s40 — 배경(플레이트)부터 스틸 선정까지 전부 3롤 + Gemini VLM 단독 판정

사용자 확정 규칙: ①모든 생성 단계=nb2 3롤(A/B/C) → Gemini VLM 판정 → 선정(선정본이 다음 단계 참조) ②실외 플레이트 8장=마스터 v2 참조 / 실내 플레이트 6장=FP+뿌리+직전 선정본 체이닝 ③스틸 23샷 참조=배경 플레이트(항상)+prev 선정본(배경 동일성 v3 판정)+캐릭터·소품(인물 샷) 모두 첨부(단일 참조 아님) ④배경 전용 샷=플레이트만+NO PEOPLE ⑤선정본 결함 수정 패스: Gemini 가 선정본의 프롬프트 위반을 검출 → 결함 있으면 수정 프롬프트 저작 → nb2 i2i(그 이미지 단독 참조) 수정본이 최종 선정본(체인 앵커), 수정 전/후 비교 표시. 텍스트 안전망(자세 정본·carried· EXPRESSION_REALISM·PROP_ORIENTATION·캐릭터 traits) 유지. 이전 판: s39 · s38

★ 스틸 선정본 모아보기 (23샷)

S4sh1 — A (Gemini 7점)
S10sh6 — C (Gemini 7점)
S10sh7 — A (Gemini 8점)
S11sh5 — C (Gemini 8점)
S17sh2 — B (Gemini 7점)
S11sh4 — C (Gemini 7점)
S13sh4 — A (Gemini 7점)
S13sh6 — B (Gemini 7점)
S5sh5 — C (Gemini 7점)
S5sh9 — A (Gemini 7점)
S12sh11 — B (Gemini 7점)
S12sh18 — C (Gemini 7점)
S12sh21 — C (Gemini 7점)
S14sh5 — C (Gemini 7점)
S14sh7 — B (Gemini 7점)
S14sh11 — C (Gemini 8점)
S18sh11 — A (Gemini 7점)
S18sh15 — C (Gemini 7점)
S18sh16 — A (Gemini 7점)
S25sh1 — C (Gemini 7점)
S25sh5 — B (Gemini 7점)
S25sh9 — A (Gemini 7점)
S27sh3 — B (Gemini 7점)

플레이트 — 실외 8(마스터 v2) + 실내 6(FP 체이닝)

마스터=master2.png · FP=floorplan

실외 bg_S4sh1 — 랭킹 A>B>C

★ 선정
A — Gemini 7점
마당, 대문, 옥상 구조물의 배치를 원본과 가장 가깝게 재현했으나, 2층 계단이 벽과 융합되는 형태적 오류가 있습니다.
B — Gemini 5점
옥상 구조물은 존재하지만 원본의 마당 담장과 대문이 완전히 누락되어 구조적 일관성이 떨어집니다.
C — Gemini 3점
물탱크, 평상 등 프롬프트가 지시한 옥상 핵심 요소들이 누락되었고 대문 구조도 원본과 다릅니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION MASTER PHOTOGRAPH — the exact building and grounds where this
master2.png
프롬프트
Using the attached master photo as the exact architectural and location reference, create a photorealistic live-action empty background plate of the same old low-rise Korean multifamily villa and its rooftop dwelling in the outskirts of contemporary Incheon. High-angle bird’s-eye view looking down toward the rooftop: clearly show the flat roof terrace, low parapet, separate rectangular rooftop home, plain closed metal entrance door, small living-room window, water tank, clothesline, and low wooden herb-drying platform in their established master-image arrangement. Include only the restrained surrounding fabric visible from this elevated direction—narrow paved alleys, nearby aging villas, utility poles and cables, and a subdued urban horizon. Clear ordinary daytime with soft natural sunlight and realistic colors, matching the scene. Deep focus, believable scale, documentary architectural photography, wide establishing composition. Empty set: no people, animals, moving vehicles, readable text, incident evidence, police activity, dramatic shadows, or event-specific props.

실외 bg_S10sh6 — 랭킹 A>B>C

★ 선정
A — Gemini 7점
프롬프트의 지시대로 문을 닫은 상태로 유지했으며, 원본의 문 디자인(창문, 우편함 형태)과 야간 분위기를 충실히 재현했습니다.
B — Gemini 4점
옥상 바닥의 질감은 원본과 유사하게 구현했으나, 문을 닫아두라는 핵심 지시를 어기고 열린 상태로 생성했습니다.
C — Gemini 3점
문을 닫으라는 지시를 무시했을 뿐만 아니라, 원본의 단일 금속 문과 전혀 다른 양개형 문으로 구조를 임의 변경했습니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION MASTER PHOTOGRAPH — the exact building and grounds where this
master2.png
프롬프트
Using the attached master photo as the exact reference for the same rooftop dwelling, create a photorealistic live-action empty background plate at night from an extremely low, tight camera position directly outside the rooftop home’s metal entrance, aimed toward the threshold and entry area. Frame the established plain metal door, doorframe, and the narrow floor area at the threshold in close-up. The interior beyond the entrance should read as unlit and dark, without inventing additional rooms or architectural details. For the clean empty plate, keep the metal door closed in its ordinary undisturbed state; no visible person, shoe, hand, flyer, forced lock, damage, or incident-specific condition. Restrained natural night ambience on the rooftop, realistic weathered surfaces, shallow-to-moderate depth of field, no readable text, no ominous stylization.

실외 bg_S10sh7 — 랭킹 A>B>C

★ 선정
A — Gemini 6점
옥상 테라스 내부에서 창문을 향하는 구도 지시를 유일하게 따랐으나, 좌측 계단 구조가 벽으로 막혀 있는 등 물리적으로 어색합니다.
B — Gemini 4점
원본 사진의 공중 카메라 구도를 피하라는 지시를 어기고 드론 뷰를 거의 그대로 모방했습니다.
C — Gemini 3점
카메라 구도 지시를 위반했을 뿐만 아니라 옥상 구조물의 필수 요소인 출입문을 완전히 누락했습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION MASTER PHOTOGRAPH — the exact building and grounds where this
master2.png
프롬프트
Using the attached master photo as the exact reference for the same rooftop dwelling, create a locked-off photorealistic live-action empty background plate at night, facing the established small living-room window from across the open roof terrace. The rooftop room is illuminated from inside, so the window glows naturally against the weathered exterior wall, but the glass and curtain surface must contain no human figures, silhouettes, reflections of people, violent action, or event-specific shadows. Preserve the master location’s flat roof, low parapet, and only those nearby rooftop fixtures that naturally fall within this camera angle. Static composition, realistic low-light exposure, subdued contemporary Incheon residential surroundings, no people, animals, readable text, police activity, or incident evidence.

실외 bg_S11sh5 — 랭킹 B>A>C

A — Gemini 4점
창문과 평상은 있으나, 물탱크가 원본과 달리 화면 우측 전경을 기형적으로 가리고 있어 공간적 일관성이 떨어집니다.
★ 선정
B — Gemini 7점
문의 색상과 형태, 우측의 창문, 평상 위 물탱크의 위치와 크기 등 원본의 모든 건축적 요소들을 매우 정확하게 재현했습니다.
C — Gemini 3점
옥상 구조물 우측에 반드시 있어야 할 창문, 평상, 물탱크가 완전히 누락되어 원본과의 일치도가 가장 낮습니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 B)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION MASTER PHOTOGRAPH — the exact building and grounds where this
master2.png
프롬프트
Using the attached master photo as the exact architectural reference, create a photorealistic live-action empty background plate at night from eye level on the rooftop landing, looking straight toward the same rooftop dwelling’s plain metal entrance door. Show the open roof terrace leading to the doorway, the weathered exterior wall, doorframe, and any fixed rooftop elements visible in their established master-image positions. As a clean undisturbed plate, the metal door is fully closed and intact, with no flyer in the seam, no forced entry, no interior figure, and no incident-specific condition. Natural dim night ambience, realistic scale and weathering, frontal composition, no people, animals, readable text, police lights, vehicles, blood, or dramatic horror lighting.

실외 bg_S17sh2 — 랭킹 B>A>C

A — Gemini 4점
옥상 구조물의 방향과 주변 건물의 공간 배치가 원본 사진의 구조와 어긋납니다.
★ 선정
B — Gemini 6점
원본의 전체적인 공간 배치와 새벽 분위기를 가장 잘 구현했으나, 물탱크 등 일부 디테일이 생략되었습니다.
C — Gemini 3점
전경의 난간이 허공에 떠 있고 계단의 위치가 잘못되어 물리적 일관성이 크게 결여되어 있습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 B)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION MASTER PHOTOGRAPH — the exact building and grounds where this
master2.png
프롬프트
Using the attached master photo as the exact location reference, create a photorealistic live-action empty background plate at dawn from parapet height on the same rooftop, composed in side profile along the top edge of the low rooftop wall. Keep the parapet edge prominent in the foreground as the surface where an animal would be composited, with the rooftop dwelling and its established small window visible in the background from the appropriate lateral direction. The room window may retain a subdued warm interior glow against the cool first light of dawn. Quiet outskirts-of-Incheon atmosphere, soft blue-gray dawn sky, realistic weathered masonry, shallow-to-moderate depth of field. No cat, no people, no animals, no readable text, no incident evidence, and no invented rooftop structures.

