 TV 받침대 위의 현대식 평면 TV가 서로 가까이 놓인 한국식 옥탑 주거 공간. 현관에는 소형 신발장과 일상적인 신발 정리 흔적이 있고, 바닥은 오래 사용해 잔기스와 광택 차이가 생긴 장판 마감이다. 벽은 밝은색 벽지이지만 모서리와 스위치 주변에 손때와 미세한 변색이 있으며, 천장에는 평범한 현대식 LED 등기구가 달려 있다. 창은 한국 저층 주택에서 흔한 알루미늄 또는 PVC 새시의 작은 미닫이창이고, 얇은 생활용 커튼이 한쪽으로 자연스럽게 걷혀 있다. 바닷바람과 습기에 노출되는 옥탑방답게 창틀과 금속 부분에 약한 산화 흔적, 실리콘 마감의 변색, 벽 아래쪽의 미세한 습기 자국이 있지만 폐가처럼 심하게 훼손되지는 않았다. 평범한 모녀의 일상적인 아침을 암시하는 차분하고 따뜻한 생활감. 식탁 위에는 간단한 아침 식사에 쓰였을 법한 컵과 작은 접시, 티슈 상자 정도만 절제해 놓고, 싱크대 주변에는 세제 용기와 건조 중인 식기처럼 실제 거주자가 사용하는 흔적을 둔다. 공간은 깔끔하게 연출된 전시장이나 고급 주택이 아니라, 제한된 면적을 알뜰하게 사용하는 서민적인 현대 한국 주거 내부여야 한다. 작은 거실 창으로 맑은 아침 햇빛이 비스듬히 들어와 식탁 가장자리와 장판 위에 밝은 사각형을 만들고, 창에서 멀어질수록 부드럽게 어두워지는 자연광을 표현한다. 실내등은 꺼져 있거나 햇빛보다 약하며, 과장된 공포 분위기나 초자연적 상징은 없다. 실제 카메라로 촬영한 다큐멘터리 풍 사진, 실제 장소 답사 사진처럼 사실적이고 담담한 결과. 실제 콘크리트 벽체의 미세한 불균일함, 금속의 사용감과 산화, 커튼의 직물 짜임, 목재 무늬와 장판의 마찰 흔적, 가구 가장자리의 작은 찍힘을 정확하게 표현한다. 자연스러운 화이트 밸런스와 현실적인 노출, 실제 렌즈의 완만한 원근감과 자연스러운 심도를 사용하며 인위적인 후처리나 광고 사진식 정돈은 하지 않는다. 사람, 얼굴, 신체, 실루엣은 전혀 없다. 위에서 내려다본 시점이 아니며 평면도, 건축 도면, 다이어그램, 삽화, 3D 시각화가 아니다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove all floating white text numbers from the image. - Replace the extra window on the far left of the left wall with a solid wall. - Rebuild the right wall to be a single flat, continuous surface with two standard doors appropriately spaced, matching the floor plan. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 오래된 빌라 옥탑방 내부 SHOT TEXT (authoritative, Korean): 수리영이 눈을 감은 채 민숙의 어깨에 코를 묻은 측면 구도 CARRIED STATE (persist exactly): Minsuk is still wearing her apron, and the small circular mark remains on her wrist. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, narrow sunlight through a small window. SHOT TEXT (authoritative, Korean): 수리영이 눈을 감은 채 민숙의 어깨에 코를 묻은 측면 구도 LOCATION (lock): A compact rooftop apartment interior with a small living-room window, a dining table, a sink and stove area, and bedrooms opening off the main space. A pot boils beside herbs being washed at the faucet. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk is still wearing her apron, and the small circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, narrow sunlight through a small window. SHOT TEXT (authoritative, Korean): 수리영이 눈을 감은 채 민숙의 어깨에 코를 묻은 측면 구도 LOCATION (lock): A compact rooftop apartment interior with a small living-room window, a dining table, a sink and stove area, and bedrooms opening off the main space. A pot boils beside herbs being washed at the faucet. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk is still wearing her apron, and the small circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment in an intimate eye-level side-profile close-up, with Suriyoung’s closed eyes and the contact of her nose against Minsuk’s shoulder as the precise focal point. Let Minsuk’s shoulder and apron anchor the frame while the apartment falls into soft, shallow-focus depth; the narrow morning sunlight grazes their profiles with restrained natural contrast. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, narrow sunlight through a small window. SHOT TEXT (authoritative, Korean): 수리영이 눈을 감은 채 민숙의 어깨에 코를 묻은 측면 구도 LOCATION (lock): A compact rooftop apartment interior with a small living-room window, a dining table, a sink and stove area, and bedrooms opening off the main space. A pot boils beside herbs being washed at the faucet. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk is still wearing her apron, and the small circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a restrained medium-wide side-on composition that holds both women within the compact apartment and preserves the full spatial context around their quiet contact. Keep their overlapping profiles visually concentrated against the deeper room, with the dining and kitchen areas remaining legible in layered depth; allow the narrow window light to cut gently through the morning interior while the rest of the room stays softly subdued. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, narrow sunlight through a small window. SHOT TEXT (authoritative, Korean): 수리영이 눈을 감은 채 민숙의 어깨에 코를 묻은 측면 구도 LOCATION (lock): A compact rooftop apartment interior with a small living-room window, a dining table, a sink and stove area, and bedrooms opening off the main space. A pot boils beside herbs being washed at the faucet. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk is still wearing her apron, and the small circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment in an intimate eye-level side-profile close-up, with Suriyoung’s closed eyes and the contact of her nose against Minsuk’s shoulder as the precise focal point. Let Minsuk’s shoulder and apron anchor the frame while the apartment falls into soft, shallow-focus depth; the narrow morning sunlight grazes their profiles with restrained natural contrast. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, narrow sunlight through a small window. SHOT TEXT (authoritative, Korean): 수리영이 눈을 감은 채 민숙의 어깨에 코를 묻은 측면 구도 LOCATION (lock): A compact rooftop apartment interior with a small living-room window, a dining table, a sink and stove area, and bedrooms opening off the main space. A pot boils beside herbs being washed at the faucet. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk is still wearing her apron, and the small circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a restrained medium-wide side-on composition that holds both women within the compact apartment and preserves the full spatial context around their quiet contact. Keep their overlapping profiles visually concentrated against the deeper room, with the dining and kitchen areas remaining legible in layered depth; allow the narrow window light to cut gently through the morning interior while the rest of the room stays softly subdued. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the hallucinated sink and faucet from under the left window; move the herbs to the actual sink next to the stove in the background. - Mirror the characters' placement and poses so that Minsuk stands on the left facing the window, with Suriyoung behind her on the right. - Change Minsuk's top to match the thick light beige crewneck sweater shown in her character reference. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 유기견 보호원 SHOT TEXT (authoritative, Korean): 철망 너머로 로트와일러의 눈을 매섭게 노려보는 수리영의 정면 얼굴 ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 철망 너머로 로트와일러의 눈을 매섭게 노려보는 수리영의 정면 얼굴 LOCATION (lock): A dog shelter with secure enclosures for multiple dogs and a work area for vaccinations, grooming, ointment application, and bathing. The shot takes place here — the attached LOCATION STRUCTURE PHOTOGRAPH is the single authority for this exact place — its fixed structure and permanent site details are LOCKED to it. No separate location photograph exists for this place. Build everything else strictly from the location text above and the shot text; the layout sketch (when attached) governs framing and placement only, and the shot text governs time of day, lighting and action. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 철망 너머로 로트와일러의 눈을 매섭게 노려보는 수리영의 정면 얼굴 LOCATION (lock): A dog shelter with secure enclosures for multiple dogs and a work area for vaccinations, grooming, ointment application, and bathing. The shot takes place here — the attached LOCATION STRUCTURE PHOTOGRAPH is the single authority for this exact place — its fixed structure and permanent site details are LOCKED to it. No separate location photograph exists for this place. Build everything else strictly from the location text above and the shot text; the layout sketch (when attached) governs framing and placement only, and the shot text governs time of day, lighting and action. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph this as a tight, eye-level frontal close-up with rigorous symmetry, compressing the wire mesh against her face while keeping it visually distinct from her skin. Let the Rottweiler register only as a soft, dark foreground presence at the lower edge, directing all attention to her sharply focused eyes and controlled facial tension. Use shallow depth and restrained natural daytime light for an intimate, confrontational stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 철망 너머로 로트와일러의 눈을 매섭게 노려보는 수리영의 정면 얼굴 LOCATION (lock): A dog shelter with secure enclosures for multiple dogs and a work area for vaccinations, grooming, ointment application, and bathing. The shot takes place here — the attached LOCATION STRUCTURE PHOTOGRAPH is the single authority for this exact place — its fixed structure and permanent site details are LOCKED to it. No separate location photograph exists for this place. Build everything else strictly from the location text above and the shot text; the layout sketch (when attached) governs framing and placement only, and the shot text governs time of day, lighting and action. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot from a lower, Rottweiler-eye-height position in a wider layered composition, with the dog’s head and eyes forming a forceful near foreground, the wire mesh defining the middle plane, and her frontal face held beyond it. Use deeper focus so the locked exchange of gazes and the physical separation remain simultaneously legible, while the enclosure structure creates firm converging lines around her. Shape the available daytime light with stronger contrast across the planes, giving the moment a tense, watchful spatial realism. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 철망 너머로 로트와일러의 눈을 매섭게 노려보는 수리영의 정면 얼굴 LOCATION (lock): A dog shelter with secure enclosures for multiple dogs and a work area for vaccinations, grooming, ointment application, and bathing. The shot takes place here — the attached LOCATION STRUCTURE PHOTOGRAPH is the single authority for this exact place — its fixed structure and permanent site details are LOCKED to it. No separate location photograph exists for this place. Build everything else strictly from the location text above and the shot text; the layout sketch (when attached) governs framing and placement only, and the shot text governs time of day, lighting and action. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph this as a tight, eye-level frontal close-up with rigorous symmetry, compressing the wire mesh against her face while keeping it visually distinct from her skin. Let the Rottweiler register only as a soft, dark foreground presence at the lower edge, directing all attention to her sharply focused eyes and controlled facial tension. Use shallow depth and restrained natural daytime light for an intimate, confrontational stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 철망 너머로 로트와일러의 눈을 매섭게 노려보는 수리영의 정면 얼굴 LOCATION (lock): A dog shelter with secure enclosures for multiple dogs and a work area for vaccinations, grooming, ointment application, and bathing. The shot takes place here — the attached LOCATION STRUCTURE PHOTOGRAPH is the single authority for this exact place — its fixed structure and permanent site details are LOCKED to it. No separate location photograph exists for this place. Build everything else strictly from the location text above and the shot text; the layout sketch (when attached) governs framing and placement only, and the shot text governs time of day, lighting and action. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot from a lower, Rottweiler-eye-height position in a wider layered composition, with the dog’s head and eyes forming a forceful near foreground, the wire mesh defining the middle plane, and her frontal face held beyond it. Use deeper focus so the locked exchange of gazes and the physical separation remain simultaneously legible, while the enclosure structure creates firm converging lines around her. Shape the available daytime light with stronger contrast across the planes, giving the moment a tense, watchful spatial realism. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Move the Rottweiler to the bottom left foreground to match the layout sketch's placement. - Redirect Suri-young's eyes downward and to the side so she is glaring directly at the Rottweiler's eyes. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
2026년 대한민국 서해안권 중소도시의 해 질 무렵, 영업 중인 동네 마트 자동문 출구를 실제 장소에서 촬영한 다큐멘터리 풍 사진. 카메라는 출구 바로 바깥 보행로의 사람 눈높이 약 1.6m에 놓이고, 실제 DSLR 또는 미러리스 카메라의 35mm급 렌즈로 자동문 문턱을 약간 비스듬히 바라본다. 센서가 작동해 투명 유리 자동문 두 장이 부분적으로 열린 순간이며, 금속 문틀과 상부 센서, 고무 가장자리, 출입구 바닥 매트와 닳은 문턱이 정확히 보인다. 통화하며 밖으로 나오는 인물이 들어갈 수 있도록 문 앞과 화면 중앙 오른쪽에 비어 있는 자연스러운 동선을 확보하되, 사진 자체에는 사람과 얼굴이 전혀 없다. 마트 내부는 현재 정상 영업 중인 상태로, 흰색 형광등과 실용적인 LED 천장등이 켜져 있고 계산대 일부, 생활용품과 포장 식품이 놓인 금속 진열대, 장바구니 거치대와 겹쳐 둔 쇼핑카트가 자동문 너머로 보인다. 유리에는 내부 조명과 푸른 회색 저녁 하늘이 약하게 겹쳐 반사되며, 내부가 완전히 가려지지 않을 정도의 현실적인 반사 강도를 유지한다. 천장 모서리에는 소형 CCTV 카메라가 있고, 출구 주변에는 인쇄물이 교체된 흔적이 남은 일반적인 행사 안내판이 있으나 읽을 수 없는 임의의 상호, 유명 브랜드 로고, 과장된 디지털 화면은 넣지 않는다. 외부는 서해안권 도시의 저층 주거·상가 혼합 골목에서 흔히 볼 수 있는 실물 전형이다. 마트가 들어선 건물은 오래 사용한 붉은 벽돌 또는 작은 석재 타일 외벽과 알루미늄 새시 출입구, 빛바랜 차양을 갖춘 현실적인 근린상가이며, 외벽 한쪽에 에어컨 실외기와 노출 배관, 가스·전기 설비 배관이 정돈되지 않은 채 이어져 있다. 프레임 가장자리에는 이웃 저층 주택의 새시 창, 방범창, 좁은 골목의 전신주와 늘어진 전선 일부가 자연스럽게 보이게 하여 건물이 고립된 콘크리트 덩어리처럼 보이지 않게 한다. 출입구 앞에는 생활 흠집이 난 금속 볼라드와 작은 먼지, 바퀴 자국, 염분 섞인 해안 공기로 약간 탁해진 유리, 닳은 페인트 등 실제 영업 공간의 사용 흔적을 담는다. 외부는 일몰 직후의 낮은 청회색 자연광, 내부는 따뜻하지 않은 중성 백색 매장 조명으로 표현하고, 문턱에서 두 광원이 현실적으로 섞이게 한다. 과도하게 어둡거나 공포 장식이 있는 공간이 아니라 일상적으로 운영되는 현대 한국 마트이며, 긴장감은 비어 있는 출구와 저녁의 밝기 차이에서만 은근히 느껴진다. 실제 콘크리트, 유리, 알루미늄, 고무 매트, 벽돌, 플라스틱 바구니의 재질과 마모를 정확히 표현하고 자연스러운 피사계 심도와 현실적인 노출을 사용한다. 깨끗한 스톡 사진이 아니라 실제 장소 기록 사진처럼 담담하고 생활감 있게, 후처리 없는 실제 카메라 촬영본. 삽화, 회화, 3D 렌더, 건축 시각화, 평면도, 도식, 탑다운 시점이 아니다. 사람, 얼굴, 시신, 혈흔 없음. 16:9 가로 비율, 실제 카메라 촬영본. One attached image is a PHOTOREAL RENDER of this SAME place — the same physical location, possibly seen from a different angle or at a different moment. Treat it as the PLACE IDENTITY reference. Keep this render consistent with it: the same spatial layout and architecture, the same surface materials and colors, and the same permanently installed fixtures, furniture and signage. Signage follows the place's nature: a commercial or public facility keeps its signage present and legible; a residential or private place has none unless the prompt says so. Reproduce any signage visible in the reference EXACTLY — same lettering, same design, same position; never invent different sign text from render to render. Camera angle, framing, lighting, time of day and weather follow THIS prompt — do NOT copy the reference's composition or mood; only the place's physical identity carries over.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the invented text signs and blue stickers from the glass doors and windows to match the reference's clear glass. - Add a utility pole and drooping wires in the background alley on the right side of the frame. - Place a scratched metal bollard on the concrete ground in front of the entrance. - Add the white air curtain unit above the interior side of the automatic doors, making it visible through the upper glass. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 대형 마트 매장 내부 SHOT TEXT (authoritative, Korean): 마트 자동문 밖에 서서 휴대폰을 귀에 댄 수리영의 상체 CARRIED STATE (persist exactly): Her bicycle remains outside the mart while Su-ri-yeong holds her mobile phone to her ear and again tries to reach Minsuk. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 자동문 밖에 서서 휴대폰을 귀에 댄 수리영의 상체 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Her bicycle remains outside the mart while Su-ri-yeong holds her mobile phone to her ear and again tries to reach Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 자동문 밖에 서서 휴대폰을 귀에 댄 수리영의 상체 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Her bicycle remains outside the mart while Su-ri-yeong holds her mobile phone to her ear and again tries to reach Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight eye-level medium close-up from outside, with her upper torso dominant and the automatic doorway forming a restrained, nearly symmetrical boundary behind her. Use shallow depth of field so the dusk street and neon resolve into soft colored highlights, while mixed storefront spill and cool ambient light model her face naturally. Keep the visual emphasis on her concentrated listening posture and the phone held correctly against her ear. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 자동문 밖에 서서 휴대폰을 귀에 댄 수리영의 상체 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Her bicycle remains outside the mart while Su-ri-yeong holds her mobile phone to her ear and again tries to reach Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her obliquely from just inside the supermarket, cropping to the upper body and holding her in a clean three-quarter profile beyond the automatic door. Use the glass, door frame, and receding interior and exterior planes to create layered depth, with faint neon reflections adding visual tension without obscuring her face. Favor a moderately deep focus and balanced dusk-to-interior illumination so the threshold itself becomes the compositional emphasis. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 자동문 밖에 서서 휴대폰을 귀에 댄 수리영의 상체 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Her bicycle remains outside the mart while Su-ri-yeong holds her mobile phone to her ear and again tries to reach Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight eye-level medium close-up from outside, with her upper torso dominant and the automatic doorway forming a restrained, nearly symmetrical boundary behind her. Use shallow depth of field so the dusk street and neon resolve into soft colored highlights, while mixed storefront spill and cool ambient light model her face naturally. Keep the visual emphasis on her concentrated listening posture and the phone held correctly against her ear. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, neon signs visible. SHOT TEXT (authoritative, Korean): 마트 자동문 밖에 서서 휴대폰을 귀에 댄 수리영의 상체 LOCATION (lock): A busy commercial district beside a harbor, crowded with neon signs, taxis, street vendors, and food tents, leading into a large supermarket with merchandise aisles and stocking areas. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Her bicycle remains outside the mart while Su-ri-yeong holds her mobile phone to her ear and again tries to reach Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her obliquely from just inside the supermarket, cropping to the upper body and holding her in a clean three-quarter profile beyond the automatic door. Use the glass, door frame, and receding interior and exterior planes to create layered depth, with faint neon reflections adding visual tension without obscuring her face. Favor a moderately deep focus and balanced dusk-to-interior illumination so the threshold itself becomes the compositional emphasis. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Reframe the background so the automatic doorway forms a nearly symmetrical boundary directly behind the character's torso. - Remove the unprompted human figure visible inside the mart through the glass on the left. - Remove all recognizable text characters from the neon signs in the background, leaving only abstract glowing shapes. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows a related part of the same dwelling, not the current room. Inherit the overall material and lighting identity only; the new space is its own architectural room and must read as the same home. REFERENCE PLAN: mode='related_style_new_space' - selected_refs[0]: ref_bg_id='L05B02' physical_space_id='ps_shared_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [4, 3] - look_at_unit: 5 - look_at_cell: [6, 8] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use broad coverage from unit 2 toward unit 5, looking at listed cell [6,8] associated with base marker 24 so marker 10 and the unit-5 fixed markers can establish a clean representative view.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show target unit 5 from unit 2 through the marker-10 connection, with base markers 12, 24, and 25 fixed according to the floor plan. Include unit-2 marker 19 only where supported by the broad view. - camera_framing_directive: Use broad 90-degree coverage from camera unit 2 at [4,3] toward unit 5 at [6,8]. Establish marker 24 as the principal look-at anchor while retaining marker 10 and enough unit-5 context for markers 12 and 25 and for the close crop in S14_Shot4. - subject_position_directive: S14_Shot3 commits no subject, so keep the broad background free of invented subjects. For S14_Shot4, place the single committed subject in a tight three-quarter view on the right, with the marker-12 area remaining softly legible on the left. - state_cue_directive: No committed state cue beyond clean residential space applies. Keep base markers 2, 5, 10, 12, 19, 24, and 25 in their persistent clean state and refrain from inventing additional cues. - negative_continuity_directive: Do not import the fixed furniture arrangement of units 1 and 3 from L05B02 into unit 5. Exclude overlay markers 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, and 39, and do not add unlisted state cues or spaces beyond targets 2 and 5. 2026년 대한민국 서해안권 도시의 옥상 주거 공간 안에 있는 작고 소박한 딸 방을 촬영한 실제 카메라 다큐멘터리 풍 사진. 딸 방 출입문 바로 안쪽 가까운 위치에서 약 1.6미터의 서 있는 사람 눈높이로, 풀프레임 미러리스 카메라와 30밀리미터 광각 렌즈를 사용해 방 안을 대각선으로 바라본다. 시선은 방 안쪽의 침대와 커튼이 달린 현대식 새시 창문을 향하며, 열린 출입문 가장자리 너머로 인접 공간의 깨끗한 식탁 일부가 자연스럽게 보인다. 침대는 사람이 방금 정리한 수준을 넘어 비정상적으로 반듯하고 흐트러짐이 없으며, 실제 섬유 조직이 보이는 평범한 침구에는 주름, 먼지, 얼룩이 거의 없다. 바닥은 작은 먼지나 머리카락, 끌린 자국조차 없이 깨끗하고, 벽도 닦아 낸 자국이나 변색 경계 없이 지나치게 말끔하다. 커튼은 실제 직물의 무게와 잔주름을 지니지만 창 주변과 커튼 안쪽의 오목한 공간에는 물건, 얼룩, 잔해가 전혀 없어 텅 빈 상태가 강조된다. 이전에 존재했을 법한 피, 신체, 붉은 원형 상징, 문자, 의식 흔적, 파손, 흩어진 물건은 현재 공간에 단 하나도 남아 있지 않으며, 지워진 자국이나 청소 흔적조차 보이지 않는다. 현대 한국의 소규모 옥상방에 어울리는 실용적인 마감, 평범한 도장 벽, 합성 바닥재, 금속과 플라스틱이 섞인 새시 창호를 사실적으로 표현한다. 밤의 실내로, 천장 생활 조명의 낮고 균일한 빛과 커튼 틈으로 스며드는 희미한 도시 야간광이 섞이며 과도한 장식 없이 차갑고 불편할 만큼 정돈된 분위기를 만든다. 실제 벽 도장의 미세한 요철, 바닥재의 약한 반사, 금속 창틀의 사용감, 커튼의 직물 짜임, 침구의 자연스러운 재질을 정확히 담고, 생활 공간 특유의 미세한 마모는 남기되 최근의 사건 흔적은 전혀 남기지 않는다. 자연스러운 원근과 깊이감, 현실적인 노출과 피사계 심도, 과장 없는 색, 후처리 없는 현장 기록 사진. 깨끗한 광고 사진이나 인테리어 화보가 아니라 실제 장소를 사실대로 기록한 무심한 사진이며, 컴퓨터 그래픽이나 삽화가 아니다. 하향식 시점, 평면도, 건축 도식은 금지한다. 사람과 얼굴은 등장하지 않는다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 오래된 빌라 옥탑방 내부 SHOT TEXT (authoritative, Korean): 살점이 뜯겨 피가 흘러내리는 끔찍한 상처를 입은 채 바닥에 앉아 고개를 떨군 민숙의 상체. IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Min-suk is seated on the floor behind the curtain with her torso slumped and her head dropped forward; one cold, stiff hand remains clenched around a crumpled old photograph. CARRIED STATE (persist exactly): Minsuk’s corpse remains seated on the floor behind the curtain with her torso slumped and her head dropped forward, her shoulder and collarbone torn and bleeding. One cold, stiff hand remains clenched around a crumpled old photograph, and the circular mark remains on her wrist. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 살점이 뜯겨 피가 흘러내리는 끔찍한 상처를 입은 채 바닥에 앉아 고개를 떨군 민숙의 상체. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Min-suk is seated on the floor behind the curtain with her torso slumped and her head dropped forward; one cold, stiff hand remains clenched around a crumpled old photograph. IMMOBILE BODIES OBEY GRAVITY: a person who is dead or unconscious exerts NO muscular effort. Every part of their body — head, torso, arms, hands, fingers, legs — rests fully on whatever supports it (floor, wall, furniture, their own lap) and hangs or slumps with gravity. NEVER show any part of an immobile person's body lifted, raised, held up in the air, or posed as if presenting something: an object in their grip stays clenched in a hand that itself lies fallen on a support — the hand does not hold the object up. If the canonical pose leaves a body part unspecified, resolve it as the most gravity-compliant, fully-supported position. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk’s corpse remains seated on the floor behind the curtain with her torso slumped and her head dropped forward, her shoulder and collarbone torn and bleeding. One cold, stiff hand remains clenched around a crumpled old photograph, and the circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 살점이 뜯겨 피가 흘러내리는 끔찍한 상처를 입은 채 바닥에 앉아 고개를 떨군 민숙의 상체. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Min-suk is seated on the floor behind the curtain with her torso slumped and her head dropped forward; one cold, stiff hand remains clenched around a crumpled old photograph. IMMOBILE BODIES OBEY GRAVITY: a person who is dead or unconscious exerts NO muscular effort. Every part of their body — head, torso, arms, hands, fingers, legs — rests fully on whatever supports it (floor, wall, furniture, their own lap) and hangs or slumps with gravity. NEVER show any part of an immobile person's body lifted, raised, held up in the air, or posed as if presenting something: an object in their grip stays clenched in a hand that itself lies fallen on a support — the hand does not hold the object up. If the canonical pose leaves a body part unspecified, resolve it as the most gravity-compliant, fully-supported position. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk’s corpse remains seated on the floor behind the curtain with her torso slumped and her head dropped forward, her shoulder and collarbone torn and bleeding. One cold, stiff hand remains clenched around a crumpled old photograph, and the circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her upper body in a tight, floor-level frontal close shot, with the dropped head dominating the upper frame and the torn, bleeding shoulder and collarbone held in stark visual emphasis. Keep the curtain close to the frame edge for a claustrophobic enclosure, using shallow focus and the uneven television-and-lamp glow to model her slumped weight and cold stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 살점이 뜯겨 피가 흘러내리는 끔찍한 상처를 입은 채 바닥에 앉아 고개를 떨군 민숙의 상체. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Min-suk is seated on the floor behind the curtain with her torso slumped and her head dropped forward; one cold, stiff hand remains clenched around a crumpled old photograph. IMMOBILE BODIES OBEY GRAVITY: a person who is dead or unconscious exerts NO muscular effort. Every part of their body — head, torso, arms, hands, fingers, legs — rests fully on whatever supports it (floor, wall, furniture, their own lap) and hangs or slumps with gravity. NEVER show any part of an immobile person's body lifted, raised, held up in the air, or posed as if presenting something: an object in their grip stays clenched in a hand that itself lies fallen on a support — the hand does not hold the object up. If the canonical pose leaves a body part unspecified, resolve it as the most gravity-compliant, fully-supported position. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk’s corpse remains seated on the floor behind the curtain with her torso slumped and her head dropped forward, her shoulder and collarbone torn and bleeding. One cold, stiff hand remains clenched around a crumpled old photograph, and the circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a steep high-angle view from slightly to the side, looking down on her collapsed upper body behind the curtain. Build the composition from the bowed head through the injured shoulder to the fully supported clenched hand and crumpled photograph, with restrained depth and dim television and lamp light creating a detached, forensic stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 살점이 뜯겨 피가 흘러내리는 끔찍한 상처를 입은 채 바닥에 앉아 고개를 떨군 민숙의 상체. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Min-suk is seated on the floor behind the curtain with her torso slumped and her head dropped forward; one cold, stiff hand remains clenched around a crumpled old photograph. IMMOBILE BODIES OBEY GRAVITY: a person who is dead or unconscious exerts NO muscular effort. Every part of their body — head, torso, arms, hands, fingers, legs — rests fully on whatever supports it (floor, wall, furniture, their own lap) and hangs or slumps with gravity. NEVER show any part of an immobile person's body lifted, raised, held up in the air, or posed as if presenting something: an object in their grip stays clenched in a hand that itself lies fallen on a support — the hand does not hold the object up. If the canonical pose leaves a body part unspecified, resolve it as the most gravity-compliant, fully-supported position. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk’s corpse remains seated on the floor behind the curtain with her torso slumped and her head dropped forward, her shoulder and collarbone torn and bleeding. One cold, stiff hand remains clenched around a crumpled old photograph, and the circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her upper body in a tight, floor-level frontal close shot, with the dropped head dominating the upper frame and the torn, bleeding shoulder and collarbone held in stark visual emphasis. Keep the curtain close to the frame edge for a claustrophobic enclosure, using shallow focus and the uneven television-and-lamp glow to model her slumped weight and cold stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 살점이 뜯겨 피가 흘러내리는 끔찍한 상처를 입은 채 바닥에 앉아 고개를 떨군 민숙의 상체. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Min-suk is seated on the floor behind the curtain with her torso slumped and her head dropped forward; one cold, stiff hand remains clenched around a crumpled old photograph. IMMOBILE BODIES OBEY GRAVITY: a person who is dead or unconscious exerts NO muscular effort. Every part of their body — head, torso, arms, hands, fingers, legs — rests fully on whatever supports it (floor, wall, furniture, their own lap) and hangs or slumps with gravity. NEVER show any part of an immobile person's body lifted, raised, held up in the air, or posed as if presenting something: an object in their grip stays clenched in a hand that itself lies fallen on a support — the hand does not hold the object up. If the canonical pose leaves a body part unspecified, resolve it as the most gravity-compliant, fully-supported position. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk’s corpse remains seated on the floor behind the curtain with her torso slumped and her head dropped forward, her shoulder and collarbone torn and bleeding. One cold, stiff hand remains clenched around a crumpled old photograph, and the circular mark remains on her wrist. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a steep high-angle view from slightly to the side, looking down on her collapsed upper body behind the curtain. Build the composition from the bowed head through the injured shoulder to the fully supported clenched hand and crumpled photograph, with restrained depth and dim television and lamp light creating a detached, forensic stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the camera framing to a tight, floor-level close-up shot focused exclusively on the character's upper body. - Modify the clothing and skin at the shoulder and collarbone to reveal a gruesome, bleeding wound with torn flesh. - Replace the folded white paper item in the character's left hand with a crumpled, old photograph. - Adjust the right hand resting on the floor so it lies completely flat and limp, showing zero muscular tension. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows the SAME physical room as this background, from a different camera angle or framing. Inherit the exact architecture, floor, walls, windows, fixed furniture and lighting of that room — this is literally the same space, only the viewpoint changes. REFERENCE PLAN: mode='same_physical_space_view' - selected_refs[0]: ref_bg_id='L05B02' physical_space_id='ps_shared_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [4, 3] - look_at_unit: 6 - look_at_cell: [7, 5] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Use neutral coverage from unit 2 toward unit 6, with the listed look-at cell [7,5] anchoring base marker 17 and allowing shot-specific crops around markers 11, 17, 18, and 19.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Frame target unit 6 from camera unit 2, retaining the unit-2 connection and base markers 11, 17, 18, and 19 where each consuming shot requires them. The new view must keep marker 19 consistent with L05B02 while establishing the fixed unit-6 marker positions from the floor plan. - camera_framing_directive: Use neutral 50-degree coverage from camera unit 2 at [4,3] toward unit 6 at [7,5]. Preserve the unit-2-to-unit-6 axis for the medium mirror-mediated composition in S18_Shot8, while allowing S18_Shot10 to crop tightly to its committed surface and marker-19 context. - subject_position_directive: For S18_Shot8, reserve the lower-left foreground for the committed over-shoulder subject while marker 32 remains sharply legible near middle-right in the mediated view. For S18_Shot10, use only the committed pictured subject content within the close surface and avoid adding a physical subject to the surrounding background. - state_cue_directive: Apply transient markers 32 and 33 only in the shot-specific mediated or content surfaces committed by S18_Shot8 and S18_Shot10. Keep all other visible structure in its persistent state and add no unlisted cues. - negative_continuity_directive: Maintain the L05B02 position of base marker 19 and the floor-plan positions of markers 11, 17, and 18. Exclude overlay markers 27, 28, 29, 30, 31, 34, 35, 36, 37, 38, and 39, and do not pull units outside 2 and 6 into the neutral view. 2026년 대한민국 서해안권 도시 또는 고립된 섬의 오래된 저층 옥상 주거에 마련된 작고 생활감 있는 실내. 욕실 문 가까이에 카메라를 두고 약 1.6m의 서 있는 사람 눈높이에서 35mm급 적당한 광각 렌즈로 바라본다. 주 시선은 문 안쪽의 작은 세면대, 수도꼭지, 거울과 바닥의 샤워 배수구를 향하고, 열린 출입구와 공간의 깊이를 따라 거실의 소박한 식탁, 의자와 액자 사진이 보조 시선축에 자연스럽게 걸리게 한다. 평면도처럼 위에서 내려다보지 말고 실제 좁은 주택 내부에서 촬영한 원근과 높이를 유지한다. 현대 한국의 소형 옥상 주거에서 흔한 실용적 마감: 습기에 조금 누렇게 변색된 밝은 타일 욕실 벽, 오래 사용한 실리콘 코킹과 옅은 물때, 스테인리스 수전의 미세한 얼룩, 플라스틱 배수구 덮개, 문틀의 생활 흠집, 거실의 장판 바닥, 저렴한 합판 또는 멜라민 식탁, 알루미늄 새시 창문. 해안의 습기와 염분 때문에 금속 모서리에 아주 약한 부식과 사용 흔적이 있고, 공간은 정돈되어 있으나 새집이나 광고용 인테리어처럼 완벽하게 깨끗하지 않다. 창으로 들어오는 흐린 낮빛과 평범한 천장등의 약한 보조광이 섞이며, 낮은 중간 밝기와 절제된 회색·베이지색 해안 중성색이 중심이다. 이 배경은 동일한 구조에서 발생하는 두 개의 별도 순간을 지원한다. 첫 순간에는 욕실 벽 또는 거울 반사면 내부에만 손이나 붓으로 한 번 그린 듯 두께가 고르지 않은 짙은 붉은 원이 잠시 나타난다. 기하학적으로 완벽한 디지털 원이 아니며 문자, 룬, 장식, 복합 마법진, 과도한 빛을 동반하지 않는다. 물리적으로 굳은 페인트 자국이 아니라 곧 사라질 관찰자 중심의 지각 현상처럼 보여야 하며, 거울 밖 공간에는 어떤 형상도 추가하지 않는다. 두 번째 순간에는 거실 식탁 주변의 액자 사진 인화면 안에서만 얼굴 자리로 추정되는 부분이 습기와 열로 사진 유제가 녹아 번진 것처럼 아래로 흐르며 식별 불가능해진다. 사람이나 알아볼 수 있는 얼굴을 묘사하지 말고, 사진 속 변형은 액자 경계 밖으로 나오지 않는다. 두 이상 현상은 한 프레임에 동시에 나타나거나 공간에 영구적으로 남지 않는 서로 다른 일시적 상태로 취급한다. 사람, 얼굴, 시신, 피는 전혀 없다. 실제 콘크리트와 타일, 금속의 미세한 녹과 물때, 직물의 짜임, 목재와 합판의 결, 장판의 눌림과 일상적인 얼룩을 정확하게 표현한다. 실제 DSLR 또는 미러리스 카메라로 촬영한 다큐멘터리 풍 사진, 실제 장소 참고 사진처럼 사실적이고 담담한 기록 사진, 자연스러운 심도와 광학적 원근, 과도한 후보정 없음. 깨끗한 스톡 사진, 삽화, CGI, 3D 렌더, 건축 시각화, 평면도, 도식이 아니다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Relocate the window from the far wall to the left wall, positioned above the TV, to match the reference layout. - Restore the kitchen counter, sink, and stove to the far wall of the living room space. - Remove the framed photograph from the living room wall so that only the red circle anomaly remains in the frame. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 오래된 빌라 옥탑방 내부 SHOT TEXT (authoritative, Korean): 수리영의 어깨 너머로 거울에 반사된 욕실 타일 벽면에 피처럼 붉은색 원형 표식이 선명하게 떠오른 정지 구도. CARRIED STATE (persist exactly): Su-ri-yeong now carries her doll-adorned backpack and still has her mobile phone. A vivid red circle is temporarily visible on the reflected bathroom wall. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 수리영의 어깨 너머로 거울에 반사된 욕실 타일 벽면에 피처럼 붉은색 원형 표식이 선명하게 떠오른 정지 구도. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong now carries her doll-adorned backpack and still has her mobile phone. A vivid red circle is temporarily visible on the reflected bathroom wall. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 수리영의 어깨 너머로 거울에 반사된 욕실 타일 벽면에 피처럼 붉은색 원형 표식이 선명하게 떠오른 정지 구도. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong now carries her doll-adorned backpack and still has her mobile phone. A vivid red circle is temporarily visible on the reflected bathroom wall. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a tight, eye-level over-the-shoulder composition, with Su-ri-yeong’s shoulder occupying a substantial soft-edged foreground and the mirror reflection dominating the frame. Hold crisp focus on the vivid red circular mark against the reflected bathroom tiles while letting the near shoulder fall gently out of focus. Keep the camera static and the illumination cool, soft, and restrained, creating an intimate moment of recognition. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 수리영의 어깨 너머로 거울에 반사된 욕실 타일 벽면에 피처럼 붉은색 원형 표식이 선명하게 떠오른 정지 구도. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong now carries her doll-adorned backpack and still has her mobile phone. A vivid red circle is temporarily visible on the reflected bathroom wall. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment as a wider, formally locked composition from just behind Su-ri-yeong, using the mirror frame and tiled grid as strong rectilinear geometry. Keep her shoulder at the edge of the foreground while preserving clear depth through the mirror to the reflected wall, placing the vivid red circle as the composition’s stark visual anchor. Use even, low-contrast early-morning illumination and a still, observational camera to make the mark feel disturbingly undeniable. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 수리영의 어깨 너머로 거울에 반사된 욕실 타일 벽면에 피처럼 붉은색 원형 표식이 선명하게 떠오른 정지 구도. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong now carries her doll-adorned backpack and still has her mobile phone. A vivid red circle is temporarily visible on the reflected bathroom wall. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a tight, eye-level over-the-shoulder composition, with Su-ri-yeong’s shoulder occupying a substantial soft-edged foreground and the mirror reflection dominating the frame. Hold crisp focus on the vivid red circular mark against the reflected bathroom tiles while letting the near shoulder fall gently out of focus. Keep the camera static and the illumination cool, soft, and restrained, creating an intimate moment of recognition. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 수리영의 어깨 너머로 거울에 반사된 욕실 타일 벽면에 피처럼 붉은색 원형 표식이 선명하게 떠오른 정지 구도. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong now carries her doll-adorned backpack and still has her mobile phone. A vivid red circle is temporarily visible on the reflected bathroom wall. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment as a wider, formally locked composition from just behind Su-ri-yeong, using the mirror frame and tiled grid as strong rectilinear geometry. Keep her shoulder at the edge of the foreground while preserving clear depth through the mirror to the reflected wall, placing the vivid red circle as the composition’s stark visual anchor. Use even, low-contrast early-morning illumination and a still, observational camera to make the mark feel disturbingly undeniable. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Redraw the right hand with correct anatomy, and rotate the phone so its screen faces the character's eyes, showing its back to the camera. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
2026년 대한민국 서해안권의 도시와 섬 생활권에서 볼 수 있는 소규모 동네 마트 외벽의 감시카메라 설치 구역. 인적이 끊긴 고요한 이른 아침이며, 해가 막 뜨기 전후의 차갑고 옅은 자연광이 낮은 밝기로 골목과 외벽을 고르게 비춘다. 마트는 붉은 벽돌과 회색 석재 타일, 부분적으로 덧댄 금속 패널이 혼재된 현실적인 저층 상가 건물이며, 닫힌 금속 롤링 셔터와 유리 출입문, 빛이 꺼진 평범한 상점 간판이 보인다. 외벽 상단에는 현대식 고정형 감시카메라가 금속 브래킷으로 설치되어 있고, 카메라에서 이어지는 검은 케이블과 회색 노출 배선관이 방수 접속함으로 연결된다. 고정 나사 주변의 옅은 녹, 케이블 타이와 실리콘 방수 처리, 염분이 말라붙은 얼룩, 빗물 자국, 미세한 균열과 부분 보수 흔적을 사실적으로 표현한다. 작은 외벽 보안등은 새벽빛 속에서 희미하게 켜져 있거나 막 꺼질 듯한 상태이며, 공상과학 장비나 과장된 인터페이스는 없다. 프레임 가장자리와 골목 너머에는 같은 지역의 실제 저층 주거지가 자연스럽게 이어진다. 붉은 벽돌 또는 화강석 타일 외벽, 알루미늄 새시 창문과 방범창, 에어컨 실외기와 외벽 배관, 도시가스 배관과 계량기, 옥상의 바랜 녹색 우레탄 방수층과 덧칠 자국, 작은 물탱크가 보인다. 좁은 골목에는 전신주와 처진 전선, 화분과 생활 잡동사니, 빨래줄, 멀리 주차된 소형 생활 차량이 있어 사람이 실제 거주하는 동네의 층층이 쌓인 흔적을 보여준다. 대상 건물은 주변과 단절된 요새처럼 보이지 않고 오래 사용된 상가와 주택 사이에 자연스럽게 섞여 있어야 한다. 바닷바람에 노출된 금속의 가벼운 부식과 콘크리트 하단의 습기 얼룩을 절제되게 반영한다. 사람, 얼굴, 인체, 시체는 전혀 없다. 지면에서 약 1.6미터 높이의 서 있는 사람 눈높이에서 35밀리미터급 렌즈를 장착한 실제 DSLR 또는 미러리스 카메라로 촬영한 다큐멘터리 풍 사진. 감시카메라 설치부와 마트 출입구, 주변 골목의 관계가 자연스럽게 읽히는 수평 시점이며, 위에서 내려다보는 시점이나 평면도, 건축 도면이 아니다. 실제 벽돌, 석재, 콘크리트, 도장 금속, 고무 케이블과 유리의 정확한 질감, 일상적인 마모와 오염, 자연스러운 원근과 피사계 심도. 깨끗한 광고용 사진이 아니라 보정하지 않은 실제 장소 기록 사진처럼 표현한다. 16:9 가로 비율, 실제 카메라 촬영본 One attached image is a PHOTOREAL RENDER of this SAME place — the same physical location, possibly seen from a different angle or at a different moment. Treat it as the PLACE IDENTITY reference. Keep this render consistent with it: the same spatial layout and architecture, the same surface materials and colors, and the same permanently installed fixtures, furniture and signage. Signage follows the place's nature: a commercial or public facility keeps its signage present and legible; a residential or private place has none unless the prompt says so. Reproduce any signage visible in the reference EXACTLY — same lettering, same design, same position; never invent different sign text from render to render. Camera angle, framing, lighting, time of day and weather follow THIS prompt — do NOT copy the reference's composition or mood; only the place's physical identity carries over.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the entrance doors to full-length clear glass sliding doors without solid lower panels or metal grilles to match the reference. - Dim the glare and brightness of the exterior security light significantly so it appears barely lit. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 대형 마트 매장 내부 SHOT TEXT (authoritative, Korean): 마트 외부 건물 벽에 달린 CCTV 카메라를 올려다보는 수리영의 옆얼굴. CARRIED STATE (persist exactly): Su-ri-yeong’s bicycle remains parked outside the mart, and she continues carrying her doll-adorned backpack and mobile phone. The exterior CCTV camera stays fixed in the identified position. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 마트 외부 건물 벽에 달린 CCTV 카메라를 올려다보는 수리영의 옆얼굴. LOCATION (lock): A large supermarket in the quiet early hours, with merchandise aisles and employee areas, plus an exterior bicycle parking area and a facade covered by security cameras. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she continues carrying her doll-adorned backpack and mobile phone. The exterior CCTV camera stays fixed in the identified position. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 마트 외부 건물 벽에 달린 CCTV 카메라를 올려다보는 수리영의 옆얼굴. LOCATION (lock): A large supermarket in the quiet early hours, with merchandise aisles and employee areas, plus an exterior bicycle parking area and a facade covered by security cameras. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she continues carrying her doll-adorned backpack and mobile phone. The exterior CCTV camera stays fixed in the identified position. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph a restrained side-profile medium close-up from her eye level, using a long-lens feel to compress her face and the CCTV camera into the same shallow visual plane. Place her profile prominently to one side and the camera near the opposite upper edge, with her lifted gaze forming the compositional link; retain enough of her shoulder and lowered hand to register what she carries. Use soft early-morning ambient light across her features and selective focus that keeps her eye and the CCTV housing crisp while the facade falls gently away. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 마트 외부 건물 벽에 달린 CCTV 카메라를 올려다보는 수리영의 옆얼굴. LOCATION (lock): A large supermarket in the quiet early hours, with merchandise aisles and employee areas, plus an exterior bicycle parking area and a facade covered by security cameras. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she continues carrying her doll-adorned backpack and mobile phone. The exterior CCTV camera stays fixed in the identified position. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot from a low position close to the exterior wall with a wide, spatial lens feel, letting the fixed CCTV camera dominate the near upper foreground while Su-ri-yeong appears below in clean side profile looking up at it. Build the frame on a strong diagonal between her face and the camera, preserving visible depth along the facade and including her carried belongings within the lower composition. Keep the early-morning light cool and even, with deeper focus so both her profile and the surveillance camera remain clearly legible. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 마트 외부 건물 벽에 달린 CCTV 카메라를 올려다보는 수리영의 옆얼굴. LOCATION (lock): A large supermarket in the quiet early hours, with merchandise aisles and employee areas, plus an exterior bicycle parking area and a facade covered by security cameras. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she continues carrying her doll-adorned backpack and mobile phone. The exterior CCTV camera stays fixed in the identified position. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph a restrained side-profile medium close-up from her eye level, using a long-lens feel to compress her face and the CCTV camera into the same shallow visual plane. Place her profile prominently to one side and the camera near the opposite upper edge, with her lifted gaze forming the compositional link; retain enough of her shoulder and lowered hand to register what she carries. Use soft early-morning ambient light across her features and selective focus that keeps her eye and the CCTV housing crisp while the facade falls gently away. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 마트 외부 건물 벽에 달린 CCTV 카메라를 올려다보는 수리영의 옆얼굴. LOCATION (lock): A large supermarket in the quiet early hours, with merchandise aisles and employee areas, plus an exterior bicycle parking area and a facade covered by security cameras. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she continues carrying her doll-adorned backpack and mobile phone. The exterior CCTV camera stays fixed in the identified position. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot from a low position close to the exterior wall with a wide, spatial lens feel, letting the fixed CCTV camera dominate the near upper foreground while Su-ri-yeong appears below in clean side profile looking up at it. Build the frame on a strong diagonal between her face and the camera, preserving visible depth along the facade and including her carried belongings within the lower composition. Keep the early-morning light cool and even, with deeper focus so both her profile and the surveillance camera remain clearly legible. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Correct the anatomy of the hand holding the phone to show distinct, naturally structured fingers. - Restore the bicycle's front wheel so that it forms a complete, perfect circle. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 8 - camera_cell: [1, 8] - look_at_unit: 8 - look_at_cell: [1, 4] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Use a static, eye-level, neutral medium composition from unit 8, looking within unit 8 toward cell [1,4], so markers 5 and 6 form the central information surface while the two staged subjects occupy the middle-left and middle-right midground.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show the portion of unit 8 visible from cell [1,8] toward cell [1,4], centered on base markers 5 and 6 and retaining marker 7 in its fixed position south of them. Units 1, 2, and 3 and opening marker 4 are geometry supersets for camera unit 8, so include them only where the selected normal view actually admits them rather than forcing their visibility. - camera_framing_directive: Frame from camera unit 8 at cell [1,8], looking toward unit 8 at cell [1,4], with a normal 50-degree lens for neutral medium coverage. Keep markers 5 and 6 near middle-center, with enough midground width for the committed middle-left and middle-right subject placements. - subject_position_directive: Place the seated committed subject in the middle-left midground with a hand near the controls, and place the leaning committed subject in the middle-right midground. Orient both toward marker 6, which remains between their eyelines at middle-center, and retain the committed upper-body medium composition. - state_cue_directive: Carry transient marker 9 on marker 6 as the committed unusually dark, unreadable displayed state. Maintain the supplied low-to-mid interior illumination and restrained neutral grading without introducing any additional uncommitted state or light cue. - negative_continuity_directive: Do not invent elements beyond numbered markers 1 through 9 or assert visibility of units and openings outside the selected view. Preserve the fixed arrangement of markers 5, 6, and 7, and do not add uncommitted state overlays beyond marker 9. 2026년 대한민국 서해안권 도시의 공공기관 또는 행정시설 안에 있는 소규모 폐쇄회로 텔레비전 보안실 모니터 구역. 출입문 근처에서 문턱과 비어 있는 서서 검토하는 공간을 대각선으로 가로질러 방 안쪽의 연속형 다중 모니터 콘솔을 바라본 구도이다. 카메라는 약 1.6미터 높이의 서 있는 사람 눈높이이며, 28~35밀리미터급 적당한 광각 렌즈를 사용한다. 작업용 회전 의자는 콘솔 앞에 놓여 있고, 의자 뒤에는 두 명이 함께 서서 화면을 검토할 수 있는 충분한 통로와 빈 바닥이 남아 있다. 사람이나 얼굴은 전혀 없다. 방 안쪽의 연속형 콘솔과 여러 대의 평면 모니터를 가장 눈에 띄게 보여 준다. 키보드와 마우스, 일반 업무용 데스크톱 컴퓨터, 벽 쪽의 소형 장비 랙, 정리된 케이블 트레이, 인터폰, 소수의 낡은 서류철이 있는 현대 한국 공공시설의 실용적인 보안실이다. 화면 인터페이스는 현실적인 일반 감시 체계 수준으로 제한하고 미래형 홀로그램이나 공상과학 장치를 넣지 않는다. 검토 중인 감시 영상은 모니터 화면 내부에만 표시되며, 비정상적으로 어둡고 노출이 부족해 희미한 명암과 압축 잡음만 보이고 장소나 대상, 얼굴, 복식은 판독할 수 없다. 어두운 영상 속에 근거 없는 인물이나 괴이한 형상, 선명한 세부를 만들어 내지 않는다. 화면 가장자리의 작은 시간 표시와 분할 감시 틀은 실제 장비처럼 보이되 글자는 읽기 어려운 크기로 둔다. 낮은 밝기의 천장 조명과 모니터의 약한 빛이 섞인 긴장된 근무 환경. 회백색 도장 벽, 실용적인 흡음 천장재, 회색 비닐 바닥, 검은색과 짙은 회색의 금속·합성수지 장비, 절제된 해안 도시권의 중성색을 사용하고 작은 진홍색 서류철 정도만 제한적인 색상 강조로 둔다. 벽 모서리의 미세한 때, 바닥의 의자 바퀴 자국, 손이 자주 닿는 콘솔 가장자리의 마모, 실제 금속의 잔흠집, 전선 피복과 플라스틱 장비의 서로 다른 질감을 사실적으로 표현한다. 지나치게 정돈된 홍보용 사무실이나 깨끗한 재고 사진처럼 보이지 않고, 실제로 교대 근무가 이어지는 생활감 있는 시설이어야 한다. 실제 디지털 일안 반사식 또는 미러리스 카메라로 촬영한 다큐멘터리 풍 사진, 실제 장소 기록 사진과 구별되지 않는 사실성, 자연스러운 원근과 깊이감, 현실적인 저조도 노출과 화면 반사, 정확한 콘크리트·금속·합성수지·직물 질감, 과도한 후처리 없음. 위에서 내려다본 시점이 아니며 바닥 평면도, 건축 도식, 삽화, 삼차원 시각화가 아니다. 16:9 가로 비율, 실제 카메라 촬영본. This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the two security officers from the room. - Mirror the image horizontally so the multi-monitor console runs along the right side of the room. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 대형 마트 총무과 CCTV 보안실 SHOT TEXT (authoritative, Korean): 어두운 CCTV 모니터 화면을 주시하는 한국인 남성 보안 직원과 그 옆에 선 혜수의 상체. CARRIED STATE (persist exactly): The relevant section of the CCTV recording remains abnormally dark and impossible to identify. Su-ri-yeong still has her doll-adorned backpack and phone with her. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 어두운 CCTV 모니터 화면을 주시하는 한국인 남성 보안 직원과 그 옆에 선 혜수의 상체. LOCATION (lock): A supermarket administrative and security office with a CCTV monitoring station, playback controls, and screens used to review recorded exterior footage. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The relevant section of the CCTV recording remains abnormally dark and impossible to identify. Su-ri-yeong still has her doll-adorned backpack and phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리); 한국인 남성 보안 직원 (한국인 남성, 성인, 평범한 얼굴, 짧고 단정한 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 어두운 CCTV 모니터 화면을 주시하는 한국인 남성 보안 직원과 그 옆에 선 혜수의 상체. LOCATION (lock): A supermarket administrative and security office with a CCTV monitoring station, playback controls, and screens used to review recorded exterior footage. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The relevant section of the CCTV recording remains abnormally dark and impossible to identify. Su-ri-yeong still has her doll-adorned backpack and phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리); 한국인 남성 보안 직원 (한국인 남성, 성인, 평범한 얼굴, 짧고 단정한 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot a tight, eye-level chest-up two-shot from beside the CCTV monitor, with the monitor’s dark edge looming softly in the near foreground and both faces seen in three-quarter view beyond it. Use shallow depth of field to hold their concentrated gaze and restrained posture in crisp focus, letting the office recede into subdued softness; the weak screen light shapes their faces against gentle morning ambient illumination. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 어두운 CCTV 모니터 화면을 주시하는 한국인 남성 보안 직원과 그 옆에 선 혜수의 상체. LOCATION (lock): A supermarket administrative and security office with a CCTV monitoring station, playback controls, and screens used to review recorded exterior footage. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The relevant section of the CCTV recording remains abnormally dark and impossible to identify. Su-ri-yeong still has her doll-adorned backpack and phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리); 한국인 남성 보안 직원 (한국인 남성, 성인, 평범한 얼굴, 짧고 단정한 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame an observational medium shot from slightly above and behind the pair, keeping both upper bodies layered beside the monitoring station while the abnormally dark CCTV image occupies the compositional center. Use deeper focus and restrained perspective so the playback controls, screens, and compact office context remain legible without distracting from the unreadable footage; let the figures form a still, asymmetrical frame around the monitor. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 어두운 CCTV 모니터 화면을 주시하는 한국인 남성 보안 직원과 그 옆에 선 혜수의 상체. LOCATION (lock): A supermarket administrative and security office with a CCTV monitoring station, playback controls, and screens used to review recorded exterior footage. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The relevant section of the CCTV recording remains abnormally dark and impossible to identify. Su-ri-yeong still has her doll-adorned backpack and phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리); 한국인 남성 보안 직원 (한국인 남성, 성인, 평범한 얼굴, 짧고 단정한 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot a tight, eye-level chest-up two-shot from beside the CCTV monitor, with the monitor’s dark edge looming softly in the near foreground and both faces seen in three-quarter view beyond it. Use shallow depth of field to hold their concentrated gaze and restrained posture in crisp focus, letting the office recede into subdued softness; the weak screen light shapes their faces against gentle morning ambient illumination. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 어두운 CCTV 모니터 화면을 주시하는 한국인 남성 보안 직원과 그 옆에 선 혜수의 상체. LOCATION (lock): A supermarket administrative and security office with a CCTV monitoring station, playback controls, and screens used to review recorded exterior footage. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The relevant section of the CCTV recording remains abnormally dark and impossible to identify. Su-ri-yeong still has her doll-adorned backpack and phone with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리); 한국인 남성 보안 직원 (한국인 남성, 성인, 평범한 얼굴, 짧고 단정한 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame an observational medium shot from slightly above and behind the pair, keeping both upper bodies layered beside the monitoring station while the abnormally dark CCTV image occupies the compositional center. Use deeper focus and restrained perspective so the playback controls, screens, and compact office context remain legible without distracting from the unreadable footage; let the figures form a still, asymmetrical frame around the monitor. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the 'LG' text logo from the back of the monitor in the foreground. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 7 - camera_cell: [6, 4] - look_at_unit: 5 - look_at_cell: [3, 7] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use the listed cell in unit 7 and aim toward unit 5 through look-at cell [3,7]; broad coverage supports the committed medium side framing and preserves travel space toward frame right.' RENDER GUIDANCE (from validated plan): - visible_space_directive: From unit 7, show the view toward unit 5 with broad coverage of visible candidate units 5, 4, and 1, including openings 2 and 3 and fixed fixture marker 6 where the cone permits. Use markers 1 through 8 to maintain the committed structural relationships; unit 8 need not appear because it lies outside the forward view. - camera_framing_directive: Frame from camera unit 7 at cell [6,4], looking toward unit 5 through cell [3,7], with the wide 90-degree lens providing broad coverage. Maintain the committed medium side framing, center the moving subject at a stable scale, and retain travel space toward frame right. - subject_position_directive: Place the committed subject in the midground at middle_center, shown profile_right with the torso crouched low over the committed moving support, moving toward frame right. Keep the subject's scale stable, preserve forward travel space, and carry the staged off-screen gaze and trailing motion cues without adding other subjects. - state_cue_directive: Include transient marker 9 as committed by the dossier and preserve numbered elements 1 through 8 as fixed base context where visible. The surfaced staging commits daytime ambient illumination with subdued neutral grading and crisp kinetic contrast; add no further uncommitted state cues. - negative_continuity_directive: Do not invent additional numbered elements, state overlays, subjects, or scenario-specific objects beyond committed markers 1 through 9 and the surfaced staging. Do not force unit 8 or other geometry outside the chosen unit-7-to-unit-5 view cone into the frame. 2026년 대한민국 서해안권 중소도시의 현대적인 경찰서 외부 자전거 주차 및 진출 구역. 도로 가장자리에서 경찰서 건물 전면을 향해 대각선으로 바라보는 구도이며, 서 있는 사람의 눈높이 약 1.6m에서 35mm급 중간 광각 렌즈로 촬영한다. 전경에서 중경으로 이어지는 포장된 진출 공간 한쪽에 실용적인 금속 자전거 거치대가 있고, 출발 직전의 평범한 생활 자전거 한 대가 거치대 바로 옆에 세워져 있다. 자전거 앞쪽에서 넓은 진출 공간을 가로질러 도로 가장자리까지 이어지는 시각적·물리적 이동 경로는 장애물 없이 명확하게 비워 둔다. 뒤쪽에는 현대 한국의 소규모 경찰서 전면이 식별되도록 출입문, 새시 창문, 절제된 공공기관 표지판과 경찰을 나타내는 일반적인 청색 계열 안내 요소를 배치하되 특정 기관명이나 작품 고유명사는 쓰지 않는다. 건물은 실제 지방 공공청사에서 흔한 밝은 석재 타일과 일부 회색 금속 패널 마감, 비와 염분에 조금 바랜 실리콘 줄눈, 문턱의 흙자국, 하부 벽면의 빗물 얼룩처럼 현실적인 사용감이 있다. 외벽에는 노출 배수관, 에어컨 실외기와 배관 덮개, 소형 CCTV 카메라가 기능적으로 설치되어 있다. 주변에는 콘크리트 보도 경계석, 희미하게 닳은 주차선, 낮은 볼라드, 배수구가 있으며, 프레임 가장자리에는 서해안권 도심의 평범한 저층 건물 일부와 전신주·전선, 교통안전 거울이 자연스럽게 이어져 건물이 고립된 세트처럼 보이지 않게 한다. 맑거나 옅게 흐린 주간의 자연광, 해안 도시 특유의 약간 습한 공기와 절제된 회색·베이지색 중성 톤, 공공시설 청색 포인트. 과도하게 어둡거나 극적인 조명 없이 현장의 실제 밝기를 유지한다. 실제 콘크리트의 거친 표면, 금속 거치대의 미세한 녹과 긁힘, 자전거 고무 타이어와 체인의 기름때, 유리 반사와 도로 포장의 보수 자국을 정확하게 표현한다. 사람, 얼굴, 인체, 피, 시체는 전혀 없다. 실제 DSLR 또는 미러리스 카메라로 촬영한 다큐멘터리 풍 사진, 실제 장소 기록 사진처럼 사실적이고 생활감 있으며 자연스러운 심도, 과도한 후처리 없음. 깨끗한 스톡 사진, 삽화, CGI, 건축 시각화가 아니며 탑다운 시점, 평면도, 건축 도식이 아니다. 16:9 가로 비율, 실제 카메라 촬영본 The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the stone bollards directly in front of the bicycle to keep the exit path to the street completely clear. - Erase the small illegible text above 'POLICE' on the main sign and the gibberish text on the left vertical blue sign. - Remove the protruding grey metal canopy structure over the entrance so the building's front facade remains flat as indicated by the floor plan. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 경찰서 외부 SHOT TEXT (authoritative, Korean): 핸들을 꽉 쥐고 허리를 한껏 숙인 채 페달을 밟으며 앞으로 나아가는 중간 순간의 수리영 측면, 머리카락과 옷자락이 움직임의 반대 방향으로 흩날리는 모습. CARRIED STATE (persist exactly): Su-ri-yeong rides her bicycle with the folded coordinate note in her pocket, while her doll-adorned backpack and mobile phone remain with her. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 핸들을 꽉 쥐고 허리를 한껏 숙인 채 페달을 밟으며 앞으로 나아가는 중간 순간의 수리영 측면, 머리카락과 옷자락이 움직임의 반대 방향으로 흩날리는 모습. LOCATION (lock): The exterior entrance and parking area of a police station, with a bicycle parked nearby and direct access to the street. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong rides her bicycle with the folded coordinate note in her pocket, while her doll-adorned backpack and mobile phone remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 핸들을 꽉 쥐고 허리를 한껏 숙인 채 페달을 밟으며 앞으로 나아가는 중간 순간의 수리영 측면, 머리카락과 옷자락이 움직임의 반대 방향으로 흩날리는 모습. LOCATION (lock): The exterior entrance and parking area of a police station, with a bicycle parked nearby and direct access to the street. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong rides her bicycle with the folded coordinate note in her pocket, while her doll-adorned backpack and mobile phone remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment in a close side-profile tracking view from roughly saddle height, moving parallel with Su-ri-yeong so her clenched hands, deeply folded posture, active pedal stroke, and backward-streaming hair and clothing remain sharply legible. Use a moderately compressed lens feel and layered lateral background blur to convey urgent forward speed, with clear lead room ahead of her. Keep the existing daylight natural and grounded in the location. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 핸들을 꽉 쥐고 허리를 한껏 숙인 채 페달을 밟으며 앞으로 나아가는 중간 순간의 수리영 측면, 머리카락과 옷자락이 움직임의 반대 방향으로 흩날리는 모습. LOCATION (lock): The exterior entrance and parking area of a police station, with a bicycle parked nearby and direct access to the street. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong rides her bicycle with the folded coordinate note in her pocket, while her doll-adorned backpack and mobile phone remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a low, wide, fixed side-on viewpoint that lets Su-ri-yeong drive across the police-station entrance and parking space within a strong environmental composition. Hold her full riding silhouette and bicycle geometry clearly against the deeper setting, catching the pedal mid-cycle while a restrained trace of motion softens her flying hair and clothing without obscuring her grip or posture. Let the location’s natural daytime light and depth carry the realism, with open space in her direction of travel. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 핸들을 꽉 쥐고 허리를 한껏 숙인 채 페달을 밟으며 앞으로 나아가는 중간 순간의 수리영 측면, 머리카락과 옷자락이 움직임의 반대 방향으로 흩날리는 모습. LOCATION (lock): The exterior entrance and parking area of a police station, with a bicycle parked nearby and direct access to the street. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong rides her bicycle with the folded coordinate note in her pocket, while her doll-adorned backpack and mobile phone remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment in a close side-profile tracking view from roughly saddle height, moving parallel with Su-ri-yeong so her clenched hands, deeply folded posture, active pedal stroke, and backward-streaming hair and clothing remain sharply legible. Use a moderately compressed lens feel and layered lateral background blur to convey urgent forward speed, with clear lead room ahead of her. Keep the existing daylight natural and grounded in the location. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 핸들을 꽉 쥐고 허리를 한껏 숙인 채 페달을 밟으며 앞으로 나아가는 중간 순간의 수리영 측면, 머리카락과 옷자락이 움직임의 반대 방향으로 흩날리는 모습. LOCATION (lock): The exterior entrance and parking area of a police station, with a bicycle parked nearby and direct access to the street. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong rides her bicycle with the folded coordinate note in her pocket, while her doll-adorned backpack and mobile phone remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a low, wide, fixed side-on viewpoint that lets Su-ri-yeong drive across the police-station entrance and parking space within a strong environmental composition. Hold her full riding silhouette and bicycle geometry clearly against the deeper setting, catching the pedal mid-cycle while a restrained trace of motion softens her flying hair and clothing without obscuring her grip or posture. Let the location’s natural daytime light and depth carry the realism, with open space in her direction of travel. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Restore the anatomy of the right hand so the fingers are distinctly formed and naturally wrapping around the handlebar. - Remove all text from the building's signs and glass doors to strictly comply with the no-text rule. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 1 - camera_cell: [7, 2] - look_at_unit: 2 - look_at_cell: [2, 3] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use the listed unit-1 camera cell and broad coverage toward unit 2, centering the look-at cell associated with base marker 19 while retaining context for target units 1, 2, and 3.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show target units 1, 2, and 3 from unit 1 toward unit 2, with base markers 7, 8, 9, 10, 14, 15, 19, 20, 21, and 22 positioned according to the floor-plan readback. Treat the geometry's other visible units and openings only as supersets, not mandatory content. - camera_framing_directive: Use broad 90-degree coverage from camera unit 1 at cell [7,2], looking toward unit 2 at cell [2,3]; preserve enough surrounding context for target units 1, 2, and 3 while allowing the consuming shots to crop toward their committed close and insert scales. - subject_position_directive: For S5_Shot9, reserve the close foreground for two committed subjects in side-profile alignment, with one slightly forward on the left and the other on the right near frame center. For S5_Shot10, permit an insert crop around the committed forearm and wrist detail; add no other subjects. - state_cue_directive: No committed state cue beyond clean residential space applies. Keep the base elements in their persistent state and refrain from inventing additional cues. - negative_continuity_directive: Exclude overlay markers 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, and 39. Do not add spaces beyond target units 1, 2, and 3 or alter the fixed positions of base markers 7, 8, 9, 10, 14, 15, 19, 20, 21, and 22. 2026년 대한민국 서해안권 도시의 저층 주택 옥상에 증축된 소형 옥탑방 내부. 현관 문턱 가까이에 카메라를 두고 약 1.6m의 서 있는 사람 눈높이에서, 거실 겸 식사 공간을 가로질러 식탁과 간이 주방의 싱크대, TV, 작은 거실 창을 대각선으로 바라본다. 풀프레임 DSLR 또는 미러리스 카메라와 28mm 광각 렌즈로 촬영한 자연스러운 시야이며, 과도한 왜곡 없이 좁은 공간의 실제 비례를 유지한다. 침실 출입문들은 프레임 가장자리에만 부분적으로 보이게 하여 중심 공간을 방해하지 않는다. 작은 식탁과 서로 맞지 않는 실용적인 식탁 의자, 스테인리스 싱크대와 낡은 합판 무늬 하부장, 짧은 조리대, 소형 냉장고, 낮은 TV 받침대 위의 현대식 평면 TV가 서로 가까이 놓인 한국식 옥탑 주거 공간. 현관에는 소형 신발장과 일상적인 신발 정리 흔적이 있고, 바닥은 오래 사용해 잔기스와 광택 차이가 생긴 장판 마감이다. 벽은 밝은색 벽지이지만 모서리와 스위치 주변에 손때와 미세한 변색이 있으며, 천장에는 평범한 현대식 LED 등기구가 달려 있다. 창은 한국 저층 주택에서 흔한 알루미늄 또는 PVC 새시의 작은 미닫이창이고, 얇은 생활용 커튼이 한쪽으로 자연스럽게 걷혀 있다. 바닷바람과 습기에 노출되는 옥탑방답게 창틀과 금속 부분에 약한 산화 흔적, 실리콘 마감의 변색, 벽 아래쪽의 미세한 습기 자국이 있지만 폐가처럼 심하게 훼손되지는 않았다. 평범한 모녀의 일상적인 아침을 암시하는 차분하고 따뜻한 생활감. 식탁 위에는 간단한 아침 식사에 쓰였을 법한 컵과 작은 접시, 티슈 상자 정도만 절제해 놓고, 싱크대 주변에는 세제 용기와 건조 중인 식기처럼 실제 거주자가 사용하는 흔적을 둔다. 공간은 깔끔하게 연출된 전시장이나 고급 주택이 아니라, 제한된 면적을 알뜰하게 사용하는 서민적인 현대 한국 주거 내부여야 한다. 작은 거실 창으로 맑은 아침 햇빛이 비스듬히 들어와 식탁 가장자리와 장판 위에 밝은 사각형을 만들고, 창에서 멀어질수록 부드럽게 어두워지는 자연광을 표현한다. 실내등은 꺼져 있거나 햇빛보다 약하며, 과장된 공포 분위기나 초자연적 상징은 없다. 실제 카메라로 촬영한 다큐멘터리 풍 사진, 실제 장소 답사 사진처럼 사실적이고 담담한 결과. 실제 콘크리트 벽체의 미세한 불균일함, 금속의 사용감과 산화, 커튼의 직물 짜임, 목재 무늬와 장판의 마찰 흔적, 가구 가장자리의 작은 찍힘을 정확하게 표현한다. 자연스러운 화이트 밸런스와 현실적인 노출, 실제 렌즈의 완만한 원근감과 자연스러운 심도를 사용하며 인위적인 후처리나 광고 사진식 정돈은 하지 않는다. 사람, 얼굴, 신체, 실루엣은 전혀 없다. 위에서 내려다본 시점이 아니며 평면도, 건축 도면, 다이어그램, 삽화, 3D 시각화가 아니다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove all floating white text numbers from the image. - Replace the extra window on the far left of the left wall with a solid wall. - Rebuild the right wall to be a single flat, continuous surface with two standard doors appropriately spaced, matching the floor plan. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 오래된 빌라 옥탑방 내부 SHOT TEXT (authoritative, Korean): 백팩을 메고 구겨진 사진을 손에 꽉 쥔 채 열린 현관문 앞에 선 수리영의 뒷모습. CARRIED STATE (persist exactly): Su-ri-yeong leaves wearing her doll-adorned backpack and tightly gripping the old photograph; the printed maps remain inside the pack and her phone remains with her. The ransacked room and red circle are left intact behind her. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 백팩을 메고 구겨진 사진을 손에 꽉 쥔 채 열린 현관문 앞에 선 수리영의 뒷모습. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong leaves wearing her doll-adorned backpack and tightly gripping the old photograph; the printed maps remain inside the pack and her phone remains with her. The ransacked room and red circle are left intact behind her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 백팩을 메고 구겨진 사진을 손에 꽉 쥔 채 열린 현관문 앞에 선 수리영의 뒷모습. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong leaves wearing her doll-adorned backpack and tightly gripping the old photograph; the printed maps remain inside the pack and her phone remains with her. The ransacked room and red circle are left intact behind her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from deep inside the apartment at standing eye level in a restrained wide composition, placing Su-ri-yeong near the far end of the room at the open entrance. Use the ransacked interior as layered foreground and midground depth, with converging room lines drawing toward her rigid back; keep the backpack, doll adornment, and clenched photograph clearly legible. Let soft dusk spill from the open window rake gently across the disorder while her figure remains naturally subdued against the doorway. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 백팩을 메고 구겨진 사진을 손에 꽉 쥔 채 열린 현관문 앞에 선 수리영의 뒷모습. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong leaves wearing her doll-adorned backpack and tightly gripping the old photograph; the printed maps remain inside the pack and her phone remains with her. The ransacked room and red circle are left intact behind her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a close rear view from slightly below waist height, compressing the doorway around Su-ri-yeong and making the tension in her gripping hand the visual anchor. Keep her backpack and doll adornment prominent while the crumpled photograph is seen naturally from the camera-facing side dictated by her grip; allow only selective fragments of the disturbed apartment to remain behind her in shallow focus. Use low, cool dusk ambience with a soft edge from the open window, preserving tactile detail in her hand, the worn photograph, and the backpack. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 백팩을 메고 구겨진 사진을 손에 꽉 쥔 채 열린 현관문 앞에 선 수리영의 뒷모습. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong leaves wearing her doll-adorned backpack and tightly gripping the old photograph; the printed maps remain inside the pack and her phone remains with her. The ransacked room and red circle are left intact behind her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from deep inside the apartment at standing eye level in a restrained wide composition, placing Su-ri-yeong near the far end of the room at the open entrance. Use the ransacked interior as layered foreground and midground depth, with converging room lines drawing toward her rigid back; keep the backpack, doll adornment, and clenched photograph clearly legible. Let soft dusk spill from the open window rake gently across the disorder while her figure remains naturally subdued against the doorway. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 백팩을 메고 구겨진 사진을 손에 꽉 쥔 채 열린 현관문 앞에 선 수리영의 뒷모습. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong leaves wearing her doll-adorned backpack and tightly gripping the old photograph; the printed maps remain inside the pack and her phone remains with her. The ransacked room and red circle are left intact behind her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a close rear view from slightly below waist height, compressing the doorway around Su-ri-yeong and making the tension in her gripping hand the visual anchor. Keep her backpack and doll adornment prominent while the crumpled photograph is seen naturally from the camera-facing side dictated by her grip; allow only selective fragments of the disturbed apartment to remain behind her in shallow focus. Use low, cool dusk ambience with a soft edge from the open window, preserving tactile detail in her hand, the worn photograph, and the backpack. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Slide the living room window open. - Place the bloodstained photograph inside the red circle on the bedroom wall. - Flip the crumpled photograph in her hand so its blank back faces the camera. - Rotate and reposition Su-ri-yeong to stand facing the open entrance door on the right. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 3 - camera_cell: [8, 2] - look_at_unit: 1 - look_at_cell: [1, 5] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Use neutral coverage from unit 3 toward unit 1, centered on the committed forward fixed elements while retaining sufficient depth for the close two-subject composition in S29_Shot9.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show the view from unit 3 toward unit 1, with units 1 and 2 available along the geometry-supported sightline. Establish base markers 1, 2, 3, 4, 5, 7, and 9, prioritizing fixed marker 4, furniture marker 5, and the committed openings 7 and 9. - camera_framing_directive: Frame from camera unit 3 at cell [8,2] toward look-at unit 1 at cell [1,5] with a normal 50-degree lens, giving neutral coverage and enough depth for the close foreground and midground relationship committed by S29_Shot9. - subject_position_directive: For S29_Shot9, place the foreground subject in the lower middle-center and the second subject across the first subject's shoulder in the upper-right midground, keeping both on the same restrained focal plane as committed by the staging. - state_cue_directive: No committed state cue beyond clean residential space applies because clean_background_expected is true and no transient markers are listed; refrain from inventing additional state cues. - negative_continuity_directive: Exclude overlay markers 10, 11, and 12 and avoid introducing scenario-specific objects or spaces outside the unit 3 toward unit 1 view. Keep the positions of fixed markers 4 and 5 and committed openings 7 and 9 stable. 2026년 대한민국 서해안에서 실제 운항하는 소형 어선의 비좁은 조타실 내부. 전방 우현의 조타 콘솔 가까이에 선 카메라가 후방을 향해 조타실 중앙의 비어 있는 동선 구역과 후방 출입 문턱, 출입문을 바라본 구도다. 화면 한쪽 전경에는 사용감 있는 조타 콘솔 가장자리와 작은 선박용 조타륜, 스로틀 레버, 나침반, 아날로그 계기와 현대식 GPS 항해 디스플레이, VHF 무전기, 낡은 스위치 패널 일부가 공간 기준점으로 보인다. 중앙 바닥은 두 명의 서 있는 인물을 나중에 배치할 수 있도록 넉넉히 비우고, 배경 사진 자체에는 사람이나 신체를 전혀 넣지 않는다. 후방에는 금속 문턱과 실용적인 출입문, 좁은 통로가 분명히 이어지며, 문 주변의 손잡이와 손때, 긁힘, 염분 얼룩이 자연스럽다. 한국 연안 소형 어선에서 흔한 실용적 구조로, 흰색 또는 옅은 회색으로 칠한 금속·유리섬유 내벽, 오래된 실란트가 보이는 알루미늄 새시 창, 전방 유리창과 와이퍼, 노출된 전선과 케이블 고정구, 작은 수납함, 고정식 선장 의자, 천장의 낮은 방수형 조명이 있다. 깨끗한 신조선이나 관광용 보트가 아니라 실제 작업선답게 도장 벗겨짐, 미세한 녹, 젖은 장화 자국, 기름때, 먼지, 소금기 어린 유리, 반복 사용으로 닳은 플라스틱과 금속 표면을 사실적으로 표현한다. 장비는 2026년의 통상적인 한국 소형 어선 수준이며 미래형 인터페이스나 홀로그램은 없다. 해 질 무렵의 차갑고 흐린 청회색 바깥빛이 창을 통해 약하게 들어오고, 낮은 천장 조명의 둔한 황백색 빛이 일부 계기와 금속 가장자리를 비춘다. 바깥 창 너머로는 어두워지는 서해의 수평선과 흐릿한 항만 또는 해상 빛이 과장 없이 희미하게만 보인다. 직전에 긴박한 일이 벌어진 듯한 답답하고 긴장된 정적은 조명과 비좁은 공간감으로만 전달하되, 파손이나 피, 시신, 사람, 얼굴은 표현하지 않는다. 일시적 사진, 붉은 원형 오버레이, 붉은 표식, 문자, 룬, 마법진, 환영도 넣지 않는다. 실제 미러리스 또는 DSLR 카메라와 35mm급 중간 광각 렌즈로 촬영한 다큐멘터리 풍 사진. 카메라 높이는 서 있는 사람의 눈높이인 약 1.6m이며, 위에서 내려다보는 시점이나 평면도, 건축 도해가 아니다. 실제 콘솔 플라스틱, 금속의 산화와 녹, 고무 패킹, 유리의 염분 얼룩, 직물과 페인트의 마모를 정확하게 보여 주고, 자연스러운 원근과 깊이, 과하지 않은 자연 심도, 현실적인 노출을 유지한다. 실제 장소 기록 사진처럼 담담하고 후처리하지 않은 결과이며, 깔끔한 스톡 사진, 삽화, 3D 렌더, 건축 시각화가 아니다. 16:9 가로 비율, 실제 카메라 촬영본. This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Reverse the camera view to shoot from the rear threshold (Unit 3) looking forward toward the steering console (Unit 1). - Add a fixed captain's chair in the center of the wheelhouse floor. - Move the steering console from the side wall to the front wall to match the floor plan layout. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge. STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO facial features beyond a bare head outline, NO clothing detail, NO material rendering. The frame contains ONLY: the camera framing, each figure as a simple correct-proportion human contour in its exact pose and screen position/size, and the few major set masses as plain outline shapes. It must read as a quick layout guide, never as a finished drawing. The attached photograph is the LOCATION where this shot happens. Use it ONLY as a LOOSE spatial reference — the rough set masses and where things sit relative to each other. You do NOT need to follow it exactly: do not copy its camera, its lighting or its details. Choose the camera and framing the SHOT TEXT needs, and draw only the few set masses that matter as plain outline shapes. THE LOCATION: 소형 어선 조타실 SHOT TEXT (authoritative, Korean): 굳어버린 인우의 어깨 너머, 조타실 벽면에 빼곡하게 그려진 기괴한 붉은색 원형 표식들이 보이는 시점 쇼트. CARRIED STATE (persist exactly): The numerous circular marks remain crowded across the wheelhouse walls, including the newly perceived red circle. Su-ri-yeong still possesses the old photograph, backpack, maps, and phone. ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 굳어버린 인우의 어깨 너머, 조타실 벽면에 빼곡하게 그려진 기괴한 붉은색 원형 표식들이 보이는 시점 쇼트. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The numerous circular marks remain crowded across the wheelhouse walls, including the newly perceived red circle. Su-ri-yeong still possesses the old photograph, backpack, maps, and phone. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 굳어버린 인우의 어깨 너머, 조타실 벽면에 빼곡하게 그려진 기괴한 붉은색 원형 표식들이 보이는 시점 쇼트. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The numerous circular marks remain crowded across the wheelhouse walls, including the newly perceived red circle. Su-ri-yeong still possesses the old photograph, backpack, maps, and phone. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight eye-level over-the-shoulder view, with In-woo’s rigid shoulder and the back edge of his head looming close in the foreground while focus settles sharply on the wall crowded with red circular marks. Use compressed depth and restrained dusk ambience so the foreground feels immobilized and the marked wall presses toward him. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 굳어버린 인우의 어깨 너머, 조타실 벽면에 빼곡하게 그려진 기괴한 붉은색 원형 표식들이 보이는 시점 쇼트. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The numerous circular marks remain crowded across the wheelhouse walls, including the newly perceived red circle. Su-ri-yeong still possesses the old photograph, backpack, maps, and phone. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a wider, slightly elevated over-the-shoulder composition that places In-woo’s tense shoulder and neatly groomed head along one edge while the marked wheelhouse walls dominate the frame. Hold broad depth of field across the cabin, arranging the dense red circles as a claustrophobic visual field around his fixed posture, with subdued directional dusk light shaping the interior. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 굳어버린 인우의 어깨 너머, 조타실 벽면에 빼곡하게 그려진 기괴한 붉은색 원형 표식들이 보이는 시점 쇼트. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The numerous circular marks remain crowded across the wheelhouse walls, including the newly perceived red circle. Su-ri-yeong still possesses the old photograph, backpack, maps, and phone. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight eye-level over-the-shoulder view, with In-woo’s rigid shoulder and the back edge of his head looming close in the foreground while focus settles sharply on the wall crowded with red circular marks. Use compressed depth and restrained dusk ambience so the foreground feels immobilized and the marked wall presses toward him. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 굳어버린 인우의 어깨 너머, 조타실 벽면에 빼곡하게 그려진 기괴한 붉은색 원형 표식들이 보이는 시점 쇼트. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The numerous circular marks remain crowded across the wheelhouse walls, including the newly perceived red circle. Su-ri-yeong still possesses the old photograph, backpack, maps, and phone. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a wider, slightly elevated over-the-shoulder composition that places In-woo’s tense shoulder and neatly groomed head along one edge while the marked wheelhouse walls dominate the frame. Hold broad depth of field across the cabin, arranging the dense red circles as a claustrophobic visual field around his fixed posture, with subdued directional dusk light shaping the interior. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Replace the small steering wheel attached to the front right window with a proper circular clear-view screen apparatus as seen in the location reference. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.





Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim streetlights. SHOT TEXT (authoritative, Korean): 정체불명의 습격자의 이빨이 뒷골목 사건의 여자 피해자의 목에 깊이 박혀 살점을 강하게 물어뜯는 찰나의 측면 LOCATION (lock): A narrow urban back alley lined with utility poles, including one where two figures are entangled. Sparse streetlights provide the only stated exterior illumination. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the dim streetlamp lighting, utility pole, alley textures, and the attackers' continuing clothing and positions from the reference. Exclude the earlier wide pushing pose and reframe the action tightly around the bite at the woman's neck. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The female victim remains pressed against the utility pole as the attacker bites deeply into her neck, leaving a torn neck wound. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정체불명의 습격자 (한국인으로 보이는 성인 남성, 어둠에 가려진 얼굴, 식별하기 어려운 머리 형태, 붉은 눈동자를 제외한 이목구비 불명); 뒷골목 사건의 여자 피해자 (한국인 여성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim streetlights. SHOT TEXT (authoritative, Korean): 정체불명의 습격자의 이빨이 뒷골목 사건의 여자 피해자의 목에 깊이 박혀 살점을 강하게 물어뜯는 찰나의 측면 LOCATION (lock): A narrow urban back alley lined with utility poles, including one where two figures are entangled. Sparse streetlights provide the only stated exterior illumination. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the dim streetlamp lighting, utility pole, alley textures, and the attackers' continuing clothing and positions from the reference. Exclude the earlier wide pushing pose and reframe the action tightly around the bite at the woman's neck. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The female victim remains pressed against the utility pole as the attacker bites deeply into her neck, leaving a torn neck wound. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정체불명의 습격자 (한국인으로 보이는 성인 남성, 어둠에 가려진 얼굴, 식별하기 어려운 머리 형태, 붉은 눈동자를 제외한 이목구비 불명); 뒷골목 사건의 여자 피해자 (한국인 여성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the instant in an unflinching, eye-level extreme close side view, cropping tightly around the two profiles, jaws, neck, and the victim’s contact with the pole. Place the bite at the sharp compositional center, with very shallow depth of field letting the attacker’s obscured face and alley textures fall away rapidly. Shape the sparse streetlight as a narrow grazing edge across skin, teeth, and the torn wound, preserving heavy natural shadow and a tense, tactile realism. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim streetlights. SHOT TEXT (authoritative, Korean): 정체불명의 습격자의 이빨이 뒷골목 사건의 여자 피해자의 목에 깊이 박혀 살점을 강하게 물어뜯는 찰나의 측면 LOCATION (lock): A narrow urban back alley lined with utility poles, including one where two figures are entangled. Sparse streetlights provide the only stated exterior illumination. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the dim streetlamp lighting, utility pole, alley textures, and the attackers' continuing clothing and positions from the reference. Exclude the earlier wide pushing pose and reframe the action tightly around the bite at the woman's neck. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The female victim remains pressed against the utility pole as the attacker bites deeply into her neck, leaving a torn neck wound. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정체불명의 습격자 (한국인으로 보이는 성인 남성, 어둠에 가려진 얼굴, 식별하기 어려운 머리 형태, 붉은 눈동자를 제외한 이목구비 불명); 뒷골목 사건의 여자 피해자 (한국인 여성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a low, restrained medium side shot that keeps the entangled upper bodies and utility pole clearly legible while the narrow alley recedes behind them. Compose the pole as a rigid vertical that traps the victim in frame, with the attacker’s body forming a dark diagonal into the bite; hold greater depth of field so the worn alley surfaces and sparse streetlights remain present without competing with the action. Let the dim streetlight separate their edges from the background while the faces remain largely submerged in credible night shadow. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Obscure the attacker's face and head completely in deep shadow so only the red eye remains identifiable. - Embed the attacker's teeth deeply into the flesh of the victim's neck to show a forceful bite. - Redraw the attacker's hand on the neck to be an anatomically correct right hand gripping the neck. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, narrow sunlight through a small window. SHOT TEXT (authoritative, Korean): 민숙의 손목 피부에 새겨진 작은 원 모양의 표식이 뚜렷하게 보이는 클로즈업 LOCATION (lock): A compact rooftop apartment interior with a small living-room window, a dining table, a sink and stove area, and bedrooms opening off the main space. A pot boils beside herbs being washed at the faucet. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the daylight interior look, warm domestic materials, and the woman's continuing clothing and arm position from the reference. Exclude the younger woman's face and the embrace from the close frame, showing only the wrist and its small circular mark. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The same small circular mark remains clearly defined on Minsuk’s wrist; she is still wearing her apron. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, narrow sunlight through a small window. SHOT TEXT (authoritative, Korean): 민숙의 손목 피부에 새겨진 작은 원 모양의 표식이 뚜렷하게 보이는 클로즈업 LOCATION (lock): A compact rooftop apartment interior with a small living-room window, a dining table, a sink and stove area, and bedrooms opening off the main space. A pot boils beside herbs being washed at the faucet. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the daylight interior look, warm domestic materials, and the woman's continuing clothing and arm position from the reference. Exclude the younger woman's face and the embrace from the close frame, showing only the wrist and its small circular mark. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The same small circular mark remains clearly defined on Minsuk’s wrist; she is still wearing her apron. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the wrist in an intimate, oblique extreme close-up, with the small circular mark held in precise critical focus and the surrounding skin falling gently out of focus. Let the narrow morning sunlight rake across the wrist, revealing natural skin texture and giving the mark quiet dramatic emphasis; reduce the warm apartment interior and apron to soft, unobtrusive color fields at the frame edges. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): morning, narrow sunlight through a small window. SHOT TEXT (authoritative, Korean): 민숙의 손목 피부에 새겨진 작은 원 모양의 표식이 뚜렷하게 보이는 클로즈업 LOCATION (lock): A compact rooftop apartment interior with a small living-room window, a dining table, a sink and stove area, and bedrooms opening off the main space. A pot boils beside herbs being washed at the faucet. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the daylight interior look, warm domestic materials, and the woman's continuing clothing and arm position from the reference. Exclude the younger woman's face and the embrace from the close frame, showing only the wrist and its small circular mark. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The same small circular mark remains clearly defined on Minsuk’s wrist; she is still wearing her apron. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (한국인 여성, 40대 초반, 부드러운 중년 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame the wrist in a restrained, nearly perpendicular close-up, presenting the skin surface and circular mark with direct, clinical clarity rather than sensual softness. Use a steadier depth of field so the wrist contour and mark remain crisply legible together, with the narrow window light creating a simple directional division between light and shade and the composition kept spare and geometrically controlled. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Point the arm downward to match the relaxed, hanging position established in the reference. - Move the circular mark to the side of the wrist below the thumb. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 철장 안의 개들을 등지고 귀에 휴대폰을 댄 채 미간을 찌푸린 수리영의 측면 LOCATION (lock): A dog shelter with secure enclosures for multiple dogs and a work area for vaccinations, grooming, ointment application, and bathing. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong has her mobile phone with her and holds it to her ear while trying to contact Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 로트와일러 (넓고 각진 머리, 짧고 굵은 주둥이, 검은 털, 황갈색 얼굴 무늬) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 철장 안의 개들을 등지고 귀에 휴대폰을 댄 채 미간을 찌푸린 수리영의 측면 LOCATION (lock): A dog shelter with secure enclosures for multiple dogs and a work area for vaccinations, grooming, ointment application, and bathing. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong has her mobile phone with her and holds it to her ear while trying to contact Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 로트와일러 (넓고 각진 머리, 짧고 굵은 주둥이, 검은 털, 황갈색 얼굴 무늬) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph this as an intimate eye-level side-profile close-up, cropping tightly around her head and upper shoulders. Keep her furrowed brow, cheek, and the phone at her ear in crisp focus while the barred enclosures and dogs behind her fall into soft, recognizable depth; use restrained available daytime light and subtle facial modeling to hold the tension. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 철장 안의 개들을 등지고 귀에 휴대폰을 댄 채 미간을 찌푸린 수리영의 측면 LOCATION (lock): A dog shelter with secure enclosures for multiple dogs and a work area for vaccinations, grooming, ointment application, and bathing. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong has her mobile phone with her and holds it to her ear while trying to contact Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 로트와일러 (넓고 각진 머리, 짧고 굵은 주둥이, 검은 털, 황갈색 얼굴 무늬) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a slightly low, medium-wide lateral view that preserves her clear profile while giving the shelter environment substantial visual weight. Arrange her against the repeating enclosure geometry, with the dogs visibly occupying the depth behind her back; favor deeper focus, firm structural lines, and unembellished daytime illumination for a tense observational feeling. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove all text from the white boxes on the table. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 눈을 크게 뜨고 입을 반쯤 벌린 채 충격으로 멈춘 혜수의 얼굴 클로즈업. LOCATION (lock): The exterior of a rooftop apartment building, including the rooftop exit, steep connecting stairs, lower courtyard, and nearby vehicle access where responders arrive. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the nighttime courtyard look, red police-light illumination, and the ongoing emergency atmosphere from the reference. Exclude the stunned young woman and the wider police-car composition, keeping only the investigator's shocked face in frame. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The wounded corpse, blood traces, and red wall circle are still upstairs as Hye-su reacts and heads toward the rooftop room; Su-ri-yeong retains the old photograph unless the later cleanup removes it. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 눈을 크게 뜨고 입을 반쯤 벌린 채 충격으로 멈춘 혜수의 얼굴 클로즈업. LOCATION (lock): The exterior of a rooftop apartment building, including the rooftop exit, steep connecting stairs, lower courtyard, and nearby vehicle access where responders arrive. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the nighttime courtyard look, red police-light illumination, and the ongoing emergency atmosphere from the reference. Exclude the stunned young woman and the wider police-car composition, keeping only the investigator's shocked face in frame. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The wounded corpse, blood traces, and red wall circle are still upstairs as Hye-su reacts and heads toward the rooftop room; Su-ri-yeong retains the old photograph unless the later cleanup removes it. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her in a locked, eye-level frontal close-up with a restrained telephoto feel, her face centered and nearly filling the frame. Keep both eyes and the parted lips critically sharp while the surroundings dissolve into darkness; let the red police-light illumination rake softly across one side of her face, leaving the opposite side in controlled shadow. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 눈을 크게 뜨고 입을 반쯤 벌린 채 충격으로 멈춘 혜수의 얼굴 클로즈업. LOCATION (lock): The exterior of a rooftop apartment building, including the rooftop exit, steep connecting stairs, lower courtyard, and nearby vehicle access where responders arrive. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the nighttime courtyard look, red police-light illumination, and the ongoing emergency atmosphere from the reference. Exclude the stunned young woman and the wider police-car composition, keeping only the investigator's shocked face in frame. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The wounded corpse, blood traces, and red wall circle are still upstairs as Hye-su reacts and heads toward the rooftop room; Su-ri-yeong retains the old photograph unless the later cleanup removes it. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Move extremely close from a slightly low, three-quarter angle with a subtly wide lens feel, creating uneasy perspective without distorting her anatomy. Frame her face asymmetrically with the nearer eye dominating the composition, keeping both widened eyes and the half-open mouth legible as red police light grazes the facial planes against a heavily defocused night background. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Add the high-collared burgundy turtleneck underneath the brown leather jacket so no bare skin is visible on her neck and chest. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 텅 빈 창가 커튼 쪽을 보며 얼굴이 파랗게 질린 채 굳어버린 수리영의 얼굴 클로즈업. LOCATION (lock): A small rooftop apartment interior with an entrance, living and dining area, and a meticulously arranged bedroom containing a bed, curtain, backpack, and doll. Every surface appears unusually clean and undisturbed. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the spotless bedroom state, curtain placement, bed area, and subdued nighttime light from the reference. Exclude the wide empty-room composition and any blood, corpse, or red symbol, using the setting only behind the frightened close-up. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The curtain area remains empty, and the formerly bloody room stays excessively clean with no corpse or red mark visible. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 텅 빈 창가 커튼 쪽을 보며 얼굴이 파랗게 질린 채 굳어버린 수리영의 얼굴 클로즈업. LOCATION (lock): A small rooftop apartment interior with an entrance, living and dining area, and a meticulously arranged bedroom containing a bed, curtain, backpack, and doll. Every surface appears unusually clean and undisturbed. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the spotless bedroom state, curtain placement, bed area, and subdued nighttime light from the reference. Exclude the wide empty-room composition and any blood, corpse, or red symbol, using the setting only behind the frightened close-up. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The curtain area remains empty, and the formerly bloody room stays excessively clean with no corpse or red mark visible. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame an extremely tight eye-level close-up, holding her face almost frontally while her gaze pulls decisively toward the curtain side of the frame. Use shallow focus to isolate the minute rigidity around her eyes, lips, and jaw, with the spotless bedroom and curtain reduced to a soft, recognizable background; subdued cool nighttime light gives her fear-stricken pallor a realistic cast without altering her natural skin or eyes. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 텅 빈 창가 커튼 쪽을 보며 얼굴이 파랗게 질린 채 굳어버린 수리영의 얼굴 클로즈업. LOCATION (lock): A small rooftop apartment interior with an entrance, living and dining area, and a meticulously arranged bedroom containing a bed, curtain, backpack, and doll. Every surface appears unusually clean and undisturbed. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the spotless bedroom state, curtain placement, bed area, and subdued nighttime light from the reference. Exclude the wide empty-room composition and any blood, corpse, or red symbol, using the setting only behind the frightened close-up. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The curtain area remains empty, and the formerly bloody room stays excessively clean with no corpse or red mark visible. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Place the camera close to the curtain area and photograph her in a compressed profile close-up, with a softly blurred edge of the curtain in the near foreground and her frozen face in crisp focus beyond it. Keep the camera slightly below eye level so her fixed gaze carries tension across the narrow depth of the frame; let gentle side light skim her cheek and catch natural moisture in her eyes while the rest of the immaculate room falls into subdued darkness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the character's facial skin tone to appear extremely pale and ashen, removing the warm hues to reflect severe fright. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 어둠이 깔린 해안도로를 향해 한 발을 허공에 띄운 채 상체를 앞으로 기울인 달리기 mid-action 자세의 수리영 뒷모습 실루엣. LOCATION (lock): A bus-stop area along the coast with seating oriented toward the sea and an open roadside edge nearby. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong runs off with her mobile phone still in her possession. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 어둠이 깔린 해안도로를 향해 한 발을 허공에 띄운 채 상체를 앞으로 기울인 달리기 mid-action 자세의 수리영 뒷모습 실루엣. LOCATION (lock): A bus-stop area along the coast with seating oriented toward the sea and an open roadside edge nearby. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong runs off with her mobile phone still in her possession. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from a low, close rear three-quarter position with a moderately wide lens feel, letting the roadway pull strongly into depth ahead of her. Use an off-center composition and a tight full-body crop that preserves the airborne foot, with slight natural motion blur at the extremities while her torso remains legible. Keep the night exposure low-key, using only the existing exterior illumination to trace her outline while retaining subtle clothing and body detail rather than rendering her as a featureless black shape. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 어둠이 깔린 해안도로를 향해 한 발을 허공에 띄운 채 상체를 앞으로 기울인 달리기 mid-action 자세의 수리영 뒷모습 실루엣. LOCATION (lock): A bus-stop area along the coast with seating oriented toward the sea and an open roadside edge nearby. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong runs off with her mobile phone still in her possession. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a distant, slightly elevated rear viewpoint with a compressed long-lens feel, holding her smaller within the established bus-stop and roadside geometry. Frame with strong negative space in the direction of movement and layered fixed elements between foreground, subject, and dark road, creating a restrained, observational tension. Expose for the night ambience so her back reads as a dark human figure with a delicate rim and faint tonal detail, sharply freezing the suspended mid-stride instant. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the character's hair to be loose and flowing down her back instead of tied in a ponytail. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, office lighting unspecified. SHOT TEXT (authoritative, Korean): 입술을 굳게 다문 채 단호하고 매서운 눈빛으로 김형사를 굽어보는 혜수의 얼굴 클로즈업. LOCATION (lock): A police station office arranged with desks, computers, telephones, and duty workstations, largely empty except for the overnight officer. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the office lighting, institutional textures, and the investigator's continuing clothing and position near her colleague from the reference. Exclude the doorway-entry action and phone from the close frame, concentrating on her stern downward gaze. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Hye-su continues holding the mobile phone containing Minsuk’s saved number. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, office lighting unspecified. SHOT TEXT (authoritative, Korean): 입술을 굳게 다문 채 단호하고 매서운 눈빛으로 김형사를 굽어보는 혜수의 얼굴 클로즈업. LOCATION (lock): A police station office arranged with desks, computers, telephones, and duty workstations, largely empty except for the overnight officer. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the office lighting, institutional textures, and the investigator's continuing clothing and position near her colleague from the reference. Exclude the doorway-entry action and phone from the close frame, concentrating on her stern downward gaze. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Hye-su continues holding the mobile phone containing Minsuk’s saved number. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame Hye-su in a tight frontal close-up from slightly below her eye line, as if the camera occupies Detective Kim’s lower position. Keep her face dominant and nearly centered, with her firmly pressed lips and sharp downward gaze in precise focus; let the existing office environment recede into a soft, unobtrusive background. Use the established office light to model her mature features with restrained contrast and a controlled, confrontational stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, office lighting unspecified. SHOT TEXT (authoritative, Korean): 입술을 굳게 다문 채 단호하고 매서운 눈빛으로 김형사를 굽어보는 혜수의 얼굴 클로즈업. LOCATION (lock): A police station office arranged with desks, computers, telephones, and duty workstations, largely empty except for the overnight officer. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the office lighting, institutional textures, and the investigator's continuing clothing and position near her colleague from the reference. Exclude the doorway-entry action and phone from the close frame, concentrating on her stern downward gaze. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Hye-su continues holding the mobile phone containing Minsuk’s saved number. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph Hye-su in a close three-quarter profile, placing the camera just off the downward path of her gaze rather than directly beneath it. Crop tightly around her face so the set of her jaw, compressed lips, and narrowed focus carry the frame, while a narrow suggestion of the established police office remains softly layered behind her. Hold the visible eye and lip line crisp, allowing the farther side of her face and background to fall away gently for a colder, more observational tension. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the hand and mobile phone from the bottom left corner, replacing them with the character's jacket and the office background. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 귀에 핸드폰을 댄 채 굳은 얼굴로 앞을 주시하는 수리영의 측면. LOCATION (lock): A large supermarket in the quiet early hours, with merchandise aisles and employee areas, plus an exterior bicycle parking area and a facade covered by security cameras. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the daylight exterior wall, CCTV-camera area, and the young woman's continuing clothing and position from the reference. Exclude the upward-looking pose and the CCTV camera if it falls outside the tighter phone-call framing. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Her bicycle remains parked outside while Su-ri-yeong holds her phone to her ear; the doll-adorned backpack remains with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 귀에 핸드폰을 댄 채 굳은 얼굴로 앞을 주시하는 수리영의 측면. LOCATION (lock): A large supermarket in the quiet early hours, with merchandise aisles and employee areas, plus an exterior bicycle parking area and a facade covered by security cameras. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the daylight exterior wall, CCTV-camera area, and the young woman's continuing clothing and position from the reference. Exclude the upward-looking pose and the CCTV camera if it falls outside the tighter phone-call framing. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Her bicycle remains parked outside while Su-ri-yeong holds her phone to her ear; the doll-adorned backpack remains with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame an intimate eye-level side-profile close-up, cropping tightly around her head, shoulder, and the hand holding the phone. Use a natural portrait perspective with very shallow depth of field, keeping her eye, set jaw, and phone-hand contact critically sharp while the exterior wall falls softly away. Let restrained early-morning daylight rake gently across the profile, emphasizing her rigid stillness and fixed forward gaze. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 귀에 핸드폰을 댄 채 굳은 얼굴로 앞을 주시하는 수리영의 측면. LOCATION (lock): A large supermarket in the quiet early hours, with merchandise aisles and employee areas, plus an exterior bicycle parking area and a facade covered by security cameras. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the daylight exterior wall, CCTV-camera area, and the young woman's continuing clothing and position from the reference. Exclude the upward-looking pose and the CCTV camera if it falls outside the tighter phone-call framing. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Her bicycle remains parked outside while Su-ri-yeong holds her phone to her ear; the doll-adorned backpack remains with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her in a restrained side-profile medium shot from slightly below eye level, placing her off-center with broad negative space extending in the direction of her stare. Use a compressed perspective and layered facade geometry to hold her firmly against the location rather than isolating her in blur. Keep the early-morning daylight subdued and directional, with her silhouette, phone gesture, backpack, and locked posture reading clearly within the environmental composition. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove all text and lettering from the white sign board above the sliding glass doors on the left. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 책상 위 사진을 내려다보며 눈을 크게 뜬 수리영의 충격받은 얼굴 클로즈업. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the daytime office lighting, desk arrangement, institutional materials, and the seated woman's clothing from the reference. Exclude the empty-office wide framing and unrelated furniture, focusing on her shocked face as she looks down at the crime photographs. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The gruesome murder-scene photographs remain spread over Hye-su’s desk as Su-ri-yeong examines them; her backpack and phone remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 책상 위 사진을 내려다보며 눈을 크게 뜬 수리영의 충격받은 얼굴 클로즈업. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the daytime office lighting, desk arrangement, institutional materials, and the seated woman's clothing from the reference. Exclude the empty-office wide framing and unrelated furniture, focusing on her shocked face as she looks down at the crime photographs. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The gruesome murder-scene photographs remain spread over Hye-su’s desk as Su-ri-yeong examines them; her backpack and phone remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a tight, desk-level close-up from just forward of Su-ri-yeong, catching her face nearly front-on as her gaze drops below the lens toward the photographs. Use very shallow focus so her widened eyes and arrested facial muscles are razor clear while the desk and photograph edges form a soft lower foreground; keep the busy office compressed into subdued blur behind her. Let the established office light fall naturally across her face, preserving realistic skin texture and restrained live-action shock. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 책상 위 사진을 내려다보며 눈을 크게 뜬 수리영의 충격받은 얼굴 클로즈업. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the daytime office lighting, desk arrangement, institutional materials, and the seated woman's clothing from the reference. Exclude the empty-office wide framing and unrelated furniture, focusing on her shocked face as she looks down at the crime photographs. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The gruesome murder-scene photographs remain spread over Hye-su’s desk as Su-ri-yeong examines them; her backpack and phone remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment in a high, oblique close-up over the desk, placing the spread photographs in the near foreground and Su-ri-yeong’s shocked face just beyond them as she looks sharply downward. Hold enough depth to retain the physical relationship between her gaze and the photographs while allowing the surrounding office to fall away at the frame edges. Use the existing daytime office illumination with gentle directional contrast, emphasizing her wide eyes and sudden stillness without stylization or anatomical exaggeration. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove all blurred figures of other people from the background. - Rotate the foreground photographs 180 degrees so they face the character looking down at them, not the camera. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, dense fog after rain. SHOT TEXT (authoritative, Korean): 닻줄을 쥔 인우 앞에 선 수리영의 상체. LOCATION (lock): An empty harbor bordered by tidal rocks, with moorings and a landing point for small boats. Dense fog obscures the water and hides other vessels from view. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still carries her backpack, maps, old photograph, and phone as she approaches In-woo, who is holding and securing the mooring line. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, dense fog after rain. SHOT TEXT (authoritative, Korean): 닻줄을 쥔 인우 앞에 선 수리영의 상체. LOCATION (lock): An empty harbor bordered by tidal rocks, with moorings and a landing point for small boats. Dense fog obscures the water and hides other vessels from view. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still carries her backpack, maps, old photograph, and phone as she approaches In-woo, who is holding and securing the mooring line. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment at eye level in an intimate medium close view centered on Su-ri-yeong’s upper body. Use shallow depth so her face, posture, and carried state command the frame while In-woo remains recognizable behind her with the mooring line in his hands, softened by the dense harbor fog. Let the cool, diffuse dusk light after rain model both figures gently, with restrained reflections from the wet surroundings. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, dense fog after rain. SHOT TEXT (authoritative, Korean): 닻줄을 쥔 인우 앞에 선 수리영의 상체. LOCATION (lock): An empty harbor bordered by tidal rocks, with moorings and a landing point for small boats. Dense fog obscures the water and hides other vessels from view. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still carries her backpack, maps, old photograph, and phone as she approaches In-woo, who is holding and securing the mooring line. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot from close beside In-woo in an over-the-shoulder composition, placing his line-holding hands and part of his figure in the immediate foreground while Su-ri-yeong’s upper body fills the opposing plane in front of him. Keep stronger depth definition so the physical relationship between her, In-woo, and the secured mooring line remains legible against the fog-muted harbor. Use the low-contrast dusk ambience and rain-darkened setting to create a tense, grounded sense of proximity. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the anchor logo from the right chest of In-woo's jacket to accurately match the character reference. - Turn the old photograph so that its back faces the camera, hiding the picture side from the viewer. - Redraw In-woo's right gloved hand so the fingers wrap anatomically correctly around the mooring line. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, dense fog after rain. SHOT TEXT (authoritative, Korean): 배에 오르기 전, 바다를 향해 귀에 핸드폰을 댄 채 입술을 굳게 다문 수리영의 옆얼굴. LOCATION (lock): An empty harbor bordered by tidal rocks, with moorings and a landing point for small boats. Dense fog obscures the water and hides other vessels from view. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the dense harbor fog, moored boat, muted sunset light, and the young woman's continuing clothing and position beside the boat from the reference. Exclude the boatman and mooring rope from the tighter phone-call frame unless they remain naturally outside the edge. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Before boarding, Su-ri-yeong holds her phone to her ear to leave a voice message; her backpack, maps, and old photograph remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, dense fog after rain. SHOT TEXT (authoritative, Korean): 배에 오르기 전, 바다를 향해 귀에 핸드폰을 댄 채 입술을 굳게 다문 수리영의 옆얼굴. LOCATION (lock): An empty harbor bordered by tidal rocks, with moorings and a landing point for small boats. Dense fog obscures the water and hides other vessels from view. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the dense harbor fog, moored boat, muted sunset light, and the young woman's continuing clothing and position beside the boat from the reference. Exclude the boatman and mooring rope from the tighter phone-call frame unless they remain naturally outside the edge. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Before boarding, Su-ri-yeong holds her phone to her ear to leave a voice message; her backpack, maps, and old photograph remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her in an intimate eye-level profile close-up, with the phone-side hand and the line of her firmly closed lips held in crisp focus. Use a gently compressed perspective and very shallow depth, letting the moored boat, wet harbor textures, and dense fog dissolve into muted dusk layers behind her. Keep the sea-facing side of the frame open so her fixed gaze and silence press into the negative space. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, dense fog after rain. SHOT TEXT (authoritative, Korean): 배에 오르기 전, 바다를 향해 귀에 핸드폰을 댄 채 입술을 굳게 다문 수리영의 옆얼굴. LOCATION (lock): An empty harbor bordered by tidal rocks, with moorings and a landing point for small boats. Dense fog obscures the water and hides other vessels from view. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the dense harbor fog, moored boat, muted sunset light, and the young woman's continuing clothing and position beside the boat from the reference. Exclude the boatman and mooring rope from the tighter phone-call frame unless they remain naturally outside the edge. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Before boarding, Su-ri-yeong holds her phone to her ear to leave a voice message; her backpack, maps, and old photograph remain with her. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame a restrained side-on medium shot from slightly below shoulder height, placing her beside the boat while preserving the landing point and fog-hidden water as readable spatial layers. Favor deeper focus and a strong foreground-to-background arrangement, using the boat edge and wet harbor geometry to hold her at the threshold before boarding. Let the soft, directional dusk glow trace her facial profile while the broad fog bank dominates the composition ahead of her. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Redraw the right hand so the knuckles are on the back edge of the phone with fingers wrapping forward towards the face. - Move the rear camera module to the phone's top corner closest to the face to correct the mirrored orientation. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 엉망이 된 옥탑방 거실을 배경으로 핸드폰을 귀에 댄 채 굳어버린 혜수의 상체. LOCATION (lock): The same compact rooftop apartment interior, now empty enough for an investigator to stand and listen to a recorded phone message. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the ransacked living-room state, sunset light, footprints, open window, and overturned dining chairs from the reference. Exclude the departing young woman, her backpack, and the photograph, replacing that moment with the investigator listening to the phone message. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains ransacked, with footprints, an open window, overturned chairs, and the red wall circle left after the photograph was removed. Hye-su holds her phone while listening to Su-ri-yeong’s message. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 엉망이 된 옥탑방 거실을 배경으로 핸드폰을 귀에 댄 채 굳어버린 혜수의 상체. LOCATION (lock): The same compact rooftop apartment interior, now empty enough for an investigator to stand and listen to a recorded phone message. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the ransacked living-room state, sunset light, footprints, open window, and overturned dining chairs from the reference. Exclude the departing young woman, her backpack, and the photograph, replacing that moment with the investigator listening to the phone message. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains ransacked, with footprints, an open window, overturned chairs, and the red wall circle left after the photograph was removed. Hye-su holds her phone while listening to Su-ri-yeong’s message. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame Hye-su in an eye-level, near-frontal medium close-up, with her upper body filling most of the image and the phone-hand profile clearly readable. Use a gently compressed perspective and selective focus: hold her face, ear, and phone in crisp detail while the ransacked room remains recognizable but softened behind her. Let the dusk window light fall laterally across her mature features, emphasizing absolute stillness, fixed gaze, and restrained facial tension. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 엉망이 된 옥탑방 거실을 배경으로 핸드폰을 귀에 댄 채 굳어버린 혜수의 상체. LOCATION (lock): The same compact rooftop apartment interior, now empty enough for an investigator to stand and listen to a recorded phone message. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the ransacked living-room state, sunset light, footprints, open window, and overturned dining chairs from the reference. Exclude the departing young woman, her backpack, and the photograph, replacing that moment with the investigator listening to the phone message. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains ransacked, with footprints, an open window, overturned chairs, and the red wall circle left after the photograph was removed. Hye-su holds her phone while listening to Su-ri-yeong’s message. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (한국인 여성, 40대 중반, 성숙한 얼굴선, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment as an environmental upper-body shot from a slightly elevated three-quarter side angle, placing Hye-su off-center while the disordered room occupies the stronger share of the composition. Use a broader, layered perspective and deeper focus so the footprints, overturned chairs, open window, and red wall circle form a legible path through the frame around her rigid posture. Shape the dusk illumination from the window into restrained contrast, allowing the room's depth and emptiness to press visually against her frozen profile. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Turn the cell phone so its screen is pressed against her ear and its back faces outward. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 인우의 등 뒤를 향해 다급하게 팔을 뻗은 채 몸을 크게 기울인 수리영의 전신 실루엣. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong follows In-woo toward the wheelhouse with the old photograph still in her possession; her backpack, maps, and phone remain aboard. The wheelhouse walls are already covered with circular marks. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 인우의 등 뒤를 향해 다급하게 팔을 뻗은 채 몸을 크게 기울인 수리영의 전신 실루엣. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong follows In-woo toward the wheelhouse with the old photograph still in her possession; her backpack, maps, and phone remain aboard. The wheelhouse walls are already covered with circular marks. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment in a low, wide lateral view across the working deck, keeping Su-ri-yeong’s entire body clearly readable from head to feet. Use the dusk sky as soft backlight so her human form, clothing, hair, outstretched arm, and extreme forward lean register in a dark but naturally detailed silhouette; arrange the depth so the direction of her reach toward In-woo’s back is unmistakable. Hold enough surrounding deck and open water in frame to make her precarious posture feel exposed and urgent. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 인우의 등 뒤를 향해 다급하게 팔을 뻗은 채 몸을 크게 기울인 수리영의 전신 실루엣. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong follows In-woo toward the wheelhouse with the old photograph still in her possession; her backpack, maps, and phone remain aboard. The wheelhouse walls are already covered with circular marks. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame from close behind In-woo, using his back as a dominant near-foreground anchor while keeping Su-ri-yeong’s full figure visible farther along the deck. Compress the depth so her urgently extended arm seems to reach across the narrow separation toward him, with her strongly leaning body outlined by restrained dusk backlight. Keep the focus and tonal emphasis on her complete human posture while In-woo’s nearer back creates immediate physical tension and a sense of movement toward the wheelhouse. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the backpack from Su-ri-yeong's back. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 차가운 시선으로 앞을 노려보는 인우의 어깨 위로 고개를 떨군 채 축 늘어진 수리영의 옆얼굴. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the cramped wheelhouse materials, sunset-tinted light, circular wall markings, and the man's continuing clothing and position from the reference. Exclude the pointing hand and old photograph, and frame the unconscious young woman collapsed over his shoulder. IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Soo-ri-young is collapsed forward onto In-woo’s shoulder, with her torso supported against him, her head drooping beside his shoulder, and her limbs hanging limp toward the floor. IMMOBILE BODIES OBEY GRAVITY: a person who is dead or unconscious exerts NO muscular effort. Every part of their body — head, torso, arms, hands, fingers, legs — rests fully on whatever supports it (floor, wall, furniture, their own lap) and hangs or slumps with gravity. NEVER show any part of an immobile person's body lifted, raised, held up in the air, or posed as if presenting something: an object in their grip stays clenched in a hand that itself lies fallen on a support — the hand does not hold the object up. If the canonical pose leaves a body part unspecified, resolve it as the most gravity-compliant, fully-supported position. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong is unconscious and is collapsed forward onto In-woo’s shoulder, with her torso supported against him, her head drooping beside his shoulder, and her limbs hanging limp toward the floor, unable to change her pose herself. Her backpack and personal items, including the old photograph, maps, and phone, remain aboard unless moved by someone else. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 차가운 시선으로 앞을 노려보는 인우의 어깨 위로 고개를 떨군 채 축 늘어진 수리영의 옆얼굴. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the cramped wheelhouse materials, sunset-tinted light, circular wall markings, and the man's continuing clothing and position from the reference. Exclude the pointing hand and old photograph, and frame the unconscious young woman collapsed over his shoulder. IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Soo-ri-young is collapsed forward onto In-woo’s shoulder, with her torso supported against him, her head drooping beside his shoulder, and her limbs hanging limp toward the floor. IMMOBILE BODIES OBEY GRAVITY: a person who is dead or unconscious exerts NO muscular effort. Every part of their body — head, torso, arms, hands, fingers, legs — rests fully on whatever supports it (floor, wall, furniture, their own lap) and hangs or slumps with gravity. NEVER show any part of an immobile person's body lifted, raised, held up in the air, or posed as if presenting something: an object in their grip stays clenched in a hand that itself lies fallen on a support — the hand does not hold the object up. If the canonical pose leaves a body part unspecified, resolve it as the most gravity-compliant, fully-supported position. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong is unconscious and is collapsed forward onto In-woo’s shoulder, with her torso supported against him, her head drooping beside his shoulder, and her limbs hanging limp toward the floor, unable to change her pose herself. Her backpack and personal items, including the old photograph, maps, and phone, remain aboard unless moved by someone else. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph an intimate, eye-level close-up from slightly forward and to the side of In-woo, compressing his cold, fixed gaze and Su-ri-yeong’s drooping side profile over his shoulder into the same narrow plane. Crop tightly around their faces and his shoulder, with shallow focus holding both expressions legible while the cramped cabin and circular forms fall into a soft, sunset-tinted background. Let the window-side dusk light rake gently across their profiles, emphasizing his controlled tension against her complete slackness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, wheelhouse lighting unspecified. SHOT TEXT (authoritative, Korean): 차가운 시선으로 앞을 노려보는 인우의 어깨 위로 고개를 떨군 채 축 늘어진 수리영의 옆얼굴. LOCATION (lock): The enclosed wheelhouse of a small fishing boat, fitted with steering controls and windows overlooking the bow. Numerous circular shapes are visible throughout the cabin. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. PREVIOUS STILL USAGE (follow exactly — what to take from the attached still and what to exclude): Take the cramped wheelhouse materials, sunset-tinted light, circular wall markings, and the man's continuing clothing and position from the reference. Exclude the pointing hand and old photograph, and frame the unconscious young woman collapsed over his shoulder. IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Soo-ri-young is collapsed forward onto In-woo’s shoulder, with her torso supported against him, her head drooping beside his shoulder, and her limbs hanging limp toward the floor. IMMOBILE BODIES OBEY GRAVITY: a person who is dead or unconscious exerts NO muscular effort. Every part of their body — head, torso, arms, hands, fingers, legs — rests fully on whatever supports it (floor, wall, furniture, their own lap) and hangs or slumps with gravity. NEVER show any part of an immobile person's body lifted, raised, held up in the air, or posed as if presenting something: an object in their grip stays clenched in a hand that itself lies fallen on a support — the hand does not hold the object up. If the canonical pose leaves a body part unspecified, resolve it as the most gravity-compliant, fully-supported position. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong is unconscious and is collapsed forward onto In-woo’s shoulder, with her torso supported against him, her head drooping beside his shoulder, and her limbs hanging limp toward the floor, unable to change her pose herself. Her backpack and personal items, including the old photograph, maps, and phone, remain aboard unless moved by someone else. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리); 인우 (한국인 남성, 20대 중반, 젊고 단정한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a restrained side-on medium shot from within the wheelhouse, framing In-woo in firm profile as he stares toward the bow while Su-ri-yeong’s limp head and side face hang visibly beyond his shoulder. Keep more of the steering area, windows, and repeated circular cabin details in view, arranging them in layered depth around the pair rather than isolating them. Favor deeper focus and directional dusk illumination from the windows, making his forward drive and her gravity-heavy collapse read through the opposing lines of their bodies. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Swap their garments so In-woo wears his olive green jacket and Su-ri-yeong wears her dark grey hooded jacket. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 들것 위에 천으로 덮인 시신을 내려다보는 구도 LOCATION (lock): Two outdoor crime scenes—a forest trail area and an urban back alley—sealed with police lines as officers examine the ground and recover bodies. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The corpse remains motionless on the stretcher beneath its covering cloth as it is collected. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 들것 위에 천으로 덮인 시신을 내려다보는 구도 LOCATION (lock): Two outdoor crime scenes—a forest trail area and an urban back alley—sealed with police lines as officers examine the ground and recover bodies. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The corpse remains motionless on the stretcher beneath its covering cloth as it is collected. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the stretcher from a close, nearly vertical overhead position, with the cloth-covered corpse dominating the frame. Use a restrained, geometrically ordered composition and crisp natural daylight, holding enough surrounding ground at the edges to anchor the physical crime-scene location while emphasizing absolute stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 들것 위에 천으로 덮인 시신을 내려다보는 구도 LOCATION (lock): Two outdoor crime scenes—a forest trail area and an urban back alley—sealed with police lines as officers examine the ground and recover bodies. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The corpse remains motionless on the stretcher beneath its covering cloth as it is collected. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a wider high-oblique view that looks down along the length of the stretcher, placing the covered corpse off center within the visible crime-scene surroundings. Build depth through the diagonal stretcher and receding ground, with subdued daylight contrast and selective focus that isolates the covered form without obscuring the established location. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the camera angle to a nearly vertical overhead position looking directly down at the stretcher. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 8 - camera_cell: [0, 4] - look_at_unit: 1 - look_at_cell: [7, 4] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Broad establishing coverage from camera unit 8 toward look-at unit 1, using listed cell [7,4] to include the committed structural and persistent markers required by S4_Shot1.' RENDER GUIDANCE (from validated plan): - visible_space_directive: From camera unit 8, show broad coverage toward unit 1, with committed target units 1, 2, 3, 8, 9, 10, and 11 represented only where supported by the view. Establish the fixed layout of base markers 1 through 12, including openings 6 and 7 and persistent markers 4, 5, and 12. - camera_framing_directive: Use broad 90-degree coverage from camera unit 8 at cell [0,4], directed toward look-at unit 1 through listed look-at cell [7,4]. Preserve the wide establishing scale committed for S4_Shot1, with marker 2 as the primary architectural focus and the surrounding unit-marker arrangement providing spatial context. - subject_position_directive: S4_Shot1 commits no subjects or character angles. Keep the background free of invented subjects and let the marker-2 structure remain the primary architectural focal point within the broad frame. - state_cue_directive: No committed state cue beyond a clean residential space applies because clean_background_expected is true and no transient markers are listed. Keep the background clean and refrain from inventing additional state cues. - negative_continuity_directive: Exclude overlay markers 13, 14, 15, and 16. Do not add scenario-specific subjects or props, and do not extend the composition to unrelated detail beyond the committed marker layout and the units supported by the camera-unit-8 visibility superset. 2026년 대한민국 서해안권의 오래된 저층 다세대 주택가에 자리한 옥탑방 옥상 외부의 낮 전경. 인접한 더 높은 건물 옥상에서 카메라를 바닥 기준 약 1.6m의 사람 눈높이에 두고, 대상 옥상의 남서쪽 모서리와 남쪽 난간벽 부근 위로 시선을 맞춘 뒤 옥상 테라스를 가로질러 옥탑 주거 공간과 물탱크 방향으로 비스듬히 바라본 높은 사선 조망이다. 실제 풀프레임 DSLR 또는 미러리스 카메라와 24mm 광각 렌즈로 촬영한 다큐멘터리 풍 사진이며, 수직 하향 시점이나 평면도처럼 보이지 않게 한다. 옥상의 완전한 외곽 윤곽과 네 방향 난간벽이 모두 프레임 안에 들어오고, 계단 진입부, 철제 받침 위의 생활용 물탱크, 빨랫줄과 소박한 빨래, 낮은 금속 건조대, 옥탑방의 낡은 금속 출입문과 작은 새시 창문이 분명히 보인다. 바닥은 한국 저층 주택 옥상에서 흔한 녹색 우레탄 방수 도장으로 마감되어 있으며 햇빛과 염분 섞인 해풍에 바랜 부분, 미세한 균열, 덧칠 자국과 빗물 얼룩이 자연스럽게 남아 있다. 난간벽과 옥탑방 외벽은 오래된 시멘트 미장과 빛바랜 연한 베이지색 도장, 일부 노출된 붉은 벽돌과 화강석 계열 외장 타일이 혼재하고, 창문 방범창, 에어컨 실외기와 외부 배관, 외벽을 따라 이어지는 가스 배관과 계량기, 작은 화분 몇 개가 층층이 보여 실제 거주 흔적을 만든다. 그러나 옥상은 정상적으로 관리되는 평범한 낮 상태이며 깨진 창문, 뜯긴 문, 강제 침입 흔적, 흩어진 잔해는 없다. 주변에는 비슷한 연식의 붉은 벽돌 및 석재 타일 외장 다세대 주택들이 촘촘히 이어지고, 좁은 골목, 전신주, 느슨하게 늘어진 전선, 주차된 소형 생활 차량이 보여 대상 건물이 실제 동네 속에 자연스럽게 연결된다. 해안 도시 특유의 옅은 대기 습도와 담백한 주간 자연광, 절제된 회백색·바랜 녹색·벽돌색 계열, 실제 콘크리트의 거친 표면, 금속의 녹과 산화 흔적, 직물의 올, 목재와 플라스틱의 생활 마모를 정확히 표현한다. 과장된 명암이나 인위적인 분위기 연출 없이 자연스러운 노출과 현실적인 원근감, 자연스러운 피사계 심도를 유지한다. 사람과 얼굴은 전혀 없으며, 초자연적 표식이나 붉은 원형 기호도 없다. 깨끗한 광고 사진, 컴퓨터 그래픽, 삽화, 건축 시각화가 아니라 후처리하지 않은 실제 장소 기록용 카메라 사진. 16:9 가로 비율, 실제 카메라 촬영본 The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Swap the positions of the door and the window on the rooftop room's front wall to match the reference plan. - Remove the external staircase attached to the left side of the rooftop room. - Add metal security bars over the small sash window. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 도심 변두리의 오래된 빌라 옥탑방이 내려다보이는 부감 구도 LOCATION (lock): The rooftop level of an old low-rise residential building on the outskirts of a city, with a small rooftop dwelling visible in an elevated establishing view. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 도심 변두리의 오래된 빌라 옥탑방이 내려다보이는 부감 구도 LOCATION (lock): The rooftop level of an old low-rise residential building on the outskirts of a city, with a small rooftop dwelling visible in an elevated establishing view. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from a steep, near-vertical overhead position in a wide establishing frame. Let the rooftop dwelling anchor the composition while the surrounding roof plane and building edges form strong geometric layers, with crisp spatial separation and restrained documentary realism. Use the existing daylight to reveal surface texture without dramatizing or altering the location. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 도심 변두리의 오래된 빌라 옥탑방이 내려다보이는 부감 구도 LOCATION (lock): The rooftop level of an old low-rise residential building on the outskirts of a city, with a small rooftop dwelling visible in an elevated establishing view. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a distant, oblique high-angle viewpoint with compressed perspective, framing the rooftop dwelling within the layered surroundings rather than looking straight down. Keep the composition dense and observational, allowing foreground and background planes to visually press around the small structure. Preserve the natural direction, contrast, and color of the established daylight for a quiet, lived-in urban mood. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Replace all surrounding streets, adjacent buildings, and the background environment to exactly match the surroundings shown in the LOCATION photograph. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows the SAME physical room as this background, from a different camera angle or framing. Inherit the exact architecture, floor, walls, windows, fixed furniture and lighting of that room — this is literally the same space, only the viewpoint changes. REFERENCE PLAN: mode='same_physical_space_view' - selected_refs[0]: ref_bg_id='L04B01' physical_space_id='fp_l04_rooftop_exterior_space_1' CAMERA DECISION (exact, from validated plan): - camera_unit: 1 - camera_cell: [5, 4] - look_at_unit: 2 - look_at_cell: [4, 6] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Neutral medium coverage from camera unit 1 toward look-at unit 2, using listed cell [4,6] to center the opening-marker plane required by S10_Shot6.' RENDER GUIDANCE (from validated plan): - visible_space_directive: From camera unit 1, direct the view toward unit 2 and opening marker 7, retaining the same fixed physical layout established by L04B01. The neutral view may include adjacent opening marker 6 and supported portions of target units 1, 2, 3, 9, and 10, but opening marker 7 remains the sole committed action plane. - camera_framing_directive: Use neutral 50-degree coverage from camera unit 1 at cell [5,4], directed toward look-at unit 2 through listed look-at cell [4,6]. Hold the medium, static, square presentation committed by S10_Shot6, with opening marker 7 functioning as the central reflected-action plane and opening marker 6 included only as allowed by the neutral coverage. - subject_position_directive: S10_Shot6 commits two reflected silhouettes in the midground within opening marker 7: one in the middle-right moving diagonally toward the other, and one in the middle-left recoiling. Keep the reflection surface in the foreground middle-center and show no bodies directly outside the reflected plane. - state_cue_directive: Carry transient markers 13, 14, 15, and 16 exactly as committed for this BG, together with use markers 1 through 7, 9, 10, and 12. Marker 16 must read on the reflected plane associated with opening marker 7, while markers 13, 14, and 15 remain tied to their supplied transient-marker placements without introducing additional state cues. - negative_continuity_directive: Keep the fixed positions inherited from L04B01 for base markers 1 through 7, 9, 10, and 12. Do not shift openings 6 or 7, persistent markers 4 or 5, or marker 12; do not import marker 8 or marker 11 into this narrower committed view unless supported by the view cone; and do not show the committed reflected subjects directly outside opening marker 7. 2026년 대한민국 서해안권 도시 또는 고립된 섬의 오래된 저층 주택 옥상, 밤중에 은밀하지만 거칠게 강제 침입이 벌어진 직후의 텅 빈 옥탑방 외부. 실제 카메라로 촬영한 다큐멘터리 풍 사진이며, 남쪽 옥상 난간 가까이에서 약 1.6미터의 서 있는 사람 눈높이로 계단참과 좁은 접근 통로를 대각선으로 가로질러 옥탑방 철문과 작은 거실 창문을 바라본다. 35밀리미터급 렌즈의 자연스러운 넓은 화각으로 옥탑방 입면, 철문, 창문을 선명하게 주요 프레임에 담고, 물탱크와 빨랫줄 및 낮은 건조대는 어둠 속 공간 깊이를 잡아 주는 실루엣으로 남긴다. 낡은 저층 주택 옥상에서 흔히 보이는 바랜 녹색 우레탄 방수 바닥에는 균열, 빗물 얼룩, 덧칠 자국과 염분 섞인 먼지가 있고, 옥탑방 외벽은 오래된 시멘트 미장과 부분적인 붉은 벽돌 또는 화강석 타일 마감이 생활 흔적과 함께 드러난다. 철문은 얇은 도장 강판과 녹슨 경첩, 손때 묻은 손잡이를 지녔으며 문틀 잠금 부근에 방금 생긴 듯한 날카로운 지렛대 긁힘과 약간 벌어진 틈이 있다. 작은 알루미늄 새시 거실 창문에는 생활형 방범창이 달려 있고 일부가 국소적으로 휘어 있으며, 잠금쇠 주변이 억지로 밀린 흔적과 한쪽 유리의 금, 창 아래 바닥에 소량의 실제 유리 파편이 남아 있다. 파괴 흔적은 소리를 줄이며 침입하려 한 듯 제한된 범위에 집중되고, 과장된 폭발이나 대규모 잔해는 없다. 창 안쪽은 거의 꺼진 실내로 보이며 식별 가능한 사람이나 얼굴, 신체, 혈흔은 전혀 없다. 외벽에는 현실적인 에어컨 실외기와 노출 배관, 가스 배관과 계량기, 전선 고정구가 층층이 붙어 있고, 옥상에는 검은 물탱크, 늘어진 빨랫줄과 몇 벌의 평범한 세탁물, 플라스틱 화분과 소소한 생활 잡동사니가 자연스럽게 놓여 있다. 주변에는 같은 시대의 붉은 벽돌 및 타일 외장 저층 주택 옥상들이 가까이 밀집하고, 알루미늄 새시 창, 방범창, 실외기, 물탱크, 전신주와 늘어진 전선이 이어져 실제 사람이 사는 해안 동네처럼 보여야 한다. 멀리 희미한 항구 또는 골목 조명과 습한 해무가 느껴지되 특정 표지나 상호는 없다. 꺼져 가는 옥상 방범등의 약한 누런 빛과 주변 건물에서 새어 오는 차가운 야간광이 섞여 철문과 창문의 침입 흔적만 현실적으로 드러내며, 깊은 그림자에도 실제 재료의 세부가 일부 남는다. 실제 콘크리트의 거친 입자, 녹슨 금속의 산화 얼룩, 유리 반사, 천의 직조, 플라스틱의 변색을 정확하게 표현하고 일상적인 마모와 습기 자국을 유지한다. 자연스러운 피사계 심도와 현실적인 야간 노출, 과도한 후보정 없는 실제 장소 기록 사진. 사람 없음, 얼굴 없음, 인체 없음, 피 없음. 위에서 내려다보는 시점이 아니며 평면도, 건축 도식, 삽화, 합성 이미지가 아니다. 16:9 가로 비율, 실제 카메라 촬영본 The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Rearrange the facade layout to match the reference image by placing the barred window on the left and the steel door on the right. - Close the steel door so it only has a slightly open gap near the lock, instead of being wide open. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 창문에 비친 그림자 속, 정체불명의 습격자의 실루엣이 민숙을 덮쳐 어깨를 강하게 물어뜯는 찰나의 역동적인 모습 LOCATION (lock): An exposed rooftop above an old residential building, fitted with a water tank, clotheslines, a drying platform covered with herbs, and a metal entrance door to a small rooftop apartment. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop-room door remains slightly open after the intruder’s entry. Minsuk still bears the small circular wrist mark as the attacker bites her shoulder. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 창문에 비친 그림자 속, 정체불명의 습격자의 실루엣이 민숙을 덮쳐 어깨를 강하게 물어뜯는 찰나의 역동적인 모습 LOCATION (lock): An exposed rooftop above an old residential building, fitted with a water tank, clotheslines, a drying platform covered with herbs, and a metal entrance door to a small rooftop apartment. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop-room door remains slightly open after the intruder’s entry. Minsuk still bears the small circular wrist mark as the attacker bites her shoulder. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the window reflection as the dominant image in a tight, tense composition, with the physical figures compressed into layered reflected depth yet retaining readable human anatomy, clothing, and facial performance. Use a slightly canted eye-level viewpoint and a close, urgent lens feel; let the force of the movement cut diagonally through the frame while hard, grazing night illumination gives the reflected action sharp separation without turning either person into an abstract silhouette. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 창문에 비친 그림자 속, 정체불명의 습격자의 실루엣이 민숙을 덮쳐 어깨를 강하게 물어뜯는 찰나의 역동적인 모습 LOCATION (lock): An exposed rooftop above an old residential building, fitted with a water tank, clotheslines, a drying platform covered with herbs, and a metal entrance door to a small rooftop apartment. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop-room door remains slightly open after the intruder’s entry. Minsuk still bears the small circular wrist mark as the attacker bites her shoulder. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a low, wider viewpoint that holds the immediate physical struggle in the foreground while the window reflection occupies a strong secondary plane, echoing the attack through shadow and movement. Build pronounced foreground-to-background depth from the rooftop architecture, with the open doorway and fixed rooftop elements anchoring the composition; keep the illumination sparse and directional so the figures remain fully human and legible while the reflected attacker reads as ominous and unidentified. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Render the figures entirely as a reflection on the exterior of the window glass, rather than showing them inside the room. - Adjust the rooftop room door so it is only slightly open. - Modify the door's design, material, and color to exactly match the brown metal door in the location reference photograph. - Change the window bars to match the reference photograph, featuring vertical bars with only a single horizontal bar in the middle. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.








STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 7 - camera_cell: [2, 6] - look_at_unit: 9 - look_at_cell: [3, 4] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Place the camera in unit 7 at cell [2,6] and aim toward unit 9 at listed look-at cell [3,4]. The normal lens provides neutral medium coverage centered on marker 10 while retaining surrounding elements from units 7, 8, and 9.' RENDER GUIDANCE (from validated plan): - visible_space_directive: From unit 7, show the approach into units 8 and 9, centered toward marker 10 at look-at cell [3,4]. Retain marker 7 as the approach anchor and include the committed surrounding markers 11, 12, 13, and 14 where supported by the normal view. - camera_framing_directive: Use camera unit 7 at cell [2,6], looking toward unit 9 at cell [3,4] with a normal 50-degree field of view. Maintain neutral medium coverage with marker 10 squarely in the middle third and enough surrounding structure from units 7, 8, and 9 to establish scale. - subject_position_directive: S11_Shot4 commits no visible subject in the frame; it is a direct subjective viewpoint. Keep the background free of invented subjects and reserve the middle center for marker 10 and overlay marker 17. - state_cue_directive: Render overlay marker 17 as the committed half-open state of marker 10. Retain numbered elements 7 through 14 as fixed background structure and fixtures, and add no other transient state cue. - negative_continuity_directive: Exclude overlay markers 15 and 16. Do not introduce unlisted state overlays, subjects, or numbered elements outside the committed set 7, 8, 9, 10, 11, 12, 13, 14, and 17, and do not expand the composition to units outside the selected unit-7-to-unit-9 view. 2026년 현대 대한민국 서해안권 도시의 오래된 저층 다세대주택 옥상, 밤의 계단 상부 도착참에서 옥상 테라스를 대각선으로 가로질러 옥탑방 현관을 바라보는 실제 카메라로 촬영한 다큐멘터리 풍 사진. 카메라는 사람이 서 있는 약 1.6m 눈높이이며 35mm급 광각 렌즈를 사용한다. 위에서 내려다본 시점, 평면도, 건축 도면이 아니라 현장에 직접 서서 본 자연스러운 원근감이다. 낡은 옥탑방 외벽에 달린 무거운 철제 현관문이 구도의 지배적인 종착점이다. 철문은 완전히 닫히지 않고 수상하게 반쯤 열려 있으며, 좁은 문틈 너머에는 불이 꺼진 실내의 현실적인 어둠만 보인다. 문손잡이와 문틀에는 반복 사용으로 생긴 긁힘, 벗겨진 도장, 작은 녹 자국과 손때가 남아 있다. 초자연적 형상이나 인물은 없다. 철문 옆 옥탑방 입면에는 오래된 알루미늄 새시 창과 금속 방범창이 있고, 창유리는 밤하늘과 옥상 조명을 희미하게 반사한다. 옥탑방은 한국 저층 주거에서 흔한 붉은 벽돌 또는 낡은 석재 타일 마감과 부분적으로 덧바른 시멘트 보수 흔적을 지닌 실물 주거 형태다. 옥상 바닥은 바랜 녹색 우레탄 방수 도장으로 마감되어 있으며 균열, 빗물 얼룩, 덧칠 자국, 배수구 주변의 검은 물때가 자연스럽다. 차가운 백색 벽부등 하나가 철문 주변과 바닥 일부를 불균일하게 밝히고, 반쯤 열린 문이 바닥에 단단한 그림자를 만든다. 조명이 닿지 않는 구석은 낮은 밝기로 남되 재료의 세부가 과도하게 사라지지 않는다. 프레임 주변에는 낮은 콘크리트 파라펫과 금속 계단 난간, 에어컨 실외기와 외벽을 따라 연결된 냉매 배관, 노출 가스 배관과 계량기, 물탱크, 전선과 소형 배전함, 느슨한 빨랫줄, 몇 개의 생활 화분과 소박한 옥상 잡동사니가 층층이 보인다. 모든 설비에는 염분 섞인 해풍과 비에 노출된 현실적인 먼지, 산화, 물자국과 일상적 마모가 있다. 난간 너머로는 비슷한 높이의 붉은 벽돌·타일 외장 주택들이 밀집해 있고, 새시 창, 방범창, 에어컨 실외기, 물탱크, 전신주와 늘어진 전선이 희미한 야간 배경을 이룬다. 멀리 있는 생활 조명만 드문드문 보이며 미래형 장비나 과장된 장식은 없다. 실제 콘크리트, 녹슨 금속의 산화층, 벗겨진 페인트, 유리 반사, 고무 배관, 벽돌 줄눈과 방수 도막의 질감을 정확하게 표현한다. 깨끗한 광고 사진이 아니라 사람이 실제 거주하는 장소의 평범한 때와 불균일함이 남은 현장 기록 사진이다. 실제 DSLR 또는 미러리스 카메라 촬영, 현실적인 야간 노출과 자연스러운 심도, 과도한 후보정 없음. CGI, 삽화, 건축 시각화가 아니며 사람, 얼굴, 시신, 피는 없다. 16:9 가로 비율, 실제 카메라 촬영본. One attached image is a PHOTOREAL RENDER of the SAME building/site this scene belongs to — it may show the outside while this scene is inside, or another part of the same place. Treat it as the BUILDING IDENTITY reference. Keep this render consistent with it: the same era, age and state of repair, the same palette and material quality, the same window and door frame styles, and anything visible through openings (windows, doorways, passages) must belong to that same building and its surroundings. Signage follows the place's nature: a commercial or public facility keeps its signage present and legible; a residential or private place has none unless the prompt says so. Reproduce any signage visible in the reference EXACTLY — same lettering, same design, same position; never invent different sign text from render to render. Lighting and time of day follow THIS prompt. Do NOT copy the reference's composition, framing or camera angle; only the building's physical identity carries over. The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove all the circular graphic overlays containing numbers (8, 9, 10, 13, 14) from the scene. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 반쯤 열린 옥탑방 현관 철문이 정면으로 보이는 시점 쇼트 LOCATION (lock): A narrow residential alley and the courtyard of a low-rise multi-unit building, with a secluded bicycle parking spot and an exterior stairway leading to the rooftop apartment and its half-open metal door. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop-room iron entrance door remains half open; Su-ri-yeong’s bicycle stays parked below in the courtyard. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 반쯤 열린 옥탑방 현관 철문이 정면으로 보이는 시점 쇼트 LOCATION (lock): A narrow residential alley and the courtyard of a low-rise multi-unit building, with a secluded bicycle parking spot and an exterior stairway leading to the rooftop apartment and its half-open metal door. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop-room iron entrance door remains half open; Su-ri-yeong’s bicycle stays parked below in the courtyard. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from a restrained medium-long distance on a square, head-on axis to the entrance, with a compressed lens feel that flattens the stairway and rooftop structure into taut architectural layers. Hold the half-open door near the exact visual center, using the surrounding walls and openings as a rigid frame; keep the courtyard and parked bicycle low and subordinate in the composition. Preserve the location’s established night illumination with controlled contrast and a quiet, watchful stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 반쯤 열린 옥탑방 현관 철문이 정면으로 보이는 시점 쇼트 LOCATION (lock): A narrow residential alley and the courtyard of a low-rise multi-unit building, with a secluded bicycle parking spot and an exterior stairway leading to the rooftop apartment and its half-open metal door. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop-room iron entrance door remains half open; Su-ri-yeong’s bicycle stays parked below in the courtyard. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a wider environmental view from a low courtyard height while keeping the entrance face-on, letting the exterior stairway form a strong ascending path toward the half-open door. Build pronounced foreground-to-background depth, with the parked bicycle anchoring the lower courtyard and the doorway held smaller but unmistakably dominant at the end of the composition. Render the established night light naturally, allowing darker architectural planes and open space to create suspense without obscuring structural detail. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Reposition the camera to a square, head-on axis directly facing the rooftop entrance door, holding the door near the exact visual center. - Move the parked bicycle from the exterior alley into the walled courtyard below the stairway. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows a related part of the same dwelling, not the current room. Inherit the overall material and lighting identity only; the new space is its own architectural room and must read as the same home. REFERENCE PLAN: mode='related_style_new_space' - selected_refs[0]: ref_bg_id='L05B02' physical_space_id='ps_shared_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [4, 3] - look_at_unit: 5 - look_at_cell: [6, 8] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use broad coverage from unit 2 toward unit 5, looking at listed cell [6,8] associated with base marker 24 so marker 10 and the unit-5 fixed markers can establish a clean representative view.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show target unit 5 from unit 2 through the marker-10 connection, with base markers 12, 24, and 25 fixed according to the floor plan. Include unit-2 marker 19 only where supported by the broad view. - camera_framing_directive: Use broad 90-degree coverage from camera unit 2 at [4,3] toward unit 5 at [6,8]. Establish marker 24 as the principal look-at anchor while retaining marker 10 and enough unit-5 context for markers 12 and 25 and for the close crop in S14_Shot4. - subject_position_directive: S14_Shot3 commits no subject, so keep the broad background free of invented subjects. For S14_Shot4, place the single committed subject in a tight three-quarter view on the right, with the marker-12 area remaining softly legible on the left. - state_cue_directive: No committed state cue beyond clean residential space applies. Keep base markers 2, 5, 10, 12, 19, 24, and 25 in their persistent clean state and refrain from inventing additional cues. - negative_continuity_directive: Do not import the fixed furniture arrangement of units 1 and 3 from L05B02 into unit 5. Exclude overlay markers 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, and 39, and do not add unlisted state cues or spaces beyond targets 2 and 5. 2026년 대한민국 서해안권 도시의 옥상 주거 공간 안에 있는 작고 소박한 딸 방을 촬영한 실제 카메라 다큐멘터리 풍 사진. 딸 방 출입문 바로 안쪽 가까운 위치에서 약 1.6미터의 서 있는 사람 눈높이로, 풀프레임 미러리스 카메라와 30밀리미터 광각 렌즈를 사용해 방 안을 대각선으로 바라본다. 시선은 방 안쪽의 침대와 커튼이 달린 현대식 새시 창문을 향하며, 열린 출입문 가장자리 너머로 인접 공간의 깨끗한 식탁 일부가 자연스럽게 보인다. 침대는 사람이 방금 정리한 수준을 넘어 비정상적으로 반듯하고 흐트러짐이 없으며, 실제 섬유 조직이 보이는 평범한 침구에는 주름, 먼지, 얼룩이 거의 없다. 바닥은 작은 먼지나 머리카락, 끌린 자국조차 없이 깨끗하고, 벽도 닦아 낸 자국이나 변색 경계 없이 지나치게 말끔하다. 커튼은 실제 직물의 무게와 잔주름을 지니지만 창 주변과 커튼 안쪽의 오목한 공간에는 물건, 얼룩, 잔해가 전혀 없어 텅 빈 상태가 강조된다. 이전에 존재했을 법한 피, 신체, 붉은 원형 상징, 문자, 의식 흔적, 파손, 흩어진 물건은 현재 공간에 단 하나도 남아 있지 않으며, 지워진 자국이나 청소 흔적조차 보이지 않는다. 현대 한국의 소규모 옥상방에 어울리는 실용적인 마감, 평범한 도장 벽, 합성 바닥재, 금속과 플라스틱이 섞인 새시 창호를 사실적으로 표현한다. 밤의 실내로, 천장 생활 조명의 낮고 균일한 빛과 커튼 틈으로 스며드는 희미한 도시 야간광이 섞이며 과도한 장식 없이 차갑고 불편할 만큼 정돈된 분위기를 만든다. 실제 벽 도장의 미세한 요철, 바닥재의 약한 반사, 금속 창틀의 사용감, 커튼의 직물 짜임, 침구의 자연스러운 재질을 정확히 담고, 생활 공간 특유의 미세한 마모는 남기되 최근의 사건 흔적은 전혀 남기지 않는다. 자연스러운 원근과 깊이감, 현실적인 노출과 피사계 심도, 과장 없는 색, 후처리 없는 현장 기록 사진. 깨끗한 광고 사진이나 인테리어 화보가 아니라 실제 장소를 사실대로 기록한 무심한 사진이며, 컴퓨터 그래픽이나 삽화가 아니다. 하향식 시점, 평면도, 건축 도식은 금지한다. 사람과 얼굴은 등장하지 않는다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 민숙의 차갑게 굳은 손안에 구겨진 채 쥐어져 있는 낡은 사진 한 장의 클로즈업. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Min-suk remains dead, seated on the floor behind the curtain with her torso slumped and her head dropped forward, with the torn shoulder wounds, while the crumpled old photograph stays clenched in her cold hand and the wrist mark remains present. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 민숙의 차갑게 굳은 손안에 구겨진 채 쥐어져 있는 낡은 사진 한 장의 클로즈업. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Min-suk remains dead, seated on the floor behind the curtain with her torso slumped and her head dropped forward, with the torn shoulder wounds, while the crumpled old photograph stays clenched in her cold hand and the wrist mark remains present. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph an extreme close-up from nearly perpendicular to the clenched hand, filling the frame with the rigid fingers and crumpled old photograph while excluding the rest of the body. Use shallow focus that holds the gripping fingertips and crushed folds sharply, with soft television and lamp light revealing the cold, dry texture and leaving the frame edges subdued. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 민숙의 차갑게 굳은 손안에 구겨진 채 쥐어져 있는 낡은 사진 한 장의 클로즈업. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Min-suk remains dead, seated on the floor behind the curtain with her torso slumped and her head dropped forward, with the torn shoulder wounds, while the crumpled old photograph stays clenched in her cold hand and the wrist mark remains present. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot from floor height at a tight oblique side angle, letting the clenched hand form a stark foreground profile around the compressed photograph. Use raking mixed television and lamp light to catch the knuckles, fixed finger joints, and raised paper creases, with a narrow plane of focus and the apartment interior dissolving into dim, indistinct depth. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the black text from the bottom left corner of the crumpled photograph. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows a related part of the same dwelling, not the current room. Inherit the overall material and lighting identity only; the new space is its own architectural room and must read as the same home. REFERENCE PLAN: mode='related_style_new_space' - selected_refs[0]: ref_bg_id='L05B02' physical_space_id='ps_shared_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [4, 3] - look_at_unit: 5 - look_at_cell: [6, 8] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use broad coverage from unit 2 toward unit 5, looking at listed cell [6,8] associated with base marker 24 so marker 10 and the unit-5 fixed markers can establish a clean representative view.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show target unit 5 from unit 2 through the marker-10 connection, with base markers 12, 24, and 25 fixed according to the floor plan. Include unit-2 marker 19 only where supported by the broad view. - camera_framing_directive: Use broad 90-degree coverage from camera unit 2 at [4,3] toward unit 5 at [6,8]. Establish marker 24 as the principal look-at anchor while retaining marker 10 and enough unit-5 context for markers 12 and 25 and for the close crop in S14_Shot4. - subject_position_directive: S14_Shot3 commits no subject, so keep the broad background free of invented subjects. For S14_Shot4, place the single committed subject in a tight three-quarter view on the right, with the marker-12 area remaining softly legible on the left. - state_cue_directive: No committed state cue beyond clean residential space applies. Keep base markers 2, 5, 10, 12, 19, 24, and 25 in their persistent clean state and refrain from inventing additional cues. - negative_continuity_directive: Do not import the fixed furniture arrangement of units 1 and 3 from L05B02 into unit 5. Exclude overlay markers 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, and 39, and do not add unlisted state cues or spaces beyond targets 2 and 5. 2026년 대한민국 서해안권 도시의 옥상 주거 공간 안에 있는 작고 소박한 딸 방을 촬영한 실제 카메라 다큐멘터리 풍 사진. 딸 방 출입문 바로 안쪽 가까운 위치에서 약 1.6미터의 서 있는 사람 눈높이로, 풀프레임 미러리스 카메라와 30밀리미터 광각 렌즈를 사용해 방 안을 대각선으로 바라본다. 시선은 방 안쪽의 침대와 커튼이 달린 현대식 새시 창문을 향하며, 열린 출입문 가장자리 너머로 인접 공간의 깨끗한 식탁 일부가 자연스럽게 보인다. 침대는 사람이 방금 정리한 수준을 넘어 비정상적으로 반듯하고 흐트러짐이 없으며, 실제 섬유 조직이 보이는 평범한 침구에는 주름, 먼지, 얼룩이 거의 없다. 바닥은 작은 먼지나 머리카락, 끌린 자국조차 없이 깨끗하고, 벽도 닦아 낸 자국이나 변색 경계 없이 지나치게 말끔하다. 커튼은 실제 직물의 무게와 잔주름을 지니지만 창 주변과 커튼 안쪽의 오목한 공간에는 물건, 얼룩, 잔해가 전혀 없어 텅 빈 상태가 강조된다. 이전에 존재했을 법한 피, 신체, 붉은 원형 상징, 문자, 의식 흔적, 파손, 흩어진 물건은 현재 공간에 단 하나도 남아 있지 않으며, 지워진 자국이나 청소 흔적조차 보이지 않는다. 현대 한국의 소규모 옥상방에 어울리는 실용적인 마감, 평범한 도장 벽, 합성 바닥재, 금속과 플라스틱이 섞인 새시 창호를 사실적으로 표현한다. 밤의 실내로, 천장 생활 조명의 낮고 균일한 빛과 커튼 틈으로 스며드는 희미한 도시 야간광이 섞이며 과도한 장식 없이 차갑고 불편할 만큼 정돈된 분위기를 만든다. 실제 벽 도장의 미세한 요철, 바닥재의 약한 반사, 금속 창틀의 사용감, 커튼의 직물 짜임, 침구의 자연스러운 재질을 정확히 담고, 생활 공간 특유의 미세한 마모는 남기되 최근의 사건 흔적은 전혀 남기지 않는다. 자연스러운 원근과 깊이감, 현실적인 노출과 피사계 심도, 과장 없는 색, 후처리 없는 현장 기록 사진. 깨끗한 광고 사진이나 인테리어 화보가 아니라 실제 장소를 사실대로 기록한 무심한 사진이며, 컴퓨터 그래픽이나 삽화가 아니다. 하향식 시점, 평면도, 건축 도식은 금지한다. 사람과 얼굴은 등장하지 않는다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 침대 위 벽면에 피로 그린 듯한 붉은색 원형 표식이 뚜렷하게 떠오른 정지 구도. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk’s corpse remains seated behind the curtain with the same wounds, but Su-ri-yeong has now removed the photograph from her hand and the wrist mark has turned red. A newly formed red circle remains visible on the wall above the bed. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 침대 위 벽면에 피로 그린 듯한 붉은색 원형 표식이 뚜렷하게 떠오른 정지 구도. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk’s corpse remains seated behind the curtain with the same wounds, but Su-ri-yeong has now removed the photograph from her hand and the wrist mark has turned red. A newly formed red circle remains visible on the wall above the bed. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a locked-off, eye-level frontal composition with the bed forming a quiet horizontal base and the wall dominating the frame. Center the red circular mark above it in crisp focus, using the dim television and lamp illumination to create restrained tonal contrast and an unnervingly static, evidentiary stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim interior with television and lamp light. SHOT TEXT (authoritative, Korean): 침대 위 벽면에 피로 그린 듯한 붉은색 원형 표식이 뚜렷하게 떠오른 정지 구도. LOCATION (lock): A compact rooftop apartment with a living room, dining table, small kitchen, main bedroom, and a separate young woman's bedroom with a bed, curtains, and a window. The living room contains a cooled cooking pot, a television left on, and a dim floor or table lamp. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk’s corpse remains seated behind the curtain with the same wounds, but Su-ri-yeong has now removed the photograph from her hand and the wrist mark has turned red. A newly formed red circle remains visible on the wall above the bed. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from close to the bed at a low, oblique angle, letting the near edge of the bed anchor the foreground while the wall rises steeply behind it. Frame tightly around the red circular mark and its immediate surroundings, with shallow depth separation and raking dim interior light revealing its irregular, blood-like surface against the wall. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Move the red circular mark to the right so it is on the wall directly above the bed. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows a related part of the same dwelling, not the current room. Inherit the overall material and lighting identity only; the new space is its own architectural room and must read as the same home. REFERENCE PLAN: mode='related_style_new_space' - selected_refs[0]: ref_bg_id='L05B02' physical_space_id='ps_shared_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [4, 3] - look_at_unit: 5 - look_at_cell: [6, 8] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use broad coverage from unit 2 toward unit 5, looking at listed cell [6,8] associated with base marker 24 so marker 10 and the unit-5 fixed markers can establish a clean representative view.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show target unit 5 from unit 2 through the marker-10 connection, with base markers 12, 24, and 25 fixed according to the floor plan. Include unit-2 marker 19 only where supported by the broad view. - camera_framing_directive: Use broad 90-degree coverage from camera unit 2 at [4,3] toward unit 5 at [6,8]. Establish marker 24 as the principal look-at anchor while retaining marker 10 and enough unit-5 context for markers 12 and 25 and for the close crop in S14_Shot4. - subject_position_directive: S14_Shot3 commits no subject, so keep the broad background free of invented subjects. For S14_Shot4, place the single committed subject in a tight three-quarter view on the right, with the marker-12 area remaining softly legible on the left. - state_cue_directive: No committed state cue beyond clean residential space applies. Keep base markers 2, 5, 10, 12, 19, 24, and 25 in their persistent clean state and refrain from inventing additional cues. - negative_continuity_directive: Do not import the fixed furniture arrangement of units 1 and 3 from L05B02 into unit 5. Exclude overlay markers 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, and 39, and do not add unlisted state cues or spaces beyond targets 2 and 5. 2026년 대한민국 서해안권 도시의 옥상 주거 공간 안에 있는 작고 소박한 딸 방을 촬영한 실제 카메라 다큐멘터리 풍 사진. 딸 방 출입문 바로 안쪽 가까운 위치에서 약 1.6미터의 서 있는 사람 눈높이로, 풀프레임 미러리스 카메라와 30밀리미터 광각 렌즈를 사용해 방 안을 대각선으로 바라본다. 시선은 방 안쪽의 침대와 커튼이 달린 현대식 새시 창문을 향하며, 열린 출입문 가장자리 너머로 인접 공간의 깨끗한 식탁 일부가 자연스럽게 보인다. 침대는 사람이 방금 정리한 수준을 넘어 비정상적으로 반듯하고 흐트러짐이 없으며, 실제 섬유 조직이 보이는 평범한 침구에는 주름, 먼지, 얼룩이 거의 없다. 바닥은 작은 먼지나 머리카락, 끌린 자국조차 없이 깨끗하고, 벽도 닦아 낸 자국이나 변색 경계 없이 지나치게 말끔하다. 커튼은 실제 직물의 무게와 잔주름을 지니지만 창 주변과 커튼 안쪽의 오목한 공간에는 물건, 얼룩, 잔해가 전혀 없어 텅 빈 상태가 강조된다. 이전에 존재했을 법한 피, 신체, 붉은 원형 상징, 문자, 의식 흔적, 파손, 흩어진 물건은 현재 공간에 단 하나도 남아 있지 않으며, 지워진 자국이나 청소 흔적조차 보이지 않는다. 현대 한국의 소규모 옥상방에 어울리는 실용적인 마감, 평범한 도장 벽, 합성 바닥재, 금속과 플라스틱이 섞인 새시 창호를 사실적으로 표현한다. 밤의 실내로, 천장 생활 조명의 낮고 균일한 빛과 커튼 틈으로 스며드는 희미한 도시 야간광이 섞이며 과도한 장식 없이 차갑고 불편할 만큼 정돈된 분위기를 만든다. 실제 벽 도장의 미세한 요철, 바닥재의 약한 반사, 금속 창틀의 사용감, 커튼의 직물 짜임, 침구의 자연스러운 재질을 정확히 담고, 생활 공간 특유의 미세한 마모는 남기되 최근의 사건 흔적은 전혀 남기지 않는다. 자연스러운 원근과 깊이감, 현실적인 노출과 피사계 심도, 과장 없는 색, 후처리 없는 현장 기록 사진. 깨끗한 광고 사진이나 인테리어 화보가 아니라 실제 장소를 사실대로 기록한 무심한 사진이며, 컴퓨터 그래픽이나 삽화가 아니다. 하향식 시점, 평면도, 건축 도식은 금지한다. 사람과 얼굴은 등장하지 않는다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 핏자국이나 붉은 표식 없이 지나치게 깨끗하게 정돈된 침대와 벽면의 정경. LOCATION (lock): A small rooftop apartment interior with an entrance, living and dining area, and a meticulously arranged bedroom containing a bed, curtain, backpack, and doll. Every surface appears unusually clean and undisturbed. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The room is now unnaturally clean: the blood, red wall circle, and Minsuk’s corpse have all vanished, ending their prior continuity. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 핏자국이나 붉은 표식 없이 지나치게 깨끗하게 정돈된 침대와 벽면의 정경. LOCATION (lock): A small rooftop apartment interior with an entrance, living and dining area, and a meticulously arranged bedroom containing a bed, curtain, backpack, and doll. Every surface appears unusually clean and undisturbed. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The room is now unnaturally clean: the blood, red wall circle, and Minsuk’s corpse have all vanished, ending their prior continuity. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from the entrance at standing eye level in a locked-off, frontal wide composition. Use restrained wide-angle perspective and deep focus, arranging the room’s existing elements in clean, rigid layers while giving the bed and wall strong geometric prominence. Flat, cool interior illumination with minimal shadow makes every surface clinically legible and turns the excessive order into the source of unease. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 핏자국이나 붉은 표식 없이 지나치게 깨끗하게 정돈된 침대와 벽면의 정경. LOCATION (lock): A small rooftop apartment interior with an entrance, living and dining area, and a meticulously arranged bedroom containing a bed, curtain, backpack, and doll. Every surface appears unusually clean and undisturbed. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The room is now unnaturally clean: the blood, red wall circle, and Minsuk’s corpse have all vanished, ending their prior continuity. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Place the camera low and close beside the bed, looking obliquely across its immaculate surface toward the wall with a compressed, intimate lens feel. Let the foreground bedding occupy much of the frame while the wall and remaining established objects stack tightly behind it in controlled depth. Soft light raking from one side reveals minute texture without disturbing the pristine appearance, creating tension through stillness and negative space. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.









STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 1 - camera_cell: [4, 3] - look_at_unit: 12 - look_at_cell: [2, 8] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use broad coverage from unit 1 toward unit 12 and opening marker 13 so the lower-left subject placement and upper-right background target required by S17_Shot2 can coexist.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show unit 1 with the view directed toward unit 12 and opening marker 13, while retaining only the required visible structural context from base markers 9, 10, and 11 within the wide cone. - camera_framing_directive: Frame from camera unit 1 at cell [4,3], looking toward unit 12 through look-at cell [2,8], with a wide 90-degree field of view. Preserve broad environmental coverage, a lower-frame lateral support line, and sufficient upper-background area for opening marker 13. - subject_position_directive: Place the committed subject from S17_Shot2 in profile in the lower-left midground, fully visible at medium environmental distance and supported by the lateral lower-frame structure; maintain its gaze line toward the upper-right background cue. - state_cue_directive: Carry the committed transient cues represented by markers 17 and 18, with marker 18 providing the contained brightness specified by S17_Shot2 against subdued dawn exposure. Do not introduce any unlisted state cue. - negative_continuity_directive: Exclude ignored overlay markers 14, 15, and 16. Do not add units or openings outside the selected wide view, and do not invent additional scenario-specific elements beyond markers 1, 9, 10, 11, 12, 13, 17, and 18. 2026년 현대 대한민국 서해안권의 오래된 저층 주택가, 조용한 새벽의 낡은 마당 담장과 그 너머 건물 전면, 옥상 위 작은 옥탑방을 담은 실제 카메라로 촬영한 다큐멘터리 풍 사진. 카메라는 동쪽 경계 담장 상단 가까운 약 1.3미터의 낮은 눈높이에 놓고, 마당을 가로질러 건물 전면을 바라보면서 시선을 위쪽 옥탑방 창문까지 올린다. 풀프레임 미러리스 카메라와 50밀리미터 표준 렌즈로 촬영한 자연스러운 원근감이며, 내려다보는 평면도 시점이나 건축 도식이 아니다. 프레임 앞쪽에는 빗물과 염분에 오래 노출되어 얼룩지고 미세하게 갈라진 시멘트 담장이 가로로 지나가며, 담장 윗선에 검은 고양이 한 마리가 조용히 앉아 불 켜진 옥탑방 창문을 올려다본다. 고양이는 과장되지 않은 실제 체형과 털 결을 지니며 새벽 역광 속 단정한 검은 실루엣으로 보인다. 사람, 얼굴, 실내 인영은 전혀 없다. 담장 너머 좁은 마당에는 오래된 콘크리트 바닥의 물때와 보수 흔적, 벽가의 소박한 화분과 생활 잡동사니가 자연스럽게 남아 있다. 건물은 실제 한국 저층 주거에서 흔한 붉은 벽돌과 부분적으로 덧댄 석재 타일, 낡은 회반죽 마감이 섞인 생활형 입면이다. 옥상 바닥에는 오래되어 바랜 녹색 우레탄 방수 도장과 덧칠 자국, 빗물 고임 흔적이 보인다. 옥탑방은 작고 실용적인 벽돌 또는 회반죽 외벽과 알루미늄 새시 창을 갖추고 있으며, 오직 그 창문 하나에서만 따뜻한 황색 실내등이 새어 나온다. 창유리에는 약한 반사와 생활 먼지가 있고 내부의 사람이나 얼굴은 보이지 않는다. 창 주변에는 현실적인 방범창, 에어컨 실외기와 노출 배관, 외벽 가스 배관과 계량기, 작은 물탱크, 빨랫줄과 마른 빨래가 층층이 배치되어 실제 거주 흔적을 만든다. 배경에는 비슷한 높이의 낡은 벽돌·타일 마감 주택들이 좁은 골목을 따라 밀집하고, 전신주와 느슨하게 늘어진 전선, 구석에 주차된 평범한 생활 차량이 부분적으로 보인다. 대상 건물은 고립된 콘크리트 요새가 아니라 주변 주거와 자연스럽게 이어진 실제 동네의 일부여야 한다. 해안 도시 특유의 습기와 염분으로 금속에는 옅은 녹과 변색이 있고, 콘크리트와 벽돌에는 빗물 자국과 검은 습기 얼룩이 남아 있다. 동트기 직전의 차갑고 흐린 청회색 자연광, 낮은 밝기의 고요한 마당, 따뜻한 옥탑방 창문과 차가운 새벽 외부의 절제된 대비. 담장 윗선과 검은 고양이, 외따로 불 켜진 창문이 시선의 중심이 되며 과장된 초현실 현상이나 임의의 상징은 없다. 경찰, 경찰차, 경광등, 수사 인력, 긴급 출동 흔적은 모두 제외한다. 실제 콘크리트의 거친 입자, 금속의 녹과 산화, 창유리 반사, 직물의 짜임, 벽돌 줄눈과 생활 오염을 정확히 표현한다. 자연스러운 심도와 사실적인 노출, 과도한 보정 없이 실제 장소를 기록한 담담한 사진이며 깨끗한 광고 사진, 삽화, 컴퓨터 그래픽, 건축 시각화처럼 보이지 않는다. 16:9 가로 비율, 실제 카메라 촬영본 One attached image is a PHOTOREAL RENDER of this SAME place — the same physical location, possibly seen from a different angle or at a different moment. Treat it as the PLACE IDENTITY reference. Keep this render consistent with it: the same spatial layout and architecture, the same surface materials and colors, and the same permanently installed fixtures, furniture and signage. Signage follows the place's nature: a commercial or public facility keeps its signage present and legible; a residential or private place has none unless the prompt says so. Reproduce any signage visible in the reference EXACTLY — same lettering, same design, same position; never invent different sign text from render to render. Camera angle, framing, lighting, time of day and weather follow THIS prompt — do NOT copy the reference's composition or mood; only the place's physical identity carries over. One attached image is a PHOTOREAL RENDER of the SAME building/site this scene belongs to — it may show the outside while this scene is inside, or another part of the same place. Treat it as the BUILDING IDENTITY reference. Keep this render consistent with it: the same era, age and state of repair, the same palette and material quality, the same window and door frame styles, and anything visible through openings (windows, doorways, passages) must belong to that same building and its surroundings. Signage follows the place's nature: a commercial or public facility keeps its signage present and legible; a residential or private place has none unless the prompt says so. Reproduce any signage visible in the reference EXACTLY — same lettering, same design, same position; never invent different sign text from render to render. Lighting and time of day follow THIS prompt. Do NOT copy the reference's composition, framing or camera angle; only the building's physical identity carries over. The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the warm yellow light emitting from the rooftop door, leaving only the window illuminated from within. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dawn, rooftop apartment light visible. SHOT TEXT (authoritative, Korean): 낡은 담장 위에 네 발을 딛고 서서 불 켜진 옥탑방 창문을 빤히 주시하는 검은 고양이의 측면 전신. LOCATION (lock): The rooftop of an old residential building with a small rooftop dwelling and a boundary wall crossed by a cat. The dwelling's interior light is visible from outside. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains lit, while its interior retains the unnaturally clean state left after the corpse and evidence vanished. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dawn, rooftop apartment light visible. SHOT TEXT (authoritative, Korean): 낡은 담장 위에 네 발을 딛고 서서 불 켜진 옥탑방 창문을 빤히 주시하는 검은 고양이의 측면 전신. LOCATION (lock): The rooftop of an old residential building with a small rooftop dwelling and a boundary wall crossed by a cat. The dwelling's interior light is visible from outside. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains lit, while its interior retains the unnaturally clean state left after the corpse and evidence vanished. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from the cat’s height in a restrained side-on medium-long view, preserving the complete profile and all four paws with clean separation against the surroundings. Use a gently compressed perspective so the illuminated rooftop-room window sits clearly along the cat’s unwavering sightline; keep the cat sharply resolved while allowing the room and rooftop depth to fall just slightly softer. Let the dawn exterior remain subdued against the contained interior glow, creating quiet, watchful tension. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dawn, rooftop apartment light visible. SHOT TEXT (authoritative, Korean): 낡은 담장 위에 네 발을 딛고 서서 불 켜진 옥탑방 창문을 빤히 주시하는 검은 고양이의 측면 전신. LOCATION (lock): The rooftop of an old residential building with a small rooftop dwelling and a boundary wall crossed by a cat. The dwelling's interior light is visible from outside. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. STRUCTURE LOOK AUTHORITY: the attached STRUCTURE LOOK photograph is the identity of the fixed structure at this location — wherever that structure appears in the frame, its shape, proportions, openings, materials and colors are LOCKED to it. The LOCATION PHOTOGRAPH remains the authority for this shot's sub-space, surroundings, time of day and lighting. If the two conflict on the structure itself, the STRUCTURE LOOK photo wins; for everything else, the LOCATION PHOTOGRAPH wins. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The rooftop room remains lit, while its interior retains the unnaturally clean state left after the corpse and evidence vanished. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a wider, low-positioned environmental composition, letting the old boundary wall run prominently through the frame as a strong directional line toward the rooftop dwelling. Hold both the cat’s full lateral stance and the illuminated window in clear spatial relation with deeper focus, emphasizing the exposed rooftop geometry and the still distance between watcher and destination. Balance the cool dawn ambience with the window’s warmer interior light without turning either into an exaggerated effect. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the rooftop dwelling's exterior to match the STRUCTURE LOOK photo, replacing the large barred window and metal door with the green door, small white window, and concrete walls. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows the SAME physical room as this background, from a different camera angle or framing. Inherit the exact architecture, floor, walls, windows, fixed furniture and lighting of that room — this is literally the same space, only the viewpoint changes. REFERENCE PLAN: mode='same_physical_space_view' - selected_refs[0]: ref_bg_id='L05B02' physical_space_id='ps_shared_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [4, 3] - look_at_unit: 6 - look_at_cell: [7, 5] - lens_enum: 'normal' - fov_deg: 50 - framing_notes: 'Use neutral coverage from unit 2 toward unit 6, with the listed look-at cell [7,5] anchoring base marker 17 and allowing shot-specific crops around markers 11, 17, 18, and 19.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Frame target unit 6 from camera unit 2, retaining the unit-2 connection and base markers 11, 17, 18, and 19 where each consuming shot requires them. The new view must keep marker 19 consistent with L05B02 while establishing the fixed unit-6 marker positions from the floor plan. - camera_framing_directive: Use neutral 50-degree coverage from camera unit 2 at [4,3] toward unit 6 at [7,5]. Preserve the unit-2-to-unit-6 axis for the medium mirror-mediated composition in S18_Shot8, while allowing S18_Shot10 to crop tightly to its committed surface and marker-19 context. - subject_position_directive: For S18_Shot8, reserve the lower-left foreground for the committed over-shoulder subject while marker 32 remains sharply legible near middle-right in the mediated view. For S18_Shot10, use only the committed pictured subject content within the close surface and avoid adding a physical subject to the surrounding background. - state_cue_directive: Apply transient markers 32 and 33 only in the shot-specific mediated or content surfaces committed by S18_Shot8 and S18_Shot10. Keep all other visible structure in its persistent state and add no unlisted cues. - negative_continuity_directive: Maintain the L05B02 position of base marker 19 and the floor-plan positions of markers 11, 17, and 18. Exclude overlay markers 27, 28, 29, 30, 31, 34, 35, 36, 37, 38, and 39, and do not pull units outside 2 and 6 into the neutral view. 2026년 대한민국 서해안권 도시 또는 고립된 섬의 오래된 저층 옥상 주거에 마련된 작고 생활감 있는 실내. 욕실 문 가까이에 카메라를 두고 약 1.6m의 서 있는 사람 눈높이에서 35mm급 적당한 광각 렌즈로 바라본다. 주 시선은 문 안쪽의 작은 세면대, 수도꼭지, 거울과 바닥의 샤워 배수구를 향하고, 열린 출입구와 공간의 깊이를 따라 거실의 소박한 식탁, 의자와 액자 사진이 보조 시선축에 자연스럽게 걸리게 한다. 평면도처럼 위에서 내려다보지 말고 실제 좁은 주택 내부에서 촬영한 원근과 높이를 유지한다. 현대 한국의 소형 옥상 주거에서 흔한 실용적 마감: 습기에 조금 누렇게 변색된 밝은 타일 욕실 벽, 오래 사용한 실리콘 코킹과 옅은 물때, 스테인리스 수전의 미세한 얼룩, 플라스틱 배수구 덮개, 문틀의 생활 흠집, 거실의 장판 바닥, 저렴한 합판 또는 멜라민 식탁, 알루미늄 새시 창문. 해안의 습기와 염분 때문에 금속 모서리에 아주 약한 부식과 사용 흔적이 있고, 공간은 정돈되어 있으나 새집이나 광고용 인테리어처럼 완벽하게 깨끗하지 않다. 창으로 들어오는 흐린 낮빛과 평범한 천장등의 약한 보조광이 섞이며, 낮은 중간 밝기와 절제된 회색·베이지색 해안 중성색이 중심이다. 이 배경은 동일한 구조에서 발생하는 두 개의 별도 순간을 지원한다. 첫 순간에는 욕실 벽 또는 거울 반사면 내부에만 손이나 붓으로 한 번 그린 듯 두께가 고르지 않은 짙은 붉은 원이 잠시 나타난다. 기하학적으로 완벽한 디지털 원이 아니며 문자, 룬, 장식, 복합 마법진, 과도한 빛을 동반하지 않는다. 물리적으로 굳은 페인트 자국이 아니라 곧 사라질 관찰자 중심의 지각 현상처럼 보여야 하며, 거울 밖 공간에는 어떤 형상도 추가하지 않는다. 두 번째 순간에는 거실 식탁 주변의 액자 사진 인화면 안에서만 얼굴 자리로 추정되는 부분이 습기와 열로 사진 유제가 녹아 번진 것처럼 아래로 흐르며 식별 불가능해진다. 사람이나 알아볼 수 있는 얼굴을 묘사하지 말고, 사진 속 변형은 액자 경계 밖으로 나오지 않는다. 두 이상 현상은 한 프레임에 동시에 나타나거나 공간에 영구적으로 남지 않는 서로 다른 일시적 상태로 취급한다. 사람, 얼굴, 시신, 피는 전혀 없다. 실제 콘크리트와 타일, 금속의 미세한 녹과 물때, 직물의 짜임, 목재와 합판의 결, 장판의 눌림과 일상적인 얼룩을 정확하게 표현한다. 실제 DSLR 또는 미러리스 카메라로 촬영한 다큐멘터리 풍 사진, 실제 장소 참고 사진처럼 사실적이고 담담한 기록 사진, 자연스러운 심도와 광학적 원근, 과도한 후보정 없음. 깨끗한 스톡 사진, 삽화, CGI, 3D 렌더, 건축 시각화, 평면도, 도식이 아니다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Relocate the window from the far wall to the left wall, positioned above the TV, to match the reference layout. - Restore the kitchen counter, sink, and stove to the far wall of the living room space. - Remove the framed photograph from the living room wall so that only the red circle anomaly remains in the frame. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 거실 식탁 위에 놓인 사진 액자 속 환하게 웃는 민숙의 얼굴 이미지가 찰흙처럼 기괴하게 일그러져 흘러내리는 찰나의 클로즈업. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues carrying the doll-adorned backpack and her phone. The framed photograph remains on the table as Minsuk’s pictured face briefly distorts and melts. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 거실 식탁 위에 놓인 사진 액자 속 환하게 웃는 민숙의 얼굴 이미지가 찰흙처럼 기괴하게 일그러져 흘러내리는 찰나의 클로즈업. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues carrying the doll-adorned backpack and her phone. The framed photograph remains on the table as Minsuk’s pictured face briefly distorts and melts. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph it as a locked, nearly straight-on extreme close-up, with the framed image filling almost the entire composition and the table reduced to a narrow grounding edge. Keep the frame geometry rigid and controlled around the grotesquely yielding face, using crisp focus across the photograph and soft, neutral early-morning illumination to make the impossible change feel like a practical effect captured in camera. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): early morning, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 거실 식탁 위에 놓인 사진 액자 속 환하게 웃는 민숙의 얼굴 이미지가 찰흙처럼 기괴하게 일그러져 흘러내리는 찰나의 클로즈업. LOCATION (lock): A compact rooftop apartment containing a main bedroom, a separate bedroom with a curtained window, a bathroom with a mirror, and a living-dining area displaying a family photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues carrying the doll-adorned backpack and her phone. The framed photograph remains on the table as Minsuk’s pictured face briefly distorts and melts. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot from table height at a close oblique angle, letting the picture frame cut diagonally through the composition while its near edge and the melting facial image occupy distinct depth planes. Use very shallow focus centered on the distorted face, with restrained early-morning side light grazing the frame and printed surface so the deformation feels tactile, immediate, and physically present. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [7, 5] - look_at_unit: 1 - look_at_cell: [3, 3] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use the listed unit-2 camera cell and look toward unit 1 with broad coverage suitable for the committed medium staging and the target-unit set [1, 2, 3].' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show unit 2 in relation to unit 1 from the selected wide view, preserve fixed markers 4, 5, 6, and 7 in their committed positions, and include unit 3 plus fixed markers 8 and 9 and openings 10 and 11 only where they fall inside the broad view cone. - camera_framing_directive: Frame from camera unit 2 at [7,5] toward look-at unit 1 at [3,6] with a wide 90-degree field of view, giving broad coverage around the committed midground subject position and the surrounding fixed markers. - subject_position_directive: For S21_Shot5, place the committed subject at seated eye level in the midground, slightly right of center and perched forward, while keeping the other committed seating cues visibly unoccupied and separated; introduce no additional subjects. - state_cue_directive: No committed state cue beyond clean residential space applies because clean_background_expected is true and no transient markers are listed; refrain from inventing additional cues and keep overlay markers 12 and 13 absent. - negative_continuity_directive: Exclude ignored overlay markers 12 and 13, do not add unlisted scenario-specific elements, and do not depict units or openings outside the chosen view cone; treat the geometry visibility lists as supersets rather than mandatory inclusions. 2026년 현대 대한민국 서해안권 도시의 공공기관 내부에 있는 형사과 사무실 좌석 구역. 실제 미러리스 또는 DSLR 카메라로 촬영한 다큐멘터리 풍 사진이며, 출입문 바로 안쪽의 서 있는 사람 눈높이 약 1.6m에서 28mm 광각 렌즈로 촬영한다. 문턱과 소규모 민원인 대기 좌석 구역을 전경에 두고, 그 너머의 공용 업무 구역에 여러 개의 실용적인 책상과 낮은 파티션, 검은색 사무용 의자, 데스크톱 모니터, 키보드, 마우스, 유선 전화기, 문서 트레이가 이어지는 넓은 설정 구도. 프레임 한쪽에는 철제 캐비닛과 개방형 선반, 공용 프린터가 놓인 서비스·수납 구역이 자연스럽게 보인다. 형사들이 낮 시간 회의 호출을 받고 급히 빠져나간 직후처럼 모든 좌석은 비어 있고, 의자 몇 개가 책상에서 약간 뒤로 밀려 있으며, 평범한 무지 머그잔과 닫힌 서류철 정도만 남아 있다. 사건 관련 사진, 수사 지도, 이름, 개인정보, 읽을 수 있는 문서 내용은 전혀 보이지 않으며 모든 모니터는 꺼져 있거나 식별 가능한 정보가 없는 빈 대기 상태다. 사람, 얼굴, 신체는 없다. 현대 한국 공공기관 사무실에서 흔한 흰색 도장 벽, 회색 계열 바닥 타일, 흠집과 손때가 남은 합판 또는 금속 사무 가구, 약간 누렇게 사용감이 밴 낮은 파티션 패브릭, 실제 플라스틱과 분체도장 금속의 질감을 정확히 표현한다. 천장은 흡음 텍스와 매립형 직사각 LED 조명으로 구성되고, 창문 블라인드 사이로 흐린 해안 도시의 낮 자연광이 들어와 실내 조명과 현실적으로 섞인다. 벽시계, 휴지통, 간단한 옷걸이 등 일상적인 업무 흔적을 절제해 배치한다. 지나치게 정돈된 홍보용 사무실이나 깨끗한 스톡 사진이 아니라, 모서리의 미세한 먼지, 바퀴 자국, 책상 표면의 잔흠집, 케이블 정리의 불균일함이 남은 실제 사용 공간이다. 자연스러운 화이트 밸런스와 사실적인 중간 밝기, 현실적인 그림자, 정확한 재료 질감, 과장되지 않은 자연스러운 심도, 무보정에 가까운 현장 기록 사진. CGI, 일러스트, 건축 시각화, 평면도, 도식, 하향 시점이 아닌 실제 장소 참고 사진. 16:9 가로 비율, 실제 카메라 촬영본. This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Change the screens of all three illuminated desktop monitors to be completely black and turned off. - Remove the framed notice board with documents from the far left wall and the printed paper pinned to the right partition. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 켜진 컴퓨터 모니터 화면 속 해상 지도 위 좌표와 오프라인 상태 메시지가 뚜렷한 정지 구도. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The monitor continues displaying Minsuk’s last offshore coordinates and an offline status. Su-ri-yeong still has her backpack and phone, with the desk photographs remaining nearby. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 켜진 컴퓨터 모니터 화면 속 해상 지도 위 좌표와 오프라인 상태 메시지가 뚜렷한 정지 구도. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The monitor continues displaying Minsuk’s last offshore coordinates and an offline status. Su-ri-yeong still has her backpack and phone, with the desk photographs remaining nearby. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): A locked-off, tight frontal insert centered on the illuminated monitor, with minimal perspective distortion and a precise crop that makes the maritime map, coordinates, and offline status the unmistakable visual focus. Keep the screen plane crisp and evenly resolved while the surrounding workstation falls softly out of focus, creating a clinical, ominous stillness. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): 켜진 컴퓨터 모니터 화면 속 해상 지도 위 좌표와 오프라인 상태 메시지가 뚜렷한 정지 구도. LOCATION (lock): A busy police station office with clustered desks, computer monitors, paperwork, and adjoining access to a meeting area. Enlarged crime-scene photographs are spread across one investigator's desk. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The monitor continues displaying Minsuk’s last offshore coordinates and an offline status. Su-ri-yeong still has her backpack and phone, with the desk photographs remaining nearby. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from an oblique desk-height angle in a wider environmental composition, placing the active monitor prominently within the foreground workstation while the clustered office recedes in layered depth. Hold enough focus on the screen for its critical display to remain clear, while the nearby desk photographs and softly rendered police-office background frame the information as part of an ongoing investigation; use restrained naturalistic contrast and a static, observational mood. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the backpack from the desk completely. - Remove all written text from the monitor screen, representing the offline status message using only a graphical symbol or warning icon. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows a related part of the same dwelling, not the current room. Inherit the overall material and lighting identity only; the new space is its own architectural room and must read as the same home. REFERENCE PLAN: mode='related_style_new_space' - selected_refs[0]: ref_bg_id='L05B02' physical_space_id='ps_shared_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [4, 3] - look_at_unit: 5 - look_at_cell: [6, 8] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use broad coverage from unit 2 toward unit 5, looking at listed cell [6,8] associated with base marker 24 so marker 10 and the unit-5 fixed markers can establish a clean representative view.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show target unit 5 from unit 2 through the marker-10 connection, with base markers 12, 24, and 25 fixed according to the floor plan. Include unit-2 marker 19 only where supported by the broad view. - camera_framing_directive: Use broad 90-degree coverage from camera unit 2 at [4,3] toward unit 5 at [6,8]. Establish marker 24 as the principal look-at anchor while retaining marker 10 and enough unit-5 context for markers 12 and 25 and for the close crop in S14_Shot4. - subject_position_directive: S14_Shot3 commits no subject, so keep the broad background free of invented subjects. For S14_Shot4, place the single committed subject in a tight three-quarter view on the right, with the marker-12 area remaining softly legible on the left. - state_cue_directive: No committed state cue beyond clean residential space applies. Keep base markers 2, 5, 10, 12, 19, 24, and 25 in their persistent clean state and refrain from inventing additional cues. - negative_continuity_directive: Do not import the fixed furniture arrangement of units 1 and 3 from L05B02 into unit 5. Exclude overlay markers 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, and 39, and do not add unlisted state cues or spaces beyond targets 2 and 5. 2026년 대한민국 서해안권 도시의 옥상 주거 공간 안에 있는 작고 소박한 딸 방을 촬영한 실제 카메라 다큐멘터리 풍 사진. 딸 방 출입문 바로 안쪽 가까운 위치에서 약 1.6미터의 서 있는 사람 눈높이로, 풀프레임 미러리스 카메라와 30밀리미터 광각 렌즈를 사용해 방 안을 대각선으로 바라본다. 시선은 방 안쪽의 침대와 커튼이 달린 현대식 새시 창문을 향하며, 열린 출입문 가장자리 너머로 인접 공간의 깨끗한 식탁 일부가 자연스럽게 보인다. 침대는 사람이 방금 정리한 수준을 넘어 비정상적으로 반듯하고 흐트러짐이 없으며, 실제 섬유 조직이 보이는 평범한 침구에는 주름, 먼지, 얼룩이 거의 없다. 바닥은 작은 먼지나 머리카락, 끌린 자국조차 없이 깨끗하고, 벽도 닦아 낸 자국이나 변색 경계 없이 지나치게 말끔하다. 커튼은 실제 직물의 무게와 잔주름을 지니지만 창 주변과 커튼 안쪽의 오목한 공간에는 물건, 얼룩, 잔해가 전혀 없어 텅 빈 상태가 강조된다. 이전에 존재했을 법한 피, 신체, 붉은 원형 상징, 문자, 의식 흔적, 파손, 흩어진 물건은 현재 공간에 단 하나도 남아 있지 않으며, 지워진 자국이나 청소 흔적조차 보이지 않는다. 현대 한국의 소규모 옥상방에 어울리는 실용적인 마감, 평범한 도장 벽, 합성 바닥재, 금속과 플라스틱이 섞인 새시 창호를 사실적으로 표현한다. 밤의 실내로, 천장 생활 조명의 낮고 균일한 빛과 커튼 틈으로 스며드는 희미한 도시 야간광이 섞이며 과도한 장식 없이 차갑고 불편할 만큼 정돈된 분위기를 만든다. 실제 벽 도장의 미세한 요철, 바닥재의 약한 반사, 금속 창틀의 사용감, 커튼의 직물 짜임, 침구의 자연스러운 재질을 정확히 담고, 생활 공간 특유의 미세한 마모는 남기되 최근의 사건 흔적은 전혀 남기지 않는다. 자연스러운 원근과 깊이감, 현실적인 노출과 피사계 심도, 과장 없는 색, 후처리 없는 현장 기록 사진. 깨끗한 광고 사진이나 인테리어 화보가 아니라 실제 장소를 사실대로 기록한 무심한 사진이며, 컴퓨터 그래픽이나 삽화가 아니다. 하향식 시점, 평면도, 건축 도식은 금지한다. 사람과 얼굴은 등장하지 않는다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 열린 방문 너머, 벽면에 거칠게 그려진 붉은색 원과 그 중앙에 꽂힌 피 묻은 낡은 사진이 보이는 구도. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The room remains ransacked, with footprints, an open window, and overturned chairs. A bloodstained old photograph is pinned at the center of the red wall circle, while Su-ri-yeong still has her backpack, maps, note, and phone. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 열린 방문 너머, 벽면에 거칠게 그려진 붉은색 원과 그 중앙에 꽂힌 피 묻은 낡은 사진이 보이는 구도. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The room remains ransacked, with footprints, an open window, and overturned chairs. A bloodstained old photograph is pinned at the center of the red wall circle, while Su-ri-yeong still has her backpack, maps, note, and phone. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from a low, moderately wide viewpoint in the living room, using the open doorway as a strong frame within the frame. Let the ransacked foreground occupy substantial space while clear depth lines lead into the bedroom, where the marked wall and its central photograph remain the precise visual destination. Cool dusk light from the open window grazes the disorder and falls away toward the bedroom, creating tense, natural depth without obscuring the key detail. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 열린 방문 너머, 벽면에 거칠게 그려진 붉은색 원과 그 중앙에 꽂힌 피 묻은 낡은 사진이 보이는 구도. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The room remains ransacked, with footprints, an open window, and overturned chairs. A bloodstained old photograph is pinned at the center of the red wall circle, while Su-ri-yeong still has her backpack, maps, note, and phone. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a tight, compressed view through the open doorway, with the near door edge occupying one side as a soft, partial foreground obstruction. Flatten the depth so the rough wall mark dominates the composition and the photograph at its center becomes the sharpest, most immediate detail; allow only restrained peripheral evidence of the surrounding disorder. Keep the dusk interior subdued and directional, emphasizing surface texture, dried staining, and the unsettling stillness of the room. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Open the closed window on the right side of the room. - Add the open solid wooden door to the doorframe and remove the raised wooden sill from the floor threshold. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. The supplied reference image shows a related part of the same dwelling, not the current room. Inherit the overall material and lighting identity only; the new space is its own architectural room and must read as the same home. REFERENCE PLAN: mode='related_style_new_space' - selected_refs[0]: ref_bg_id='L05B02' physical_space_id='ps_shared_1_2_3' CAMERA DECISION (exact, from validated plan): - camera_unit: 2 - camera_cell: [4, 3] - look_at_unit: 5 - look_at_cell: [6, 8] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Use broad coverage from unit 2 toward unit 5, looking at listed cell [6,8] associated with base marker 24 so marker 10 and the unit-5 fixed markers can establish a clean representative view.' RENDER GUIDANCE (from validated plan): - visible_space_directive: Show target unit 5 from unit 2 through the marker-10 connection, with base markers 12, 24, and 25 fixed according to the floor plan. Include unit-2 marker 19 only where supported by the broad view. - camera_framing_directive: Use broad 90-degree coverage from camera unit 2 at [4,3] toward unit 5 at [6,8]. Establish marker 24 as the principal look-at anchor while retaining marker 10 and enough unit-5 context for markers 12 and 25 and for the close crop in S14_Shot4. - subject_position_directive: S14_Shot3 commits no subject, so keep the broad background free of invented subjects. For S14_Shot4, place the single committed subject in a tight three-quarter view on the right, with the marker-12 area remaining softly legible on the left. - state_cue_directive: No committed state cue beyond clean residential space applies. Keep base markers 2, 5, 10, 12, 19, 24, and 25 in their persistent clean state and refrain from inventing additional cues. - negative_continuity_directive: Do not import the fixed furniture arrangement of units 1 and 3 from L05B02 into unit 5. Exclude overlay markers 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, and 39, and do not add unlisted state cues or spaces beyond targets 2 and 5. 2026년 대한민국 서해안권 도시의 옥상 주거 공간 안에 있는 작고 소박한 딸 방을 촬영한 실제 카메라 다큐멘터리 풍 사진. 딸 방 출입문 바로 안쪽 가까운 위치에서 약 1.6미터의 서 있는 사람 눈높이로, 풀프레임 미러리스 카메라와 30밀리미터 광각 렌즈를 사용해 방 안을 대각선으로 바라본다. 시선은 방 안쪽의 침대와 커튼이 달린 현대식 새시 창문을 향하며, 열린 출입문 가장자리 너머로 인접 공간의 깨끗한 식탁 일부가 자연스럽게 보인다. 침대는 사람이 방금 정리한 수준을 넘어 비정상적으로 반듯하고 흐트러짐이 없으며, 실제 섬유 조직이 보이는 평범한 침구에는 주름, 먼지, 얼룩이 거의 없다. 바닥은 작은 먼지나 머리카락, 끌린 자국조차 없이 깨끗하고, 벽도 닦아 낸 자국이나 변색 경계 없이 지나치게 말끔하다. 커튼은 실제 직물의 무게와 잔주름을 지니지만 창 주변과 커튼 안쪽의 오목한 공간에는 물건, 얼룩, 잔해가 전혀 없어 텅 빈 상태가 강조된다. 이전에 존재했을 법한 피, 신체, 붉은 원형 상징, 문자, 의식 흔적, 파손, 흩어진 물건은 현재 공간에 단 하나도 남아 있지 않으며, 지워진 자국이나 청소 흔적조차 보이지 않는다. 현대 한국의 소규모 옥상방에 어울리는 실용적인 마감, 평범한 도장 벽, 합성 바닥재, 금속과 플라스틱이 섞인 새시 창호를 사실적으로 표현한다. 밤의 실내로, 천장 생활 조명의 낮고 균일한 빛과 커튼 틈으로 스며드는 희미한 도시 야간광이 섞이며 과도한 장식 없이 차갑고 불편할 만큼 정돈된 분위기를 만든다. 실제 벽 도장의 미세한 요철, 바닥재의 약한 반사, 금속 창틀의 사용감, 커튼의 직물 짜임, 침구의 자연스러운 재질을 정확히 담고, 생활 공간 특유의 미세한 마모는 남기되 최근의 사건 흔적은 전혀 남기지 않는다. 자연스러운 원근과 깊이감, 현실적인 노출과 피사계 심도, 과장 없는 색, 후처리 없는 현장 기록 사진. 깨끗한 광고 사진이나 인테리어 화보가 아니라 실제 장소를 사실대로 기록한 무심한 사진이며, 컴퓨터 그래픽이나 삽화가 아니다. 하향식 시점, 평면도, 건축 도식은 금지한다. 사람과 얼굴은 등장하지 않는다. 16:9 가로 비율, 실제 카메라 촬영본 This interior belongs to the same single real building/place as this location group's other spaces. Keep its construction era, age and state of repair, material quality and window/door frame styles consistent with ONE ordinary real building of the kind this prompt describes, and anything visible through its windows, doorways or passages must plausibly belong to that same building and its immediate surroundings.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 두 명의 어린 한국인 여자아이와 지붕 위 둥근 원 장식이 있는 낡은 시골 식당이 찍힌 빛바랜 사진의 클로즈업. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong has removed the bloodstained photograph from the red circle and holds it for inspection; the ransacked room and the now-empty red wall circle remain behind her. Her backpack still contains the printed maps. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 두 명의 어린 한국인 여자아이와 지붕 위 둥근 원 장식이 있는 낡은 시골 식당이 찍힌 빛바랜 사진의 클로즈업. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong has removed the bloodstained photograph from the red circle and holds it for inspection; the ransacked room and the now-empty red wall circle remain behind her. Her backpack still contains the printed maps. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the faded image nearly straight-on in an extremely tight, centered close-up, with its pictured subjects and architectural detail immediately readable. Keep the photograph’s plane largely sharp while the ransacked bedroom falls into complete, unobtrusive blur beyond it; soft dusk light from the open window reveals the faded emulsion, worn surface, and blood staining with restrained forensic clarity. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, interior with an open window. SHOT TEXT (authoritative, Korean): 두 명의 어린 한국인 여자아이와 지붕 위 둥근 원 장식이 있는 낡은 시골 식당이 찍힌 빛바랜 사진의 클로즈업. LOCATION (lock): A compact rooftop apartment ransacked throughout, with footprints, overturned dining chairs, an open living-room window, and disturbed household items. The bedroom contains a bed and a wall marked by a red circle holding a bloodstained photograph. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong has removed the bloodstained photograph from the red circle and holds it for inspection; the ransacked room and the now-empty red wall circle remain behind her. Her backpack still contains the printed maps. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use an intimate oblique close-up that looks across the photograph rather than squarely at it, creating strong near-to-far depth within the print. Let shallow focus settle on the two girls and the round roof ornament while the photograph’s edges and distant portions soften naturally; low, grazing dusk illumination from the open window catches creases, faded texture, and bloodstained areas, giving the clue a tactile and ominous presence. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove all text from the building in the photograph. - Remove the fingers visible in the bottom left corner. - Slide the window panes open in the blurred background. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
STYLE CONTRACT — ordinary, modest, lived-in residential interior. Treat the result as an actual reference photograph of a real home: everyday materials, believable wear, modest furniture in plain shapes, natural daylight or simple ceiling lighting. Strictly avoid luxury, showroom, hotel-suite, boutique-design, high-end-retail, or magazine-staging styling. No marble surfaces, no chandeliers, no designer furniture, no polished decor displays, no curated styling props, no glossy magazine finish. Use the supplied base floor plan as the only visual reference. Render a fresh photoreal interior under the modest style contract; treat the base markers as spatial guidance, not as overlay material. REFERENCE PLAN: mode='fp_seeded_anchor' - reference: base floor plan (anchor) CAMERA DECISION (exact, from validated plan): - camera_unit: 6 - camera_cell: [9, 4] - look_at_unit: 3 - look_at_cell: [4, 4] - lens_enum: 'wide' - fov_deg: 90 - framing_notes: 'Wide coverage from unit 6 toward unit 3, centered on look-at cell [4,4], supports the full-figure depth arrangement and forward movement axis committed for S28_Shot9.' RENDER GUIDANCE (from validated plan): - visible_space_directive: From unit 6 looking toward unit 3, show the floor-plan-supported forward axis through unit 1 and toward unit 3, with units 4 and 5 available at the lateral edges under the wide view. Keep openings 7 and 8 and fixed markers 9, 10, 11, and 12 in their committed floor-plan positions. - camera_framing_directive: Frame from camera unit 6 at cell [9,4] toward unit 3 through look-at cell [4,4] with a wide 90-degree field of view. Use broad coverage along the unit-6-to-unit-3 axis so the lower-center foreground, middle-center depth plane, and upper-center destination remain legible together. - subject_position_directive: For S28_Shot9, retain one committed full-body subject back to camera in the lower center, lunging forward with an extended arm, and a second back-to-camera subject in the middle-center background moving along the same axis toward unit 3. Preserve the rear spacing and wide-frame depth separation committed by the staging. - state_cue_directive: No committed state cue beyond a clean residential space applies because clean_background_expected is true and no transient markers are listed. Refrain from inventing additional state cues. - negative_continuity_directive: Exclude ignored markers 14 and 15. Do not introduce unlisted transient markers, do not alter the fixed positions of markers 7, 8, 9, 10, 11, or 12, and do not depict units outside the floor-plan-supported view cone as committed visible space. 2026년 대한민국 서해안에서 실제 운항하는 소형 연안 작업선의 외부 갑판. 선미 설비 구역 가까이에 선 카메라가 선미 작업 갑판을 따라 전방의 조타실 출입문을 바라보는 구도이며, 카메라 높이는 갑판에서 약 1.6미터인 성인 눈높이, 28밀리미터 광각 렌즈에 해당하는 자연스러운 원근감이다. 선미에서 조타실 문까지 짧고 막힘없는 이동 경로가 화면의 중심축을 이루고, 양쪽에는 난간과 선체 구조 사이로 이어지는 좁은 측면 통로가 보인다. 조타실 출입문은 급히 드나들 수 있도록 열려 있고, 내부는 저녁의 희미한 실내등과 계기판에서 새어 나오는 약한 빛만 보여 구체적인 화면 정보나 사람은 보이지 않는다. 지도와 사진은 전경의 별도 물체로 두지 않는다. 현대 한국 서해안 소형 선박의 현실적인 구조와 사용 흔적: 바닷물과 작업화로 닳아 미끄럼 방지 무늬가 부분적으로 마모된 도장 강철 갑판, 용접 자국이 남은 금속 난간, 염분 얼룩과 가벼운 녹이 밴 볼라드와 소형 윈치, 안전하게 가장자리로 정리된 굵은 밧줄, 벽면의 구명환, 낮은 방수 갑판등, 알루미늄 새시 조타실 창, 고무 패킹이 닳은 금속 출입문, 지붕 위 통신 안테나와 항해 설비를 사실적으로 표현한다. 이동 중심부에는 발을 걸 만한 장애물이 없고, 작업 장비는 양옆으로 밀려 정리되어 있다. 지나치게 새롭거나 깔끔한 관광선이 아니라 매일 쓰이는 연안 작업선다운 물때, 빗물 자국, 벗겨진 도장, 금속의 염분 부식, 고무와 밧줄의 거친 섬유 질감이 자연스럽게 축적되어 있다. 해 질 무렵의 갑작스러운 소동 상태. 서쪽 하늘의 남은 차가운 청회색 자연광이 갑판과 조타실 외벽에 낮게 퍼지고, 막 켜진 따뜻한 백색 갑판등이 문 주변과 젖은 금속 표면에 제한적으로 반사된다. 바다는 난간 너머로 어둡고 낮게 보이며, 수평선과 멀리 떨어진 항만의 희미한 생활 불빛만 배경에 남는다. 강한 폭풍이나 과장된 파도 없이 실제 서해안 저녁의 습기와 바람, 약간 흔들린 밧줄 끝과 열린 문으로 긴박함을 암시한다. 사람, 얼굴, 신체, 시체, 피, 초자연적 형상은 전혀 배치하지 않는다. 실제 미러리스 또는 디지털 일안 카메라로 촬영한 다큐멘터리 풍 사진, 실제 장소 기록 사진처럼 담담한 촬영, 자연스러운 노출과 색, 후처리 없는 현실적인 저조도 표현, 정확한 금속 녹과 도장 박리, 실제 유리 반사, 고무 패킹, 밧줄 섬유, 젖은 강철의 질감, 과장되지 않은 자연스러운 심도. 정면의 조타실 문까지 공간 관계가 명확하되 완전한 무한 초점처럼 평평하지 않게 표현한다. 깨끗한 광고용 사진, 삽화, 컴퓨터 그래픽, 건축 시각화, 평면도, 하향 시점이 아닌 실제 현장 사진. 16:9 가로 비율, 실제 카메라 촬영본 The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Add the horizontal railing crossing the lower foreground deck to connect the side rails, corresponding to marker 11. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 해질 무렵 붉은 노을빛이 비치는 바다 한가운데 소형 어선이 떠 있는 전경. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong and In-woo are aboard the same small fishing boat; her backpack, printed maps, old photograph, and phone remain aboard with her. The many circular marks already exist inside the wheelhouse. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 해질 무렵 붉은 노을빛이 비치는 바다 한가운데 소형 어선이 떠 있는 전경. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong and In-woo are aboard the same small fishing boat; her backpack, printed maps, old photograph, and phone remain aboard with her. The many circular marks already exist inside the wheelhouse. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph an extremely wide, restrained establishing view from near water level, with the open sea occupying most of the frame and the small fishing boat held modestly against the distant horizon. Use expansive depth and ample negative space to stress its isolation offshore, while the red dusk light skims across the water and gently outlines the exposed deck and enclosed wheelhouse. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 해질 무렵 붉은 노을빛이 비치는 바다 한가운데 소형 어선이 떠 있는 전경. LOCATION (lock): A small fishing boat underway on open water, with an exposed working deck and an enclosed wheelhouse. The coastline is no longer nearby, suggesting the vessel has traveled well offshore. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong and In-woo are aboard the same small fishing boat; her backpack, printed maps, old photograph, and phone remain aboard with her. The many circular marks already exist inside the wheelhouse. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a high, oblique long-lens view that makes the fishing boat the dominant subject while compressing the surrounding open water into layered bands behind it. Frame the vessel diagonally so the exposed working deck leads toward the enclosed wheelhouse, with the low red dusk illumination shaping its surfaces and reflecting softly across the sea. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the silhouettes of the people standing on the back deck of the boat. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
2026년 대한민국 서해 해상, 해 질 무렵 현대식 소형 연안 어선 한 척이 거대한 짙은 해무 띠 속으로 진입하는 순간을 포착한 실제 카메라 다큐멘터리 풍 사진. 수면 가까운 다른 선박의 안정된 갑판에서 약 1.6m 성인 눈높이로 촬영한 시점이며, 절대 항공 시점이나 탑다운 구도, 평면도, 건축 도식이 아니다. 35mm급 렌즈를 장착한 실제 DSLR 또는 미러리스 카메라로 촬영한 현장 기록 사진처럼 표현한다. 프레임 중하단에는 한국 서해 연안에서 흔히 볼 수 있는 실용적인 소형 어선의 선미와 조타실, 흰색과 청회색 도장이 군데군데 벗겨진 선체, 염분 자국과 녹슨 금속 난간, 작업용 윈치, 감긴 밧줄, 부표, 안테나, 소형 레이더, 켜지기 시작한 항해등이 보인다. 승선한 사람이나 얼굴은 전혀 보이지 않는다. 어선의 선수 방향은 화면 깊숙한 곳의 불투명한 안개 장벽을 향하고, 선체 앞부분부터 윤곽이 빠르게 흐려지며 짙은 해무에 삼켜지는 실제 광학적 소실을 보여 준다. 바다는 서해 특유의 탁한 회녹색과 납빛이 섞인 잔잔한 수면이며, 작은 파도와 어선이 남긴 낮은 항적이 현실적으로 이어진다. 수평선 부근의 낮은 황금빛 석양은 안개 뒤에서 확산되어 흐릿한 금빛 띠와 제한적인 반사광만 만들고, 주변은 청회색과 회갈색의 절제된 해안 중성색으로 가라앉아 있다. 안개는 단순한 흰 벽이 아니라 밀도 차이가 있는 습한 해무로, 가까운 곳의 물방울성 흐림과 먼 곳의 낮은 가시거리, 부드럽게 사라지는 수평선을 자연스럽게 나타낸다. 실제 금속의 산화와 염분 얼룩, 젖은 밧줄 섬유, 거친 선체 도장, 물결의 불규칙한 반사처럼 정확한 재질 질감을 담고, 장기간 조업한 배의 일상적인 마모와 때를 유지한다. 자연스러운 저조도 노출과 현실적인 피사계 심도, 과도한 후보정 없는 담담한 현장 사진. 깨끗한 광고용 스톡 사진이 아니며 CGI, 삽화, 회화, 건축 시각화가 아닌 실제 장소에서 실제 카메라로 촬영한 사진과 구별할 수 없는 결과. 16:9 가로 비율, 실제 카메라 촬영본 One attached image is a PHOTOREAL RENDER of the SAME building/site this scene belongs to — it may show the outside while this scene is inside, or another part of the same place. Treat it as the BUILDING IDENTITY reference. Keep this render consistent with it: the same era, age and state of repair, the same palette and material quality, the same window and door frame styles, and anything visible through openings (windows, doorways, passages) must belong to that same building and its surroundings. Signage follows the place's nature: a commercial or public facility keeps its signage present and legible; a residential or private place has none unless the prompt says so. Reproduce any signage visible in the reference EXACTLY — same lettering, same design, same position; never invent different sign text from render to render. Lighting and time of day follow THIS prompt. Do NOT copy the reference's composition, framing or camera angle; only the building's physical identity carries over. The LAST attached image is a TOP-DOWN INTERIOR FLOOR PLAN of the building at this location — a STRUCTURAL REFERENCE ONLY, never content to draw. It defines the building's real scale: its footprint, room count, and the placement of its doors and windows. Render the scene so the building's exterior size, number of storeys, and the scale and placement of its doors and windows stay consistent with that plan. Do NOT draw the floor plan itself, its lines, text or numbers anywhere in the image.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the tall mast and antenna structure from the roof of the wheelhouse, leaving only the small radar dome to match the reference. - Add the two illuminated caged wall lamps to the exterior rear wall of the wheelhouse, directly above the life ring and the open door. - Apply a thick fog overlay and optical blur to the furthest visible structures (the cabin and roof) so they appear to be fading into and being swallowed by the fog bank. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): sunset, golden reflection and dense fog. SHOT TEXT (authoritative, Korean): 뱃머리가 짙은 안개 속으로 반쯤 들어간 채 선수 양옆으로 흰 물보라가 고정되어 있는 소형 어선의 전경. LOCATION (lock): Open sea surrounding a small fishing boat as it approaches a dense bank of fog. The low sun casts a long golden reflection across the water before the vessel enters the mist. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The same boat continues into the dense fog with unconscious Su-ri-yeong aboard in In-woo’s custody. Her backpack, old photograph, maps, and phone remain on the vessel, and the wheelhouse circles remain in place. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): sunset, golden reflection and dense fog. SHOT TEXT (authoritative, Korean): 뱃머리가 짙은 안개 속으로 반쯤 들어간 채 선수 양옆으로 흰 물보라가 고정되어 있는 소형 어선의 전경. LOCATION (lock): Open sea surrounding a small fishing boat as it approaches a dense bank of fog. The low sun casts a long golden reflection across the water before the vessel enters the mist. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The same boat continues into the dense fog with unconscious Su-ri-yeong aboard in In-woo’s custody. Her backpack, old photograph, maps, and phone remain on the vessel, and the wheelhouse circles remain in place. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from very low near water level in a centered, head-on composition, with the hull rising forcefully above the camera and the bow’s entry into the fog as the dominant visual beat. Use a compressed lens feel so the dense mist forms an imposing wall behind the fixed white spray on both sides, while the golden reflection leads directly toward the vessel. Keep the light soft and backlit through the fog, preserving crisp spray against muted sea and mist. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): sunset, golden reflection and dense fog. SHOT TEXT (authoritative, Korean): 뱃머리가 짙은 안개 속으로 반쯤 들어간 채 선수 양옆으로 흰 물보라가 고정되어 있는 소형 어선의 전경. LOCATION (lock): Open sea surrounding a small fishing boat as it approaches a dense bank of fog. The low sun casts a long golden reflection across the water before the vessel enters the mist. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The same boat continues into the dense fog with unconscious Su-ri-yeong aboard in In-woo’s custody. Her backpack, old photograph, maps, and phone remain on the vessel, and the wheelhouse circles remain in place. NO PEOPLE IN THIS SHOT: the shot text shows only the place and its state — no living person or any body part appears in frame, unless the shot text itself explicitly says so. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a distant, elevated oblique wide view that places the vessel deeper in the frame and gives the surrounding sea and fog bank strong compositional weight. Arrange the long golden reflection as a diagonal path toward the boat, while the two white bursts beside the bow provide the sharpest visual accents as it crosses into the mist. Let atmospheric depth progressively soften the hull toward the fog, creating a restrained, ominous sense of isolation. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Move the boat forward so its front half is visibly engulfed by the dense fog. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Draw a single CAMERA-VIEW storyboard frame (16:9) of the scene staged on the attached TOP-DOWN SITE PLAN, seen from the camera position given in the STAGING GEOMETRY data below. Jurisdiction of sources — follow all three, they do not conflict: - The attached SITE PLAN is the SOT for what exists on the site and how its zones and landmarks are arranged relative to each other. - The STAGING GEOMETRY data below is the SOT for XY POSITIONS and horizontal heading ONLY: where each subject stands on that plan, where the camera stands, and which way it looks. Distances, directions and relative depths between subjects come from these coordinates. Subjects outside the camera's horizontal field of view are out of frame. - The CAMERA DIRECTION text below (when present) is the SOT for the VERTICAL angle, elevation, tilt and framing (eye-level, high angle, overhead crane, low angle, ...). If it asks for a high or overhead angle, draw that angle — the site plan being top-down does NOT mean the frame must be eye-level. STYLE — LIGHT STORYBOARD FRAME: thin uniform dark outlines on plain paper. No shading, no hatching, no texture, no facial features beyond a minimal head shape, no costume detail. Human figures are correctly proportioned full-body outlines in their canonical poses. Environment is reduced to a few placement lines (ground line, key landmark silhouettes) — just enough to read positions and depth. STAGING GEOMETRY — PLANNING DATA ONLY, NEVER RENDER IT: the lines below are normalized map coordinates on the attached site plan (x runs left→right 0..1, y runs top→bottom 0..1). Use them solely to place the camera and subjects. Do NOT draw any of this data in the image — no numbers, no coordinates, no labels, no arrows, no cones, no dots, no diagram symbols of any kind. - the camera stands at (x=0.79, y=0.31) and looks toward (x=0.57, y=0.52); subjects outside the camera's horizontal field of view are out of frame - airborne silhouetted attacker stands at (x=0.47, y=0.42) - fallen injured man stands at (x=0.68, y=0.63) CAMERA DIRECTION (vertical angle / elevation / framing SOT): After the hard cut, a waist-height side view holds a wide slice of space around 숲속 사건의 남자 피해자, with his fallen body in the lower right and 정체불명의 습격자 suspended across the upper left-to-center. The frame freezes the peak of the attacker's diagonal flight, both arms reaching toward the victim, while the wider camera distance becomes the sole strong break from the preceding close portrait. THE LOCATION: 해 질 무렵의 숲속 바닥 SHOT TEXT (authoritative, Korean): 공중에 뜬 검은 실루엣의 정체불명의 습격자가 바닥에 쓰러진 숲속 사건의 남자 피해자를 향해 양팔을 뻗은 찰나 CRITICAL — THE SITE PLAN IS A STAGING REFERENCE, NOT CONTENT: do NOT draw the plan itself, and do NOT draw any diagram elements in the frame — no circles, dots, wedges, cones, arrows, callouts, codes or any other overlay symbols. The output is a clean storyboard drawing of the scene as seen by the camera only. No text, no letters, no numbers, no captions anywhere in the image.