실외 bg_S11sh4 — 랭킹 C>A>B

A — Gemini 5점
야간 조명과 피사계 심도는 적절하지만, 원본에 없는 시멘트 블록 벽이 생성되어 건축적 일관성을 잃었습니다.
B — Gemini 4점
개방형 철제 계단이 콘크리트 구조로 왜곡되고 계단 재질도 달라져 원본과의 형태적 일치도가 가장 낮습니다.
★ 선정
C — Gemini 6점
원본의 재질(철판, 난간)과 마당 요소를 가장 잘 재현했으나, 배경에 계단이 중복 배치된 공간적 오류가 아쉽습니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION MASTER PHOTOGRAPH — the exact building and grounds where this
master2.png
프롬프트
Using the attached master photo as the exact architectural and spatial reference, create a photorealistic live-action empty background plate at night from close face height on the continuous side/rear staircase connecting the enclosed courtyard to the rooftop. The camera is positioned at a middle stair landing beside the established simple metal pipe handrail, with the handrail and adjacent weathered villa wall forming the near background and the stair route receding naturally behind. Compose it as a close-up background suitable for placing a person paused midway on the stairs, but show no person or hand. Preserve only the stair geometry and fixed surfaces supported by the master image. Realistic dim residential night lighting, natural colors, shallow depth of field, no animals, readable text, police lights, damage, or event-specific props.

실외 bg_S13sh4 — 랭킹 C>A>B

A — Gemini 5점
마당의 전반적인 분위기는 모방했으나, 계단이 허공에서 끊기는 등 물리적 오류가 있으며 우측 건물 형태가 다릅니다.
B — Gemini 3점
원본의 다세대 주택 구조를 완전히 무시하고 다른 형태의 건축물과 계단을 생성하여 공간적 일관성이 매우 떨어집니다.
★ 선정
C — Gemini 7점
마당의 불규칙한 바닥재, 화분, 계단 아래 잡동사니 등 원본의 디테일을 가장 잘 살렸으나 계단 방향과 우측 벽면 구조에 일부 차이가 있습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION MASTER PHOTOGRAPH — the exact building and grounds where this
master2.png
프롬프트
Using the attached master photo as the exact reference for the same old multifamily villa and its ground-level surroundings, create a photorealistic live-action empty background plate at night from standing eye level near the villa’s ground entrance, facing the small enclosed courtyard and the base of the continuous side/rear stair. Compose a neutral medium close-up background with sufficient clear foreground space for a standing person, while keeping the weathered entrance area, courtyard surfaces, and lower stair architecture spatially consistent with the master. Do not add a police car or any unestablished object. Restrained natural neighborhood night ambience, realistic exposure and weathering, no people, animals, vehicles in action, siren light, readable text, blood, evidence, or event-specific disturbance.

실외 bg_S13sh6 — 랭킹 C>B>A

A — Gemini 3점
계단이 물리적으로 연결되지 않은 기하학적 오류가 있으며 대문 디자인이 원본과 다릅니다.
B — Gemini 4점
계단 형태가 원본의 지그재그 구조와 크게 다르고 마당 출입문이 누락되어 일관성이 떨어집니다.
★ 선정
C — Gemini 7점
지시된 측면 카메라 구도를 정확히 따랐으며 원본의 대문 디자인과 계단 하단부 형태를 가장 잘 유지했습니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION MASTER PHOTOGRAPH — the exact building and grounds where this
master2.png
프롬프트
Using the attached master photo as the exact reference for the same villa location, create a photorealistic live-action empty background plate at night from shoulder height beside the ground-level entrance and enclosed courtyard, oriented laterally across the approach between the narrow alley and the base of the rooftop stair. Frame the weathered villa wall, courtyard edge, entrance architecture, and lower portion of the established metal-railed stair as a side-profile dialogue background, leaving uncluttered midground space where two performers would be composited facing each other. Keep all architecture consistent with the master and do not invent signage or additional structures. Natural subdued residential night lighting, realistic depth of field, no people, police personnel, vehicles, flashing lights, readable text, blood, or incident-specific props.

실내 plate_living_dining_day_root — 랭킹 C>A>B

A — Gemini 5점
개별 피사체의 상태는 양호하나, 주방이 후면 벽에 배치되고 내부 문이 2개만 보여 전체적인 공간 구조와 시점이 도면과 어긋납니다.
B — Gemini 4점
창문과 주방이 후면에 배치되는 등 도면의 레이아웃과 전혀 다르며, 요구된 3개의 방 문이 제대로 노출되지 않았습니다.
★ 선정
C — Gemini 7점
지정된 카메라 위치(현관 쪽)에서 좌측 주방과 창문, 그리고 3개의 내부 문(침실 2, 욕실 1)을 모두 정확하게 묘사해 도면 충실도가 가장 높습니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (1장)
FLOOR PLAN — the spatial truth of this interior
int_fp.png
프롬프트
ROOT PLATE. Use the attached floor-plan specification as the authoritative layout for the same small 38–45 square meter Korean rooftop apartment. Daytime interior, with narrow natural sunlight entering through the small exterior living-room window. Place the camera at standing eye level near the entry-side corner, looking diagonally across the central combined living and dining area so the maximum number of fixed spatial identifiers are visible: the compact dining table and several upright chairs, the linear kitchenette with sink, faucet, short worktop, base cabinets and compact cooktop, the television, floor lamp, small exterior window, and the direct interior doors leading to the two bedrooms and bathroom. Include the ordinary framed family photograph near the dining area, with tiny indistinct photographic details and no text. Keep the TV off, the faucet off, the cooktop off, and any pot clean and inactive. Modest, compact, lived-in rooftop housing, realistic Korean residential interior, photorealistic live-action background plate, natural perspective and restrained production design. Empty set: no people, no readable text, no blood, no footprints, no overturned furniture, no boiling water, no spilled cups, no supernatural circles, no damaged or melting photograph, and no other incident-moment state.

실내 plate_living_dining_sunset_floor_view — 랭킹 B>A>C

A — Gemini 5점
카메라 높이 변화가 거의 없으며, 벽면에 프롬프트에서 금지한 오염 자국(특정 사건을 암시하는 상태)이 생성되었습니다.
★ 선정
B — Gemini 6점
약간 낮아진 카메라 구도와 따뜻한 일몰 채광을 잘 표현했으며, 원본의 재질과 객체 배치를 충실히 유지했습니다.
C — Gemini 4점
바닥 재질이 나무로 변경되어 레퍼런스와 어긋나며, 왼쪽 프레임에 구조물이 추가되어 TV가 가려졌습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 B)
수정 후 (i2i, 최종)
참조 (2장)
FLOOR PLAN — the spatial truth of this interior
int_fp.png
ROOT INTERIOR PHOTOGRAPH — the same interior
plate_living_dining_day_root_sel.png
프롬프트
Use the attached floor plan and the supplied root plate, which depict this exact same small Korean rooftop apartment; also use the immediately previous plate as the continuity reference. Sunset interior. Position the camera near the entry threshold at a slightly lower standing height than the root view, looking inward and gently downward across the living-room floor and compact dining zone toward the small exterior window. Preserve exactly the same spatial relationships, architecture, television, floor lamp, linear kitchenette, dining table, chairs, framed family photograph, and direct bedroom and bathroom doors established by the root. Warm fading sunset light enters through the small window while the interior remains naturally dim. All dining chairs must be upright in their normal positions and the exterior window closed in a neutral condition. Leave clear floor area and believable close-up background depth for a person standing in the common room. Photorealistic live-action empty background plate, no people, no readable text, no muddy footprints, no overturned chairs, no searched-through belongings, no open window, no blood, no supernatural marks, no phone, and no other incident-specific state.

실내 plate_daughter_bedroom_sunset_bed_wall — 랭킹 C>B>A

A — Gemini 3점
침대가 반대쪽 벽에 배치되었고 문의 위치와 거실 뷰가 도면과 어긋납니다.
B — Gemini 3점
방의 좌우 구조가 완전히 뒤바뀌어 문과 창문의 위치가 도면과 일치하지 않습니다.
★ 선정
C — Gemini 7점
도면의 방 구조(좌측 문, 정면 침대, 우측 창문)와 이전 컷의 거실 연결이 정확히 구현되었습니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (3장)
FLOOR PLAN — the spatial truth of this interior
int_fp.png
ROOT INTERIOR PHOTOGRAPH — the same interior
plate_living_dining_day_root_sel.png
PREVIOUS ADJACENT VIEW — the immediately preceding plate of this same
plate_living_dining_sunset_floor_view_sel.png
프롬프트
Use the attached floor plan, the supplied root plate, and the immediately previous sunset living-room plate as references for this exact same rooftop apartment. Sunset interior in the daughter's bedroom. Place the camera just inside the daughter's open interior doorway, facing into the compact room toward the single bed and the wall above the bed, while also retaining part of the exterior window with full-length curtains and the usable recess behind the curtains in the composition. Through the doorway edge, preserve a small visual connection to the sunset common area established in the previous plate. The single bed rests against a wall; include the backpack and doll only as ordinary, neatly placed loose belongings consistent with the floor-plan specification. Warm, fading sunset light, realistic compact-room proportions, photorealistic live-action background plate. Keep the wall above the bed completely plain and undamaged. Empty set: no people, no readable text, no red circle, no pinned or bloodstained photograph, no blood, no corpse, no disturbed furniture, no clenched hand, and no other incident-moment state.

실내 plate_daughter_bedroom_night_doorway_wide — 랭킹 C>A>B

A — Gemini 5점
야간 설정은 맞으나, 원본에 없는 닫힌 문과 무늬가 있는 수납장이 추가되었습니다.
B — Gemini 3점
야간이 아닌 일몰에 가까운 조명이며, 침대 위 창문이 커튼으로 가려져 참조 이미지와 불일치합니다.
★ 선정
C — Gemini 7점
요청된 야간 시간대를 잘 반영했으며, 이전 참조 이미지의 방 구조와 소품 위치를 충실히 재현했습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (3장)
FLOOR PLAN — the spatial truth of this interior
int_fp.png
ROOT INTERIOR PHOTOGRAPH — the same interior
plate_living_dining_day_root_sel.png
PREVIOUS ADJACENT VIEW — the immediately preceding plate of this same
plate_daughter_bedroom_sunset_bed_wall_sel.png
프롬프트
Use the attached floor plan, the supplied root plate, and the immediately previous daughter's-bedroom sunset plate as references for the exact same room and geometry. Night interior. Re-create the daughter's bedroom from nearly the same camera axis, with the camera at the interior doorway looking toward the single bed, the wall above the bed, and the exterior window with full-length curtains and sufficient recess space behind them. Preserve the bed, window, curtain, door, backpack and doll positions as normal residential set dressing, but present the room exceptionally neat and clean. The common area beyond the doorway should be dim, with only plausible low spill from the living-room floor lamp; no invented fixtures. Photorealistic live-action empty background plate, realistic night exposure and compact rooftop-apartment scale. No people, no readable text, no corpse, no blood, no bloody footprints, no wound, no old photograph, no red circle on the wall, no shifted belongings, and no other incident-specific or supernatural state.

실내 plate_entry_night_inward_view — 랭킹 C>B>A

A — Gemini 3점
금지된 복도 구조를 생성했을 뿐만 아니라 램프의 형태를 왜곡하고 전체적인 공간 배치가 평면도와 크게 어긋납니다.
B — Gemini 4점
야간 실내 조명과 가구의 형태는 양호하나, 원본 평면도에 없는 긴 복도를 임의로 생성하여 공간 구조 지침을 심각하게 위반했습니다.
★ 선정
C — Gemini 7점
복도를 추가하지 않고 현관과 거실을 직접 연결하라는 핵심 공간 지시를 가장 잘 따랐으며, 지정된 가구와 야간 조명 분위기를 무난하게 구현했습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (3장)
FLOOR PLAN — the spatial truth of this interior
int_fp.png
ROOT INTERIOR PHOTOGRAPH — the same interior
plate_living_dining_day_root_sel.png
PREVIOUS ADJACENT VIEW — the immediately preceding plate of this same
plate_daughter_bedroom_night_doorway_wide_sel.png
프롬프트
Use the attached floor plan, the supplied root plate, and the immediately previous night daughter's-bedroom plate as continuity references for this exact same rooftop apartment. Night interior at the entry. Place the camera immediately beside the exterior entry door, facing inward across the compact shoe-removal threshold and small shoe area toward the central living and dining room. Show enough of the common room to identify the same dining table, television or floor-lamp zone, and the direct interior doorways established by the root, without adding a corridor. The entry must feel compact and directly connected to the living space. Use dim practical spill from the existing living-room floor lamp and subdued night ambience; do not invent additional lighting fixtures. Leave neutral background depth suitable for a tight facial shot near the entrance. Photorealistic live-action empty set, no people, no readable text, no police equipment, no disturbed belongings, no blood, no footprints, no supernatural marks, and no incident-moment state.

실내 plate_bathroom_day_mirror_tile_view — 랭킹 B>C>A

A — Gemini 4점
거울에 물리적으로 불가능한 전혀 다른 공간과 문이 반사되어 사실적인 공간 및 반사 요구사항을 심각하게 위반했습니다.
★ 선정
B — Gemini 7점
평면도 배치를 준수하고 반대편 타일 벽의 거울 반사를 현실적으로 구현하여 프롬프트의 요구사항을 가장 충실히 따랐습니다.
C — Gemini 5점
평면도와 달리 세면대의 위치가 잘못되었으며, 거울에 일치하지 않는 샤워기와 창문이 반사되어 공간적 일관성이 떨어집니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 B)
수정 후 (i2i, 최종)
참조 (3장)
FLOOR PLAN — the spatial truth of this interior
int_fp.png
ROOT INTERIOR PHOTOGRAPH — the same interior
plate_living_dining_day_root_sel.png
PREVIOUS ADJACENT VIEW — the immediately preceding plate of this same
plate_entry_night_inward_view_sel.png
프롬프트
Use the attached floor plan, the supplied root plate, and the immediately previous entry-at-night plate as references for the same compact rooftop apartment; preserve the bathroom door's direct relationship to the central common area established by the root. Daytime interior in the small bathroom. Place the camera inside the bathroom, near the interior door and at standing eye level, facing the washbasin and wall mirror so that a substantial section of the opposite tiled bathroom wall is clearly visible in the mirror reflection. Include only the specified compact residential fixtures: washbasin with faucet, wall mirror, tiled walls, compact toilet, and minimal shower fittings. Maintain realistic 2.5–3.5 square meter proportions and modest Korean rooftop-apartment materials. Soft neutral daytime light, photorealistic live-action empty background plate. The mirror and reflected tile wall must be clean and ordinary. No people or human reflection, no readable text, no water running, no red circle, no blood, no supernatural effect, and no other incident-moment state.

옥상·옥탑방 외부 (rooftop_room_exterior)

LOCATION lock: The flat rooftop of an aging low-rise apartment building, enclosed by a waist-high parapet. A small rooftop dwelling has a metal entrance door and a window visible from the open roof.

S4sh1 플레이트만 (배경 전용) — 랭킹 A>C>B

맑은 낮, 오래된 다세대 빌라 옥상 위에 자리 잡은 옥탑방을 높은 곳에서 내려다본 부감 구도
★ 선정
A — Gemini 7점
로케이션 사진의 건축 양식, 구조물 및 세부 요소(빨랫줄 등)를 가장 정확하게 재현했습니다.
B — Gemini 4점
원본 로케이션에 없는 거대한 녹색 지붕이 전경에 추가되어 공간적 일관성이 낮습니다.
C — Gemini 5점
전반적인 구조는 일치하나 로케이션 사진에 명시된 옥상의 빨랫줄이 누락되었습니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
bg_S4sh1_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): daytime.

SHOT TEXT (authoritative, Korean): 맑은 낮, 오래된 다세대 빌라 옥상 위에 자리 잡은 옥탑방을 높은 곳에서 내려다본 부감 구도

LOCATION (lock): The flat rooftop of an aging low-rise apartment building, enclosed by a waist-high parapet. A small rooftop dwelling has a metal entrance door and a window visible from the open roof. 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.

MOVEMENT (follow exactly): static: No person is visible; the rooftop room remains fixed on top of the old multi-family villa beneath the high, downward-looking camera.

FIGURES — size & depth (follow exactly): The rooftop room appears small, about ~1/6 of the frame height, and is FARTHER from the camera than the surrounding upper roof surfaces in the foreground.

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.

S10sh6 플레이트만 (배경 전용) — 랭킹 C>A>B

현관 철문이 아주 살짝 열린 틈새로 보이는 어두운 실내와 신발 앞코
A — Gemini 5점
문이 너무 넓게 열려 있고 다리가 선명하게 보여 '보이지 않는 몸' 지시를 어겼습니다.
B — Gemini 4점
다리가 노출되었으며, 레퍼런스와 달리 문에 도시 불빛이 반사되어 장소 일치도가 떨어집니다.
★ 선정
C — Gemini 7점
'아주 살짝 열린 틈새'와 '보이지 않는 몸' 지시를 잘 지켜 신발 앞코만 적절하게 표현했습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
bg_S10sh6_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 현관 철문이 아주 살짝 열린 틈새로 보이는 어두운 실내와 신발 앞코

LOCATION (lock): The flat rooftop of an aging low-rise apartment building, enclosed by a waist-high parapet. A small rooftop dwelling has a metal entrance door and a window visible from the open roof. 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.