{
"camera": {
"look_target": {
"x": 0.575,
"y": 0.52
},
"origin": {
"x": 0.79,
"y": 0.31
}
},
"entity_placements": [
{
"slot": "E1",
"subject_en": "airborne silhouetted attacker",
"x": 0.47,
"y": 0.42
},
{
"slot": "E2",
"subject_en": "fallen injured man",
"x": 0.68,
"y": 0.63
}
],
"rationale_ko": "A1 woodland floor의 넓은 중앙 공터에 피해자를 우하단, 공중의 습격자를 좌상단에 두어 양팔을 뻗으며 대각선으로 덮치는 찰나를 구성했다. 카메라는 두 인물의 공격 축에 비스듬히 직교하는 우상단 쪽에 충분히 떨어져 배치해 허리 높이의 넓은 측면 구도가 되도록 했다."
}





Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 공중에 뜬 검은 실루엣의 정체불명의 습격자가 바닥에 쓰러진 숲속 사건의 남자 피해자를 향해 양팔을 뻗은 찰나 LOCATION (lock): A dense forest with thick undergrowth forming a rough escape path through the vegetation. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The fallen male victim must still be missing one shoe, with the large bite wound on his thigh continuing to bleed. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정체불명의 습격자 (한국인으로 보이는 성인 남성, 어둠에 가려진 얼굴, 식별하기 어려운 머리 형태, 붉은 눈동자를 제외한 이목구비 불명); 숲속 사건의 남자 피해자 (한국인 남성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 공중에 뜬 검은 실루엣의 정체불명의 습격자가 바닥에 쓰러진 숲속 사건의 남자 피해자를 향해 양팔을 뻗은 찰나 LOCATION (lock): A dense forest with thick undergrowth forming a rough escape path through the vegetation. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The fallen male victim must still be missing one shoe, with the large bite wound on his thigh continuing to bleed. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정체불명의 습격자 (한국인으로 보이는 성인 남성, 어둠에 가려진 얼굴, 식별하기 어려운 머리 형태, 붉은 눈동자를 제외한 이목구비 불명); 숲속 사건의 남자 피해자 (한국인 남성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Shoot from an extremely low position beside the fallen victim, looking upward through the rough escape path so the victim anchors the near foreground while the airborne attacker dominates above, both outstretched arms driving toward him. Use a wide, immersive lens feel with strong near-to-far depth; preserve readable human anatomy and clothing in the attacker while the dusk backlight keeps his face difficult to identify. Let the dense undergrowth close around the composition, making the suspended instant feel immediate and inescapable. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 공중에 뜬 검은 실루엣의 정체불명의 습격자가 바닥에 쓰러진 숲속 사건의 남자 피해자를 향해 양팔을 뻗은 찰나 LOCATION (lock): A dense forest with thick undergrowth forming a rough escape path through the vegetation. The shot takes place here — the attached PREVIOUS SHOT STILL shows this exact place. THIS SHOT CONTINUES THE PREVIOUS SHOT: everything the attached still established — the place, its fixed features and wear, each person's clothing and state — persists. Any person in it who cannot move stays PRECISELY as photographed (body, pose, contact points, held objects); only the camera changes. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The fallen male victim must still be missing one shoe, with the large bite wound on his thigh continuing to bleed. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정체불명의 습격자 (한국인으로 보이는 성인 남성, 어둠에 가려진 얼굴, 식별하기 어려운 머리 형태, 붉은 눈동자를 제외한 이목구비 불명); 숲속 사건의 남자 피해자 (한국인 남성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame the moment from a distant lateral viewpoint through the forest, using a compressed lens feel to hold the airborne attacker and fallen victim in a stark vertical relationship within the same shallow plane. Keep both bodies clearly legible in profile, emphasizing the attacker’s extended arms and the narrowing gap toward the victim rather than subjective impact. Dusk light filters softly across the vegetation while foreground foliage partially hems the frame, creating an observational, ominously restrained image. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Darken the flying attacker's entire head and face into a heavy, featureless black shadow, adding only distinct red pupils to his eyes. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 눈을 크게 뜬 채 겁에 질린 숲속 사건의 남자 피해자의 얼굴 정면 구도 LOCATION (lock): A dense forest with thick undergrowth forming a rough escape path through the vegetation. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The male victim is missing one shoe and has a large, bleeding bite mark on his thigh. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 숲속 사건의 남자 피해자 (한국인 남성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 눈을 크게 뜬 채 겁에 질린 숲속 사건의 남자 피해자의 얼굴 정면 구도 LOCATION (lock): A dense forest with thick undergrowth forming a rough escape path through the vegetation. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The male victim is missing one shoe and has a large, bleeding bite mark on his thigh. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 숲속 사건의 남자 피해자 (한국인 남성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use an eye-level, extreme frontal close-up, with the face nearly filling the frame and the eyes held close to the upper third. Keep the composition rigidly centered and confrontational, with very shallow focus dissolving the forest into dim dusk texture. Soft, cool ambient light falls evenly enough to preserve natural detail in both eyes while gentle undergrowth shadow shapes the face. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk. SHOT TEXT (authoritative, Korean): 눈을 크게 뜬 채 겁에 질린 숲속 사건의 남자 피해자의 얼굴 정면 구도 LOCATION (lock): A dense forest with thick undergrowth forming a rough escape path through the vegetation. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The male victim is missing one shoe and has a large, bleeding bite mark on his thigh. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 숲속 사건의 남자 피해자 (한국인 남성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from close range with a moderately wide perspective, keeping the face dominant and square to camera while allowing the head, shoulders, and receding escape path to remain legible. Build strong depth with nearby vegetation framing the foreground and the forest drawing away directly behind him. Let the fading dusk create uneven, natural patches of cool light and shadow, making the surrounding space feel immediate and inescapable. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim streetlights. SHOT TEXT (authoritative, Korean): 희미한 가로등 불빛 아래, 정체불명의 습격자가 뒷골목 사건의 여자 피해자를 전봇대에 거칠게 밀어붙인 채 뒤엉켜 있는 구도 LOCATION (lock): A narrow urban back alley lined with utility poles, including one where two figures are entangled. Sparse streetlights provide the only stated exterior illumination. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The female victim remains pinned against the utility pole and entangled with her attacker. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정체불명의 습격자 (한국인으로 보이는 성인 남성, 어둠에 가려진 얼굴, 식별하기 어려운 머리 형태, 붉은 눈동자를 제외한 이목구비 불명); 뒷골목 사건의 여자 피해자 (한국인 여성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim streetlights. SHOT TEXT (authoritative, Korean): 희미한 가로등 불빛 아래, 정체불명의 습격자가 뒷골목 사건의 여자 피해자를 전봇대에 거칠게 밀어붙인 채 뒤엉켜 있는 구도 LOCATION (lock): A narrow urban back alley lined with utility poles, including one where two figures are entangled. Sparse streetlights provide the only stated exterior illumination. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The female victim remains pinned against the utility pole and entangled with her attacker. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정체불명의 습격자 (한국인으로 보이는 성인 남성, 어둠에 가려진 얼굴, 식별하기 어려운 머리 형태, 붉은 눈동자를 제외한 이목구비 불명); 뒷골목 사건의 여자 피해자 (한국인 여성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the struggle from close range at roughly shoulder height, looking obliquely along the utility pole so it becomes a hard vertical anchor in the composition. Use a tight, claustrophobic crop and a moderately shallow depth of field, with the attacker’s near-side body partially dominating the foreground while the victim’s face, hair, and pinned posture remain clearly readable. Let the dim streetlight rake unevenly across the figures, preserving deep facial obscurity on the attacker and concentrating visual tension on their compressed physical entanglement. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, dim streetlights. SHOT TEXT (authoritative, Korean): 희미한 가로등 불빛 아래, 정체불명의 습격자가 뒷골목 사건의 여자 피해자를 전봇대에 거칠게 밀어붙인 채 뒤엉켜 있는 구도 LOCATION (lock): A narrow urban back alley lined with utility poles, including one where two figures are entangled. Sparse streetlights provide the only stated exterior illumination. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The female victim remains pinned against the utility pole and entangled with her attacker. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 정체불명의 습격자 (한국인으로 보이는 성인 남성, 어둠에 가려진 얼굴, 식별하기 어려운 머리 형태, 붉은 눈동자를 제외한 이목구비 불명); 뒷골목 사건의 여자 피해자 (한국인 여성, 성인, 평범한 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Frame the moment from farther down the alley in a wide, static composition, keeping the utility pole and the entangled pair as a stark focal cluster within the surrounding depth and empty alley space. Use a slightly elevated eye line and deep focus so the narrow passage, repeating poles, and sparse streetlights establish distance and isolation without diminishing the legibility of the pinning action. Hold most of the frame in restrained darkness, allowing the limited streetlight to isolate the figures with a cold, observational sense of danger. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the anatomically impossible extra hand and black sleeve from the right side of the utility pole. - Remove all visible text, letters, and characters from the utility pole. - Change the attacker's eye in the shadow so the iris is visibly red, maintaining normal anatomical proportions. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 해안가 도로를 배경으로 자전거 페달을 밟으며 앞으로 나아가는 수리영의 전신 측면, 머리카락이 뒤로 휘날리는 mid-action LOCATION (lock): A coastal road running alongside the sea, wide enough for a bicycle route with open views toward the water. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues riding her bicycle with her earphones in place. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 해안가 도로를 배경으로 자전거 페달을 밟으며 앞으로 나아가는 수리영의 전신 측면, 머리카락이 뒤로 휘날리는 mid-action LOCATION (lock): A coastal road running alongside the sea, wide enough for a bicycle route with open views toward the water. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues riding her bicycle with her earphones in place. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use an eye-level lateral tracking view, holding her complete profile and bicycle crisply in a balanced medium-wide frame with generous lead room ahead. Let the coastal background carry restrained horizontal motion blur while her pedaling body, face, and wind-swept hair remain sharply legible, giving the instant fluid forward momentum. Natural daylight with clean, dimensional modeling and realistic contrast. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day. SHOT TEXT (authoritative, Korean): 해안가 도로를 배경으로 자전거 페달을 밟으며 앞으로 나아가는 수리영의 전신 측면, 머리카락이 뒤로 휘날리는 mid-action LOCATION (lock): A coastal road running alongside the sea, wide enough for a bicycle route with open views toward the water. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues riding her bicycle with her earphones in place. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from a low, wider vantage near road level, keeping her entire figure and bicycle relatively compact within an expansive coastal composition. Use the road’s directional geometry and layered depth toward the open water to emphasize travel, with clear negative space in front of her and the mid-action pose frozen cleanly rather than blurred. Shape the daylight softly across her profile while preserving depth and detail throughout the setting. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove all text from the bicycle frame. - Redraw the bicycle crankset so the two arms are exactly 180 degrees apart, and ensure only two legs and two feet are visible on the pedals. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night. SHOT TEXT (authoritative, Korean): 어두운 해안도로를 배경으로 허리를 숙인 채 한쪽 무릎을 굽혀 페달을 강하게 밟아 누르고, 옷자락이 바람에 뒤로 날리는 수리영의 실루엣 LOCATION (lock): A coastal road beside the dark sea, serving as a bicycle route back toward the residential district. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues home on her bicycle with her mobile phone still in her possession. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night. SHOT TEXT (authoritative, Korean): 어두운 해안도로를 배경으로 허리를 숙인 채 한쪽 무릎을 굽혀 페달을 강하게 밟아 누르고, 옷자락이 바람에 뒤로 날리는 수리영의 실루엣 LOCATION (lock): A coastal road beside the dark sea, serving as a bicycle route back toward the residential district. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues home on her bicycle with her mobile phone still in her possession. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment in a wide lateral profile from a low, level camera position, keeping her full figure and bicycle cleanly readable against the dark coastal road and sea. Use restrained depth compression and strong negative space ahead of her, with subtle night backlight defining her human profile, bent posture, driving leg, and wind-swept clothing while retaining natural live-action detail within the shadow. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night. SHOT TEXT (authoritative, Korean): 어두운 해안도로를 배경으로 허리를 숙인 채 한쪽 무릎을 굽혀 페달을 강하게 밟아 누르고, 옷자락이 바람에 뒤로 날리는 수리영의 실루엣 LOCATION (lock): A coastal road beside the dark sea, serving as a bicycle route back toward the residential district. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues home on her bicycle with her mobile phone still in her possession. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Place the camera very low and close in a rear three-quarter tracking view, using an expansive lens feel so the bicycle and forceful pedal stroke dominate the foreground while her lowered torso drives diagonally through the frame. Let the road and dark shoreline recede deeply behind her; shape the available night light into a narrow edge around her body and flying garment, preserving realistic texture rather than reducing her to a featureless black shape. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Add a mobile phone to her hand or make it clearly visible in her pocket. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 어두운 밤바다를 배경으로 낡은 버스정류장 벤치에 고개를 숙인 채 멍하니 앉아 있는 수리영의 전신. LOCATION (lock): A bus-stop area along the coast with seating oriented toward the sea and an open roadside edge nearby. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still has her mobile phone and continues trying unsuccessfully to reach Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 어두운 밤바다를 배경으로 낡은 버스정류장 벤치에 고개를 숙인 채 멍하니 앉아 있는 수리영의 전신. LOCATION (lock): A bus-stop area along the coast with seating oriented toward the sea and an open roadside edge nearby. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still has her mobile phone and continues trying unsuccessfully to reach Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph the moment as a restrained, static eye-level full shot, with her entire body and the worn bench clearly framed against the dark sea. Use a balanced frontal composition with ample breathing room around her, keeping the phone visible but visually subordinate. Shape the night illumination softly from one side, preserving natural facial detail beneath the bowed head while the background falls into deep, quiet tonal layers. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night, exterior illumination unspecified. SHOT TEXT (authoritative, Korean): 어두운 밤바다를 배경으로 낡은 버스정류장 벤치에 고개를 숙인 채 멍하니 앉아 있는 수리영의 전신. LOCATION (lock): A bus-stop area along the coast with seating oriented toward the sea and an open roadside edge nearby. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong still has her mobile phone and continues trying unsuccessfully to reach Minsuk. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Take a low, oblique long-shot view from near the open roadside edge, using the foreground to lead diagonally toward the bench while the sea occupies broad negative space beyond. Keep her full figure relatively small in the frame, with the bowed posture and phone readable through clean separation rather than close detail. Favor subdued back-side illumination that traces the figure and bench without turning either into a silhouette, leaving the surrounding night dense and isolating. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Rotate the mobile phone in her hands so she is holding it vertically (portrait mode), which is appropriate for texting or calling. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): PC방 모니터 화면의 지도를 주시하는 수리영의 측면 상체. LOCATION (lock): A public computer café with individual monitor stations, internet-connected computers, and access to a printer for producing paper maps. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong keeps the coordinate note and phone with her and places the folded printed maps inside her doll-adorned backpack. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): PC방 모니터 화면의 지도를 주시하는 수리영의 측면 상체. LOCATION (lock): A public computer café with individual monitor stations, internet-connected computers, and access to a printer for producing paper maps. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong keeps the coordinate note and phone with her and places the folded printed maps inside her doll-adorned backpack. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph a tight side-profile upper-body close-up from seated eye level, with the near edge of the monitor forming a soft foreground plane and her face held in crisp focus. Use shallow depth and restrained monitor spill across her features, emphasizing the unwavering line of her gaze and the minute tension in her posture while the café recedes unobtrusively. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day, interior lighting unspecified. SHOT TEXT (authoritative, Korean): PC방 모니터 화면의 지도를 주시하는 수리영의 측면 상체. LOCATION (lock): A public computer café with individual monitor stations, internet-connected computers, and access to a printer for producing paper maps. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong keeps the coordinate note and phone with her and places the folded printed maps inside her doll-adorned backpack. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a wider lateral medium shot at monitor height, composing her upper body and the monitor as distinct opposing masses across the frame. Keep more of the computer-station depth legible with layered perspective and moderate depth of field, using subdued interior illumination and the screen as a localized visual anchor to make her concentrated stillness feel isolated within the café. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove the blurred man sitting at the computer in the background on the left. - Remove all text from the monitor screen, the documents on the backpack, the sticky note by the keyboard, and the wall signs in the background. - Remove the stack of papers resting on top of the backpack. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): late afternoon, heavy rain and thunderclouds. SHOT TEXT (authoritative, Korean): 비에 흠뻑 젖은 채 굳은 표정으로 앞을 노려보는 수리영의 얼굴 클로즈업. LOCATION (lock): An exposed coastal route beside the sea, traversed by bicycle during a heavy shower beneath dense storm clouds. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues riding her bicycle with the printed maps secured in her backpack, while the coordinate note and phone remain in her possession. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): late afternoon, heavy rain and thunderclouds. SHOT TEXT (authoritative, Korean): 비에 흠뻑 젖은 채 굳은 표정으로 앞을 노려보는 수리영의 얼굴 클로즈업. LOCATION (lock): An exposed coastal route beside the sea, traversed by bicycle during a heavy shower beneath dense storm clouds. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues riding her bicycle with the printed maps secured in her backpack, while the coordinate note and phone remain in her possession. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use an extremely tight, eye-level frontal close-up, holding her eyes near the upper third while the lower edge crops firmly below the chin. Keep both eyes sharply resolved and let the coastal route and sea dissolve into a soft, storm-darkened background; cold diffuse late-afternoon skylight and rain across her face emphasize the rigid stillness of her expression. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): late afternoon, heavy rain and thunderclouds. SHOT TEXT (authoritative, Korean): 비에 흠뻑 젖은 채 굳은 표정으로 앞을 노려보는 수리영의 얼굴 클로즈업. LOCATION (lock): An exposed coastal route beside the sea, traversed by bicycle during a heavy shower beneath dense storm clouds. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong continues riding her bicycle with the printed maps secured in her backpack, while the coordinate note and phone remain in her possession. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph her in a low, close three-quarter profile from alongside her direction of travel, with her face filling the frame and her fixed forward gaze aimed into compressed negative space ahead. Use a parallel tracking feel: keep her features crisp while the rain-lashed coastal surroundings trail into restrained directional blur, shaped by soft storm-cloud light with subtle contour along the wet cheek and jaw. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Crop the bottom edge of the frame tighter so it cuts off firmly just below the chin, removing the shoulders from view. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, dense fog after rain. SHOT TEXT (authoritative, Korean): 안개 낀 바다를 향해 갯바위 위에 멍하니 앉아 있는 수리영의 뒷모습. LOCATION (lock): An empty harbor bordered by tidal rocks, with moorings and a landing point for small boats. Dense fog obscures the water and hides other vessels from view. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong remains on the rocks with her backpack, the printed maps, the old photograph, and her mobile phone, which shows several missed calls from Hye-su. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, dense fog after rain. SHOT TEXT (authoritative, Korean): 안개 낀 바다를 향해 갯바위 위에 멍하니 앉아 있는 수리영의 뒷모습. LOCATION (lock): An empty harbor bordered by tidal rocks, with moorings and a landing point for small boats. Dense fog obscures the water and hides other vessels from view. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong remains on the rocks with her backpack, the printed maps, the old photograph, and her mobile phone, which shows several missed calls from Hye-su. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Photograph from a low, distant position directly behind her in a wide environmental composition. Place her seated figure low in the frame while the fog-obscured water occupies most of the image, using the tidal rocks, moorings, and landing point as subdued depth layers. Let the wet rock surfaces catch faint dusk reflections, with soft, directionless post-rain light preserving natural detail in her hair, clothing, body, and belongings rather than reducing her to a silhouette. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, dense fog after rain. SHOT TEXT (authoritative, Korean): 안개 낀 바다를 향해 갯바위 위에 멍하니 앉아 있는 수리영의 뒷모습. LOCATION (lock): An empty harbor bordered by tidal rocks, with moorings and a landing point for small boats. Dense fog obscures the water and hides other vessels from view. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot. REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot text may describe characters metaphorically, figuratively or with exaggeration. Photograph what a real movie camera would actually record on a physical set — exaggerated or figurative impressions become realistic staging choices (lighting, distance, angle, wardrobe), not literal fantasy imagery. EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly features non-human or virtual beings (as in science fiction or fantasy), every character — however indirectly, vaguely or figuratively the text describes them — IS a real human. When the text gives no direct visual description of a person, IMAGINE one and still show them as a concrete, fully-formed human being: always render the human form to the maximum extent — build, posture, face, hands, clothing — never reduce a person to a shape, blob, solid silhouette or abstract mass. EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a person's eyes, face or presence emotionally or figuratively (vacant, hollow, dazed, burning, lifeless gaze and the like), it describes an ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY through gaze direction, focus, eyelids, facial muscles, stillness and posture. Every living person's eyes remain anatomically normal human eyes with a natural iris and pupil, natural sclera and normal proportions; NEVER whiten, blank out, cloud over, glow, enlarge or otherwise alter eyeballs, skin or anatomy — unless the story explicitly declares that being non-human or supernatural in form. PROPS FACE THE RIGHT WAY: every handheld or used object must be oriented exactly as its real-world use requires. A person reading, watching or operating something (a phone, a photograph, a paper, any device) has its functional side — screen, front, page — facing THEIR OWN eyes; the camera then sees whatever side the staging geometry implies (often its back). Show the functional side to the camera ONLY when the shot text itself stages it toward the viewer. Never flip, mirror or reverse an object's front and back. CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong remains on the rocks with her backpack, the printed maps, the old photograph, and her mobile phone, which shows several missed calls from Hye-su. PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above. No text, captions, watermarks or annotations anywhere. VISUAL APPROACH — this take (camera, framing, composition): Use a tighter rear view from slightly above her seated height, framing her head, shoulders, back, and grounded posture as the visual center while keeping the established belongings clearly readable within the composition. Compress the harbor and foggy water into quiet, overlapping planes behind her, with the wet tidal-rock texture held sharply in the foreground and the distance dissolving softly into mist. Shape the dusk illumination as a gentle lateral wash through the fog, emphasizing her absolute stillness without revealing her face. PRIORITY OF INSTRUCTIONS: the VISUAL APPROACH above governs camera, framing and composition ONLY. Every other instruction in this prompt — location, time of day, people and their identity, poses, props, carried state, physical rules, and the no-text rule — is binding exactly as written earlier. If the VISUAL APPROACH appears to conflict with any of them, the earlier instruction wins.
Edit this photograph. Apply ONLY the corrections listed below, each in place, changing nothing else: CORRECTIONS: - Remove all boats and vessels from the water and dock so that none are visible. - Change the phone screen interface from an active incoming call to a screen displaying missed call text notifications. - Reposition the maps, photograph, and mobile phone to the rock space beside or slightly in front of the character so they fall within her natural field of view. PRESERVE EVERYTHING ELSE EXACTLY as in the original photograph — every person, pose, face, garment, object, set feature, lighting, camera and framing stay identical. No text, captions or watermarks anywhere.