MOVEMENT (follow exactly): The unknown man's shoe toe advances from the rooftop exterior through the narrowly opened iron doorway into the dark room, leading his unseen body inward.

FIGURES — size & depth (follow exactly): The shoe toe is small, about ~1/10 of the frame height, and lies FARTHER from the camera than the NEARER iron door edges; the dark interior recedes farthest beyond it.

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.

S10sh7 플레이트만 (배경 전용) — 랭킹 A>B>C

불이 켜진 옥탑방 창문에 거대한 그림자가 작은 그림자의 어깨 쪽으로 고개를 꺾은 형태가 맺혀 있는 정지 구도
★ 선정
A — Gemini 8점
지정된 로케이션을 완벽하게 재현했으며, 남자 그림자가 여자 그림자의 어깨 쪽으로 고개를 꺾으며 겹치는 디테일과 크기 비율을 가장 정확히 구현했습니다.
B — Gemini 5점
배경은 훌륭하게 묘사되었으나, 두 그림자가 얼굴을 마주보고 있어 '어깨 쪽으로 고개를 꺾은' 프롬프트의 지시와 어긋납니다.
C — Gemini 4점
배경 재현율은 높지만, 남자 그림자의 고개가 꺾인 형태가 뚜렷하지 않고 두 인물의 어깨 쪽 겹침 묘사가 부족합니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
bg_S10sh7_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 불이 켜진 옥탑방 창문에 거대한 그림자가 작은 그림자의 어깨 쪽으로 고개를 꺾은 형태가 맺혀 있는 정지 구도

LOCATION (lock): The flat rooftop of an aging low-rise apartment building, enclosed by a waist-high parapet. A small rooftop dwelling has a metal entrance door and a window visible from the open roof. 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.

MOVEMENT (follow exactly): static: A real man appearing as a large dark silhouette, with normal human build, leans into Minsook and angles his head down toward her shoulder as she is caught beneath him.

FIGURES — size & depth (follow exactly): The man's shadow fills roughly ~2/3 of the frame height, larger than Minsook's smaller shadow at about ~1/3; both people are FARTHER than the NEARER window surface, while their mutual camera-depth order is not established. Their silhouettes overlap at Minsook's shoulder, leaving almost no distance between their paths.

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.

S11sh5 플레이트+prev+엔티티 (prev=S10sh6) — 랭킹 C>B>A

prev 사용 지시: Take the aged rooftop surface, metal entrance door, surrounding exterior materials, and nighttime illumination from the reference. Keep the entrance door visibly open to the degree required by the current scene. Exclude the stranger's shoe and any suggestion that the stranger is still standing at the doorway.
옥상에 선 수리영의 시선 끝에 반쯤 열려 있는 어두운 현관 철문이 보이는 정면 구도
A — Gemini 4점
배경과 문의 묘사는 훌륭하지만 캐릭터 레퍼런스의 모자가 누락되어 시각적 연속성이 떨어집니다.
B — Gemini 5점
캐릭터의 외형은 잘 일치하나, 명시적으로 제외하라고 지시한 신발 형태의 물체가 문턱에 남아있어 감점되었습니다.
★ 선정
C — Gemini 8점
캐릭터의 의상(모자 포함)을 정확히 유지하고 지시대로 현관문의 신발을 성공적으로 배제하여 프롬프트를 가장 충실히 구현했습니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (3장)
LOCATION PHOTOGRAPH — the exact place of this shot
bg_S11sh5_sel.png
PREVIOUS SHOT STILL — a visually related earlier shot of this same pla
S10sh6_sel.png
CHARACTER REFERENCE — 수리영
39864973-d3d5-4886-bfb2-f8db608a005b.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 옥상에 선 수리영의 시선 끝에 반쯤 열려 있는 어두운 현관 철문이 보이는 정면 구도

LOCATION (lock): The flat rooftop of an aging low-rise apartment building, enclosed by a waist-high parapet. A small rooftop dwelling has a metal entrance door and a window visible from the open roof. 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 aged rooftop surface, metal entrance door, surrounding exterior materials, and nighttime illumination from the reference. Keep the entrance door visibly open to the degree required by the current scene. Exclude the stranger's shoe and any suggestion that the stranger is still standing at the doorway.

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.

MOVEMENT (follow exactly): static: Suriyoung stands tensely on the rooftop with her body and gaze directed straight toward the half-open iron entrance door and its dark interior.

FIGURES — size & depth (follow exactly): Suriyoung appears about ~1/2 of the frame height in the NEARER rooftop area, while the half-open door appears about ~1/3 and is FARTHER ahead along her line of sight.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (Korean young woman, early 20s face, oval face, natural black long hair) — 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.

S17sh2 플레이트만 (배경 전용) — 랭킹 B>A>C

옥상 담벼락 위에서 한쪽 앞발을 허공으로 뻗은 검은 고양이의 측면
A — Gemini 5점
배경은 레퍼런스와 훌륭하게 일치하나, 고양이가 앞발을 허공으로 뻗는 역동적인 동작이 부족합니다.
★ 선정
B — Gemini 7점
앞발을 허공으로 뻗은 고양이의 자세와 배경의 모든 고정 요소(물탱크 포함)를 정확하게 재현했습니다.
C — Gemini 3점
고양이의 도약 자세가 다소 부자연스러우며, 레퍼런스에 있는 붉은 물탱크가 누락되었습니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 B)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
bg_S17sh2_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dawn.

SHOT TEXT (authoritative, Korean): 옥상 담벼락 위에서 한쪽 앞발을 허공으로 뻗은 검은 고양이의 측면

LOCATION (lock): The flat rooftop of an aging low-rise apartment building, enclosed by a waist-high parapet. A small rooftop dwelling has a metal entrance door and a window visible from the open roof. 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.

MOVEMENT (follow exactly): The black cat moves side-on across and over the rooftop wall toward the opposite side, extending one forepaw into the air as its body follows.

FIGURES — size & depth (follow exactly): The cat appears medium-sized, about ~1/3 of the frame height, and is NEARER to the camera than the FARTHER side beyond the wall; the wall runs beneath its crossing path.

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.

외부 철제계단 (exterior_metal_staircase)

LOCATION lock: A narrow exterior metal staircase attached to an old low-rise residential building. It has exposed steel steps and tubular pipe railings leading upward toward the roof.

S11sh4 플레이트+엔티티 — 랭킹 C>A>B

철제 파이프 난간을 손으로 잡은 수리영이 코끝을 찡그린 채 계단 중간에 서 있는 얼굴 클로즈업
A — Gemini 4점
동작과 표정은 자연스러우나, 얼굴 클로즈업 지시를 무시하고 너무 넓은 샷으로 렌더링되었습니다.
B — Gemini 3점
프레이밍은 나쁘지 않으나, 손이 난간을 잡지 않고 허공에 떠 있는 치명적인 묘사 오류가 있습니다.
★ 선정
C — Gemini 7점
클로즈업 프레이밍 요건에 가장 근접하며, 난간을 잡는 동작과 찡그린 표정을 정확히 구현했습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (2장)
LOCATION PHOTOGRAPH — the exact place of this shot
bg_S11sh4_sel.png
CHARACTER REFERENCE — 수리영
39864973-d3d5-4886-bfb2-f8db608a005b.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 철제 파이프 난간을 손으로 잡은 수리영이 코끝을 찡그린 채 계단 중간에 서 있는 얼굴 클로즈업

LOCATION (lock): A narrow exterior metal staircase attached to an old low-rise residential building. It has exposed steel steps and tubular pipe railings leading upward toward the roof. 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.

MOVEMENT (follow exactly): static: Suri-young pauses midway up the staircase while ascending toward the rooftop, gripping the metal-pipe railing with a tense posture and wrinkling her nose at the sudden foul smell, her body oriented uphill.

FIGURES — size & depth (follow exactly): Suri-young’s face fills ~2/3 of the frame height in close-up and is the nearest figure; her hand and the metal-pipe railing sit slightly farther from the camera as she remains midway on the stairs.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (Korean young woman, early 20s face, oval face, natural black long hair) — 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.

빌라 골목·마당 (residential_alley_courtyard)

LOCATION lock: A confined ground-level alley and small courtyard beside an aging multi-unit residential building. Concrete walls, building entrances, and the base of the exterior access structure frame the space.

S13sh4 플레이트+엔티티 — 랭킹 A>C>B

수리영이 초점을 잃은 눈으로 허공을 응시하며 서 있는 모습
★ 선정
A — Gemini 7점
레퍼런스의 복장(모자 포함)과 장소를 정확히 재현했으며, 허공을 응시하는 멍한 시선 처리가 지시문과 가장 잘 부합합니다.
B — Gemini 4점
장소와 인물의 자세는 잘 구현되었으나, 캐릭터 레퍼런스에 있는 모자가 누락되어 감점되었습니다.
C — Gemini 6점
캐릭터의 외형과 배경은 잘 일치하지만, 카메라 렌즈를 정면으로 바라보고 있어 '허공을 응시하는' 지시문의 묘사가 다소 약합니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (2장)
LOCATION PHOTOGRAPH — the exact place of this shot
bg_S13sh4_sel.png
CHARACTER REFERENCE — 수리영
39864973-d3d5-4886-bfb2-f8db608a005b.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 수리영이 초점을 잃은 눈으로 허공을 응시하며 서 있는 모습

LOCATION (lock): A confined ground-level alley and small courtyard beside an aging multi-unit residential building. Concrete walls, building entrances, and the base of the exterior access structure frame the space. 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.

MOVEMENT (follow exactly): static: Su-ri-young stands motionless and dazed after coming down from the rooftop room, her unfocused eyes staring into empty space and her body lacking purposeful direction.

FIGURES — size & depth (follow exactly): Su-ri-young is the only visible figure, so she is both the nearest and farthest person; her apparent fraction of frame height is unspecified in the source.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (Korean young woman, early 20s face, oval face, natural black long hair) — 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.

S13sh6 플레이트+prev+엔티티 (prev=S13sh4) — 랭킹 B>A>C

prev 사용 지시: Take the confined courtyard's concrete surfaces, building entrances, access structure, and nighttime emergency ambience from the reference. Preserve the young woman's standing position in the same ground-level area. Exclude her earlier vacant stare and empty-air eyeline; frame her now looking up at the approaching woman.
고개를 든 채 혜수의 얼굴을 마주보고 있는 수리영의 측면 구도
A — Gemini 5점
이전 컷의 소품 배치는 잘 유지했으나, 절대 복사하지 말라는 이전 컷의 카메라 프레이밍을 그대로 차용했고 수리영이 올려다보는 느낌이 다소 부족합니다.
★ 선정
B — Gemini 7점
프레이밍 복사 금지 지시를 준수하고 명시적으로 허용된 원근감의 자유도를 활용하여, 수리영이 올려다보는 측면 구도를 가장 지시문에 맞게 연출했습니다.
C — Gemini 4점
프레이밍 복사 금지를 어기고 위치 레퍼런스의 구도를 답습했을 뿐만 아니라, 이전 컷에서 확립된 소품 배치를 무시하고 레퍼런스의 화분들을 그대로 가져와 연속성을 훼손했습니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 B)
수정 후 (i2i, 최종)
참조 (4장)
LOCATION PHOTOGRAPH — the exact place of this shot
bg_S13sh6_sel.png
PREVIOUS SHOT STILL — a visually related earlier shot of this same pla
S13sh4_sel.png
CHARACTER REFERENCE — 수리영
39864973-d3d5-4886-bfb2-f8db608a005b.png
CHARACTER REFERENCE — 혜수
bddad176-aa6a-4a71-b5d3-d02e36e19657.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 고개를 든 채 혜수의 얼굴을 마주보고 있는 수리영의 측면 구도

LOCATION (lock): A confined ground-level alley and small courtyard beside an aging multi-unit residential building. Concrete walls, building entrances, and the base of the exterior access structure frame the space. 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 confined courtyard's concrete surfaces, building entrances, access structure, and nighttime emergency ambience from the reference. Preserve the young woman's standing position in the same ground-level area. Exclude her earlier vacant stare and empty-air eyeline; frame her now looking up at the approaching woman.

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.

MOVEMENT (follow exactly): static: Su-ri-young holds her head raised and faces Hye-su directly in side profile, looking up at her while remaining dazed and stationary.

FIGURES — size & depth (follow exactly): Su-ri-young and Hye-su's face are visible facing each other, but their respective frame-height fractions and which is nearer to the camera are unspecified; their paths have converged at conversational distance, with neither moving past the other.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (Korean young woman, early 20s face, oval face, natural black long hair); 혜수 (Korean middle-aged woman, mid-40s face, mature facial features, dark natural hair) — 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.

옥탑방 내부 (rooftop_room_interior)

LOCATION lock: A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls.

S5sh5 플레이트+엔티티 — 랭킹 C>B>A

다급하게 상체를 기울이며 손가락 끝으로 TV 전원 버튼을 세게 누르고 있는 민숙의 측면 구도
A — Gemini 3점
요구된 원근법 구도를 따르지 않았고 손목 자국이 너무 크게 묘사되었으며, 불필요한 인물이 뚜렷하게 등장하여 가장 낮게 평가되었습니다.
B — Gemini 4점
손목 자국 형태는 준수하나 카메라와 피사체 간의 원근법이 반대로 표현되었고, 지시문에 없는 인물이 명확히 추가되어 지침을 위반했습니다.
★ 선정
C — Gemini 7점
카메라에 더 가까운 손과 TV의 원근 구도를 유일하게 구현하고 손목 자국도 지침에 맞으나, 배경에 지시문에 없는 인물 일부가 등장해 감점되었습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (2장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_living_dining_day_root_sel.png
CHARACTER REFERENCE — 민숙
899945af-f9bf-4880-bdd7-c9d1f45a5327.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): interior ambient light.

SHOT TEXT (authoritative, Korean): 다급하게 상체를 기울이며 손가락 끝으로 TV 전원 버튼을 세게 누르고 있는 민숙의 측면 구도

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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.

MOVEMENT (follow exactly): Min-sook urgently pitches her upper body forward toward the TV and forcefully drives a fingertip into its power button to turn it off as Su-ri-young emerges from her room.

FIGURES — size & depth (follow exactly): Min-sook's side-view upper body fills roughly 2/3 of the frame height, with her reaching hand and the TV button NEARER to the camera than her face and torso. The TV is FARTHER along her forward reach, and her body closes the short distance toward it.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk remains in her apron, with the same small circular mark on her wrist; the mark must already be present here because she has had it since childhood.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (Korean middle-aged woman, early-40s face, soft mature features, natural dark hair) — 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.

S5sh9 플레이트+prev+엔티티 (prev=S5sh5) — 랭킹 A>B>C

prev 사용 지시: Take the cramped living area's worn materials, daylight, and the woman's apron and position from the reference. Preserve the continuity of her wrist and its small circular mark. Exclude the TV-button-pressing action and any wider room elements that fall outside this tight wrist framing.
민숙의 손목에 선명하게 드러난 작은 원형 표식의 타이트 샷
★ 선정
A — Gemini 7점
타이트한 샷으로 손목의 표식을 선명하게 보여주며, 이전 샷의 기울인 자세와 의상 연속성을 가장 잘 유지했습니다.
B — Gemini 5점
손목 표식과 프레이밍은 적절하나, 레퍼런스에 지정된 몸을 기울인 자세 대신 똑바로 서 있어 연속성 지시를 어겼습니다.
C — Gemini 3점
배경에 분절된 의상과 추가 인물 형상이 나타나 단일 캐릭터 조건 및 샷의 연속성을 심각하게 훼손했습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (3장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_living_dining_day_root_sel.png
PREVIOUS SHOT STILL — a visually related earlier shot of this same pla
S5sh5_sel.png
CHARACTER REFERENCE — 민숙
899945af-f9bf-4880-bdd7-c9d1f45a5327.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): interior ambient light.

SHOT TEXT (authoritative, Korean): 민숙의 손목에 선명하게 드러난 작은 원형 표식의 타이트 샷

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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 living area's worn materials, daylight, and the woman's apron and position from the reference. Preserve the continuity of her wrist and its small circular mark. Exclude the TV-button-pressing action and any wider room elements that fall outside this tight wrist 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.

MOVEMENT (follow exactly): static: Min-sook's wrist is held in view, with the sharply visible small circular mark facing the camera.

FIGURES — size & depth (follow exactly): The wrist fills most of the tight frame, while the circular mark occupies a small area at its center. The skin and mark are the NEAREST and only principal subject, with any body or room detail FARTHER and out of focus.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The TV remains switched off, and Minsuk still wears the apron. The small, unusually distinct 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 (Korean middle-aged woman, early-40s face, soft mature features, natural dark hair) — 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.

S12sh11 플레이트+엔티티 — 랭킹 B>A>C

옷과 피부가 피투성이가 된 민숙이 바닥에 주저앉아 고개를 푹 숙인 정지 상태
A — Gemini 5점
무력한 자세와 구도는 잘 표현되었으나, 침대 위 창문 등 고정된 배경 구조가 레퍼런스와 다르게 왜곡되었습니다.
★ 선정
B — Gemini 7점
고개를 숙인 정지 상태의 자세와 2/3 프레이밍을 정확히 구현했으며, 배경의 핵심 건축 요소들을 충실히 유지했습니다.
C — Gemini 4점
배경은 완벽히 일치하지만, 캐릭터가 능동적인 자세를 취하고 있으며 화면에서 차지하는 비율이 지시보다 작습니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 B)
수정 후 (i2i, 최종)
참조 (2장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_daughter_bedroom_night_doorway_wide_sel.png
CHARACTER REFERENCE — 민숙 (환시)
1d7902d5-8b31-4ab6-9e6a-5da6ab5d842f.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 옷과 피부가 힘없이 무너져 미동이 없는 민숙이 바닥에 주저앉아 고개를 푹 숙인 정지 상태

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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-sook is seated collapsed on the floor behind the curtain with her head dropped forward. One hand is clenched around a crumpled photograph.

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.

MOVEMENT (follow exactly): static: utterly motionless, collapsed Min-sook is seated collapsed on the floor behind the curtain with her head dropped forward, shoulders fallen, limbs limp, and body weight fully given way.

FIGURES — size & depth (follow exactly): Min-sook's dark stains-covered body fills about 2/3 of the frame height and is the NEAREST principal figure. The floor directly beneath her is nearer than the surrounding bedroom and curtain area, which recede FARTHER behind her.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Min-sook remains dead behind the curtain, seated collapsed on the floor with her head dropped forward, her torn shoulder and collarbone exposed amid the dark stains and dark-stained footprints. One hand is clenched around a crumpled photograph, 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: 민숙 (환시) — 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.

S12sh18 플레이트+prev+엔티티 (prev=S12sh11) — 랭킹 C>B>A

prev 사용 지시: Take the bedroom's dim nighttime look and the seated woman's fixed body, clothing, and hand position from the reference. Preserve the bloodied condition and the crumpled photograph held in her hand. Exclude the wider view of her body, wounds, bed, and curtain from this tight photograph insert.
민숙의 손에 꽉 쥐어진 구겨진 사진의 타이트 샷
A — Gemini 3점
이전 샷과 일치하지 않는 긴소매 의상을 입고 있으며, 손의 방향과 쥐고 있는 방식이 레퍼런스와 전혀 다릅니다.
B — Gemini 4점
손을 바닥에서 들어 올린 자세로 변경되어 고정된 자세 지침을 위반했고, 타이트 샷임에도 배경이 너무 넓게 보입니다.
★ 선정
C — Gemini 7점
레퍼런스의 바닥에 놓인 손 자세, 손목의 멍 자국, 의상, 구겨진 사진을 가장 정확하게 연속성 있게 유지한 타이트 샷입니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (4장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_daughter_bedroom_night_doorway_wide_sel.png
PREVIOUS SHOT STILL — a visually related earlier shot of this same pla
S12sh11_sel.png
CHARACTER REFERENCE — 민숙 (환시)
1d7902d5-8b31-4ab6-9e6a-5da6ab5d842f.png
PROP REFERENCE — 구겨진 피 묻은 낡은 흑백 사진
fc23070d-a644-45e4-a5d8-ecb98fe8d2d3.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 민숙의 손에 꽉 쥐어진 구겨진 사진의 타이트 샷

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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 bedroom's dim nighttime look and the seated woman's fixed body, clothing, and hand position from the reference. Preserve the dark-stained condition and the crumpled photograph held in her hand. Exclude the wider view of her body, wounds, bed, and curtain from this tight photograph insert.

IMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Min-sook is seated collapsed on the floor behind the curtain with her head dropped forward. One hand is clenched around a crumpled photograph.

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.

MOVEMENT (follow exactly): static: utterly motionless, collapsed Min-sook's hand remains clenched around a crumpled photograph, with the photograph exposed toward the camera.

FIGURES — size & depth (follow exactly): The dead woman's hand fills roughly 2/3 of the tight frame, and the crumpled photograph fills about 1/3. The photograph is NEARER where it protrudes from her grasp, while her palm, wrist, and collapsed body are progressively FARTHER behind it.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk remains seated collapsed on the floor behind the curtain with her head dropped forward, with the wounds and dark stains undisturbed. The crumpled photograph stays clenched in her hand until Suri-young pulls it free, as the circular wrist mark turns red.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 민숙 (환시) — 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.

S12sh21 플레이트만 (배경 전용) — 랭킹 C>A>B

침대 위쪽 벽면에 붉은색 원형 표식이 절반쯤 나타난 상태
A — Gemini 5점
인물 배제 조건은 충족했으나, 붉은 원이 절반이 아닌 거의 완성된 형태로 그려져 묘사에 어긋납니다.
B — Gemini 3점
텍스트에 명시되지 않은 한 인물이 없어야 한다는 강력한 지침을 위반하고 침대에 사람을 등장시켰습니다.
★ 선정
C — Gemini 7점
지시문대로 프레임 내 인물을 배제하고, 벽면에 절반만 그려진 붉은 원을 정확하게 연출했습니다.
✔ Gemini 결함 검사: 0건 — 선정본 그대로 사용
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_daughter_bedroom_night_doorway_wide_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 침대 위쪽 벽면에 붉은색 원형 표식이 절반쯤 나타난 상태

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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.

MOVEMENT (follow exactly): A red circular mark spreads around the wall above the bed, progressing along a ring-like path as though an unseen brush is drawing it, with about half the circle formed.

FIGURES — size & depth (follow exactly): The half-formed red circle fills roughly 1/2 of the frame height on the wall and is the principal visible object. The wall surface and mark are FARTHER than the nearer edge of the bed, with the red pigment visually sitting closest on that wall plane.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Minsuk’s motionless figure, wounds, and the room’s dark stains traces remain unchanged; her hand is now without the photograph, which Suri-young has taken, and the wrist mark is red. A red circle is partially formed 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.

S14sh5 플레이트만 (배경 전용) — 랭킹 C>B>A

핏자국 없이 깨끗한 방 내부 전경
A — Gemini 3점
'비정상적으로 깨끗한'이라는 지시와 달리 문과 벽에 때가 타 있고 천장 조명에 붉은 자국이 남아 있습니다.
B — Gemini 5점
방은 깨끗하게 묘사되었으나 프롬프트에 언급되지 않은 두 번째 인형이 우측 하단에 추가되었습니다.
★ 선정
C — Gemini 7점
백팩과 인형의 위치를 원본과 다르게 배치했으며, 지시대로 얼룩 없이 매우 깨끗한 방의 상태를 가장 잘 구현했습니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_daughter_bedroom_night_doorway_wide_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 어두운 얼룩 없이 깨끗한 방 내부 전경

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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.

MOVEMENT (follow exactly): static: the excessively tidy bedroom stands empty, with no dark stainsstains, red wall mark, or collapsed body remaining anywhere in the room.

FIGURES — size & depth (follow exactly): The empty room fills the full frame; nearer floor and furniture edges occupy the foreground, while the bed, curtain, and clean back wall are FARTHER away. No person is visible, and the formerly occupied curtain area is now empty.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The room is unnaturally spotless, with no dark stains, wall circle, or motionless figure behind the curtain. The backpack and doll are present in positions slightly different from when the body was discovered.

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.

S14sh7 플레이트+prev+엔티티 (prev=S14sh5) — 랭킹 B>A>C

prev 사용 지시: Take the spotless bedroom layout, fixed furnishings, worn surfaces, and nighttime lighting from the reference. Keep the room free of blood, a body, and the red wall mark. Exclude the wide empty-room composition from the close-up, showing only as much background as supports the woman's stunned gaze.
수리영이 멍한 눈으로 텅 빈 방 안을 응시하는 얼굴 클로즈업
A — Gemini 5점
인물의 표정과 프레이밍은 적절하나, 레퍼런스에 없던 침대 옆 조명이 추가되었고 유지되어야 할 배낭이 누락되었습니다.
★ 선정
B — Gemini 7점
정상적인 눈동자로 멍한 표정을 잘 연출했으며, 배경에 이전 샷의 배낭 위치를 정확히 유지하여 지침을 가장 충실히 따랐습니다.
C — Gemini 3점
배경의 배낭은 유지했으나, '해부학적으로 정상적인 인간의 눈'이어야 한다는 핵심 지시를 무시하고 눈동자를 하얗게 변형했습니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 B)
수정 후 (i2i, 최종)
참조 (3장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_daughter_bedroom_night_doorway_wide_sel.png
PREVIOUS SHOT STILL — a visually related earlier shot of this same pla
S14sh5_sel.png
CHARACTER REFERENCE — 수리영
39864973-d3d5-4886-bfb2-f8db608a005b.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 수리영이 멍한 눈으로 텅 빈 방 안을 응시하는 얼굴 클로즈업

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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 layout, fixed furnishings, worn surfaces, and nighttime lighting from the reference. Keep the room free of dark stains, a body, and the red wall mark. Exclude the wide empty-room composition from the close-up, showing only as much background as supports the woman's stunned 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.

MOVEMENT (follow exactly): static: pale-faced Su-ri-young holds her body rigid and stares blankly into the empty bedroom where she expected to find her mother's body.

FIGURES — size & depth (follow exactly): Su-ri-young's face fills about 2/3 of the frame height and is the NEAREST figure. The empty room she watches is FARTHER beyond her eyeline, with no other person visible.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The empty room remains excessively clean, with the motionless figure, dark stains, and red wall mark still absent. The backpack and doll remain in their altered positions.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (Korean young woman, early 20s face, oval face, natural black long hair) — 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.

S14sh11 플레이트+엔티티 — 랭킹 C>A>B

혜수가 날카로운 눈빛으로 김형사를 노려보는 모습
A — Gemini 5점
프레이밍과 배경 및 소품 배치는 지시문을 충실히 따랐으나, 캐릭터 레퍼런스에 있는 비니가 누락되었습니다.
B — Gemini 3점
혜수가 화면에서 가장 가까운 인물이어야 한다는 명시적인 크기 및 깊이 지시를 어기고 김 형사를 전면에 배치했습니다.
★ 선정
C — Gemini 8점
혜수가 가장 가까운 인물이어야 한다는 거리감 지시를 잘 따랐으며, 캐릭터 레퍼런스의 의상(비니 포함)과 소품 배치까지 완벽히 구현했습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (2장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_entry_night_inward_view_sel.png
CHARACTER REFERENCE — 혜수
bddad176-aa6a-4a71-b5d3-d02e36e19657.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): night.

SHOT TEXT (authoritative, Korean): 혜수가 날카로운 눈빛으로 김형사를 노려보는 모습

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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.

MOVEMENT (follow exactly): static: Hye-su fixes a sharp, hostile stare toward Detective Kim, her face and body oriented directly at him.

FIGURES — size & depth (follow exactly): Hye-su fills roughly 2/3 of the frame height and is the NEAREST visible figure. Detective Kim is the FARTHER target of her gaze, whether at the edge of the frame or just off-screen, with no crossing movement between them.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The apartment remains cleared of the earlier evidence: the table is clean, and Suri-young’s room has no motionless figure, dark stains, or red circle. The backpack and doll remain slightly displaced from their earlier positions.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 혜수 (Korean middle-aged woman, mid-40s face, mature facial features, dark natural hair) — 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.

S18sh11 플레이트만 (배경 전용) — 랭킹 A>B>C

거울 속 반사된 욕실 타일 벽면에 붉은색 원형 표식이 절반쯤 나타난 상태
★ 선정
A — Gemini 7점
원이 완전히 반원 형태는 아니지만 세 후보 중 가장 불완전하게 그려져 '절반쯤 나타난 상태'에 가장 근접하며, 거울 높이 대비 원의 크기(약 1/2)도 잘 맞췄습니다.
B — Gemini 5점
원형 표식이 거의 이어져 있어 '절반쯤 나타난 상태'라는 진행형의 묘사를 제대로 반영하지 못했습니다.
C — Gemini 4점
원이 완전히 닫힌 채로 크게 그려져 지시된 형태 및 크기 비율을 전혀 충족하지 않습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_bathroom_day_mirror_tile_view_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): daytime.

SHOT TEXT (authoritative, Korean): 거울 속 반사된 욕실 타일 벽면에 붉은색 원형 표식이 절반쯤 나타난 상태

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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.

MOVEMENT (follow exactly): A red circular mark suddenly develops across the bathroom tile wall seen in the mirror, extending around a ring-like path until roughly half is visible.

FIGURES — size & depth (follow exactly): The mirror and reflected tiled wall fill most of the frame, while the half-formed red circle occupies about 1/2 of the reflected frame height. The mirror surface is physically NEARER to the camera, while the marked bathroom wall appears FARTHER within the reflection.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Suri-young continues to have her doll-adorned backpack with her, while her bedroom remains clean and without a motionless figure. A red circle is partially visible on the bathroom wall only in the mirror reflection.

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.

S18sh15 플레이트만 (배경 전용) — 랭킹 C>A>B

액자 속 민숙의 얼굴 부분 이미지가 아래로 일그러지며 흘러내리는 찰나
A — Gemini 5점
지정된 장소의 배경은 잘 구현되었으나, 사진의 이미지가 액자 유리를 뚫고 테이블 위로 흘러나와 유리 아래에 있어야 한다는 조건에 위배됩니다.
B — Gemini 4점
이미지가 액자 밖으로 입체적으로 흘러나와 깊이 조건에 어긋나며, 지정된 장소의 고유한 특징도 배경에서 잘 드러나지 않습니다.
★ 선정
C — Gemini 7점
유리에 비친 반사면 뒤로 사진 속 얼굴이 일그러져 흘러내리는 모습을 정확히 묘사하여 프롬프트가 요구한 표면 아래의 깊이감을 완벽히 구현했습니다.
✔ Gemini 결함 검사: 0건 — 선정본 그대로 사용
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_living_dining_day_root_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): daytime.

SHOT TEXT (authoritative, Korean): 액자 속 민숙의 얼굴 부분 이미지가 아래로 일그러지며 흘러내리는 찰나

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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.

MOVEMENT (follow exactly): The image of Min-sook's smiling face inside the framed photograph distorts and flows downward before Su-ri-young's eyes.

FIGURES — size & depth (follow exactly): The framed photograph fills most of the close frame, and Min-sook's pictured face occupies roughly 1/2 of its height. The photograph's glass and frame are NEARER to the camera, while the collapsing facial image is visually FARTHER beneath the surface.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The bathroom’s red circle has vanished, and Suri-young still has the doll-adorned backpack. The framed photograph remains on the table as Minsuk’s face in it distorts and runs downward.

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.

S18sh16 플레이트+prev+엔티티 (prev=S5sh5) — 랭킹 A>B>C

prev 사용 지시: Take the same worn living-room materials, small-window daylight, sparse furnishings, and established room layout from the reference. Use only the background continuity and place the distressed young woman within that space. Exclude the apron-wearing woman and the earlier TV-button-pressing action, and do not reproduce the distorted photograph as the main subject.
수리영이 두 손으로 머리를 감싸 쥐고 입을 크게 벌린 얼굴
★ 선정
A — Gemini 7점
얼굴과 손이 화면의 3/4을 차지하는 프레임 비율을 잘 맞췄으며, 필수 요소인 인형이 달린 배낭까지 화면에 포함하여 지시문을 가장 충실히 이행했습니다.
B — Gemini 5점
클로즈업 프레임과 겁에 질린 표정 연기는 매우 훌륭하지만, 반드시 착용하고 있어야 할 인형 장식 배낭이 완전히 누락되었습니다.
C — Gemini 4점
인형 배낭과 장소의 디테일은 정확하게 묘사했으나, 얼굴과 손이 화면의 3/4을 채워야 한다는 프레임 크기 지시를 완전히 위반하여 피사체가 너무 작게 잡혔습니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (3장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_living_dining_day_root_sel.png
PREVIOUS SHOT STILL — a visually related earlier shot of this same pla
S5sh5_sel.png
CHARACTER REFERENCE — 수리영
39864973-d3d5-4886-bfb2-f8db608a005b.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): daytime.

SHOT TEXT (authoritative, Korean): 수리영이 두 손으로 머리를 감싸 쥐고 입을 크게 벌린 얼굴

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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 same worn living-room materials, small-window daylight, sparse furnishings, and established room layout from the reference. Use only the background continuity and place the distressed young woman within that space. Exclude the apron-wearing woman and the earlier TV-button-pressing action, and do not reproduce the distorted photograph as the main subject.

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.

MOVEMENT (follow exactly): static: terrified and overwhelmed, Su-ri-young clamps both hands around her head and holds her mouth wide open in a scream, her posture rigid with panic.

FIGURES — size & depth (follow exactly): Su-ri-young's face and hands fill about 3/4 of the frame height and form the NEAREST subject. Her hands sit slightly NEARER than her face on either side, while the room behind her is FARTHER and secondary.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The framed photograph remains on the table but has returned to normal, and the bathroom wall remains without the red circle. Suri-young still has the doll-adorned backpack 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 (Korean young woman, early 20s face, oval face, natural black long hair) — 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.

S25sh1 플레이트만 (배경 전용) — 랭킹 C>A>B

해질 무렵 옥탑방 거실, 흙 묻은 발자국들이 찍힌 바닥과 쓰러진 식탁 의자들이 보이는 전경
A — Gemini 5점
거실 창문이 닫혀 있으며, 침실 벽의 붉은 원이 거대한 단색 페인트 칠처럼 부자연스럽게 묘사되었습니다.
B — Gemini 3점
침실 쪽 붉은 원이 인위적인 그래픽 어노테이션처럼 추가되어 어떠한 주석도 금지한 지시사항을 위반했습니다.
★ 선정
C — Gemini 7점
벽에 그려진 붉은 원과 핀으로 고정된 사진이 사실적이며, 열린 창문과 진흙 발자국의 원근감이 프롬프트의 지시를 잘 따랐습니다.
⚠ Gemini 결함 2건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 C)
수정 후 (i2i, 최종)
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_living_dining_sunset_floor_view_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, just after sunset.

SHOT TEXT (authoritative, Korean): 해질 무렵 옥탑방 거실, 흙 묻은 발자국들이 찍힌 바닥과 쓰러진 식탁 의자들이 보이는 전경

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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.

MOVEMENT (follow exactly): static: muddy footprints remain across the ransacked living-room floor among overturned dining chairs, indicating a prior path through the room but no current movement.

FIGURES — size & depth (follow exactly): The footprint-marked floor fills the lower half of the wide frame, with the NEAREST prints and fallen chair parts in the foreground appearing larger. Additional prints, the dining area, and the open living-room window recede FARTHER into the room.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The apartment remains ransacked, with dirty footprints on the floor, the living-room window open, and the dining chairs overturned. The red circle and the stained old photograph pinned at its center are already present in Suri-young’s room.

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.

S25sh5 플레이트만 (배경 전용) — 랭킹 B>A>C

붉은 원 한가운데 피 묻은 낡은 흑백 사진이 벽에 꽂혀 있는 타이트 샷
A — Gemini 4점
어질러진 방의 상태는 배경에 묘사되었으나, 사진과 붉은 원이 침실 벽이 아닌 허공에 떠 있는 CG 그래픽처럼 잘못 표현되었습니다.
★ 선정
B — Gemini 7점
지시된 타이트 샷의 구도를 완벽히 따랐으며, 붉은 원과 사진이 허공이 아닌 실제 벽면에 물리적으로 존재하는 모습을 정확히 구현했습니다.
C — Gemini 3점
사진과 붉은 원이 허공에 떠 있을 뿐만 아니라, 지시된 방의 어질러진 상태(넘어진 의자 등)도 전혀 반영되지 않았습니다.
✔ Gemini 결함 검사: 0건 — 선정본 그대로 사용
참조 (1장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_daughter_bedroom_sunset_bed_wall_sel.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, just after sunset.

SHOT TEXT (authoritative, Korean): 붉은 원 한가운데 얼룩진 낡은 흑백 사진이 벽에 꽂혀 있는 타이트 샷

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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.

MOVEMENT (follow exactly): static: a stained old photograph remains pinned at the center of the red circle on Su-ri-young's bedroom wall, facing outward toward the camera.

FIGURES — size & depth (follow exactly): The photograph fills roughly 1/3 of the tight frame height, while the surrounding red circle occupies most of the frame. The photograph projects NEARER from the wall, and the red mark lies FARTHER against the flat wall surface behind it.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The dirty footprints, ransacked furnishings, open window, and overturned chairs remain undisturbed. In the bedroom, the stained old photograph is still pinned at the center of the red wall circle.

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.

S25sh9 플레이트+prev+엔티티 (prev=S25sh5) — 랭킹 A>B>C

prev 사용 지시: Take the worn bedroom wall texture, sunset illumination, and the continuing red circle from the reference. Preserve the same bloodstained old photograph after it has been pulled from the wall. Exclude the pinning position and empty the center of the wall mark; focus instead on the hand tightly gripping the photograph.
수리영의 손이 구겨진 사진을 꽉 움켜쥔 타이트 샷
★ 선정
A — Gemini 7점
캐릭터의 긴팔 의상과 붉은 원 배경, 타이트 샷 규정을 잘 따랐으나, 손가락 관절(knuckles)이 카메라에 더 가깝게 향해야 한다는 디테일을 놓쳤습니다.
B — Gemini 5점
손가락 관절 방향은 프롬프트와 일치하지만, 지정된 긴팔 의상이 누락되어 맨팔이 드러났으며 벽에 핀 자국이 남아있습니다.
C — Gemini 3점
타이트 샷이 아닌 너무 넓은 화각으로 촬영되어 손과 사진이 프레임을 채우는 비율 규정을 크게 위반했습니다.
⚠ Gemini 결함 3건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 A)
수정 후 (i2i, 최종)
참조 (4장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_daughter_bedroom_sunset_bed_wall_sel.png
PREVIOUS SHOT STILL — a visually related earlier shot of this same pla
S25sh5_sel.png
CHARACTER REFERENCE — 수리영
39864973-d3d5-4886-bfb2-f8db608a005b.png
PROP REFERENCE — 구겨진 피 묻은 낡은 흑백 사진
fc23070d-a644-45e4-a5d8-ecb98fe8d2d3.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, just after sunset.

SHOT TEXT (authoritative, Korean): 수리영의 손이 구겨진 사진을 꽉 움켜쥔 타이트 샷

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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 worn bedroom wall texture, sunset illumination, and the continuing red circle from the reference. Preserve the same stained old photograph after it has been pulled from the wall. Exclude the pinning position and empty the center of the wall mark; focus instead on the hand tightly gripping the photograph.

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.

MOVEMENT (follow exactly): static: Su-ri-young's tense hand crushes the crumpled photograph in a tight grip as she holds it close.

FIGURES — size & depth (follow exactly): Su-ri-young's hand fills roughly 2/3 of the tight frame, and the exposed portion of the photograph fills about 1/3. Her knuckles are NEARER to the camera, while the photograph is partly FARTHER inside her closed fingers.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The apartment remains ransacked, and the red wall circle remains after the photograph has been removed from its center. Suri-young tightly grips the same crumpled, stained photograph.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (Korean young woman, early 20s face, oval face, natural black long hair) — 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.

S27sh3 플레이트+prev+엔티티 (prev=S25sh1) — 랭킹 B>C>A

prev 사용 지시: Take the ransacked living area's worn materials, sunset light, open-window condition, muddy footprints, and overturned chairs from the reference as continuing environmental state. Place the middle-aged woman with her smartphone within that same room. Exclude the earlier empty wide-floor emphasis, and do not add the young woman, her backpack, or the bloodstained photograph to this close-up.
혜수가 미간을 깊게 찌푸린 채 스마트폰을 내려다보는 얼굴 클로즈업
A — Gemini 3점
폰을 귀에 대고 있어 시선 지시와 불일치하며, 불필요한 텍스트가 화면에 노출되었습니다.
★ 선정
B — Gemini 7점
스마트폰의 기능적 방향(화면이 인물을 향함), 표정, 배경 및 '텍스트 없음' 제약을 완벽히 준수했습니다.
C — Gemini 5점
스마트폰 화면이 카메라를 향해 시선 구조가 어긋나며, 화면에 금지된 텍스트가 포함되었습니다.
⚠ Gemini 결함 1건 → nb2 i2i 수정본이 최종 선정본(체인 앵커)
수정 전 (선정 원본 B)
수정 후 (i2i, 최종)
참조 (3장)
LOCATION PHOTOGRAPH — the exact place of this shot
plate_living_dining_sunset_floor_view_sel.png
PREVIOUS SHOT STILL — a visually related earlier shot of this same pla
S25sh1_sel.png
CHARACTER REFERENCE — 혜수
bddad176-aa6a-4a71-b5d3-d02e36e19657.png
프롬프트 전문
Create ONE FINAL photorealistic live-action film still of the moment below — contemporary South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk, just after sunset.

SHOT TEXT (authoritative, Korean): 혜수가 미간을 깊게 찌푸린 채 스마트폰을 내려다보는 얼굴 클로즈업

LOCATION (lock): A cramped, aging rooftop residence with a small living area, bedroom wall, sparse furniture, and a compact tiled bathroom. Fixed features include the metal entrance door, a window, a bed, and worn interior walls. 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 area's worn materials, sunset light, open-window condition, muddy footprints, and overturned chairs from the reference as continuing environmental state. Place the middle-aged woman with her smartphone within that same room. Exclude the earlier empty wide-floor emphasis, and do not add the young woman, her backpack, or the stained photograph to this 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.

MOVEMENT (follow exactly): static: Hye-su lowers her gaze toward the smartphone and listens to Su-ri-young's recorded message with her brow deeply furrowed.

FIGURES — size & depth (follow exactly): Hye-su's face fills about 2/3 of the close-up frame, while the smartphone occupies a smaller area below her face. The phone is NEARER to the camera, Hye-su's face is slightly FARTHER, and the room behind her is farthest.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): The apartment remains ransacked, with the footprints, open window, overturned chairs, and the now-empty red wall circle left in place; Suri-young has departed with the photograph and backpack. Hyesu holds the smartphone on which she is checking Suri-young’s recorded 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 (Korean middle-aged woman, mid-40s face, mature facial features, dark natural hair) — 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.