s39 — 옥탑 23샷: 콘티 제외·참조 1장 + 3롤 Gemini VLM 단독 선정 (prev 8 / 플레이트 15)

사용자 확정 규칙: ①콘티 제외 — 참조는 단 한 장: prev 판정 v3(배경 동일성 유일 기준, s38 재사용)가 prev 를 주면 이전 샷 선정본 / 아니면 배경 플레이트. ②샷당 nb2 3롤(A/B/C)★Gemini VLM 단독이 프롬프트 (+참조 일관성) 충실도 0-10 판정 → 최고점 선정(동점=Gemini 랭킹). GPT 판정은 사용자 지시로 평가에서 제외. ③선정본(초록 테두리+★)이 후속 샷의 prev 앵커(스토리 순서 체인). 자세 정본·carried state· EXPRESSION_REALISM 텍스트 안전망 유지. 이전 판: s38 갤러리

★ 선정본 모아보기 (Gemini 점수 단독, 23샷)

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

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 배경 플레이트 — Gemini winner=B 랭킹=B>A>C

맑은 낮, 오래된 다세대 빌라 옥상 위에 자리 잡은 옥탑방을 높은 곳에서 내려다본 부감 구도
A — Gemini 4점
레퍼런스 이미지의 카메라 구도를 그대로 복사하지 말라는 명시적 지시를 위반했습니다.
★ 선정
B — Gemini 7점
레퍼런스 구도를 피하고 전경에 다른 지붕을 배치하여 요구된 원경의 부감 구도와 피사체 크기를 정확히 구현했습니다.
C — Gemini 4점
지시사항을 무시하고 레퍼런스 이미지의 프레이밍과 거리를 그대로 답습했습니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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 appear unless the shot text itself says so.

No text, captions, watermarks or annotations anywhere.

S10sh6 배경 플레이트 — Gemini winner=A 랭킹=A>C>B

현관 철문이 아주 살짝 열린 틈새로 보이는 어두운 실내와 신발 앞코
★ 선정
A — Gemini 7점
약간 열린 문틈으로 어두운 실내를 향해 들어가는 신발 앞코와 다리를 정확히 묘사하여 지시문을 잘 따랐습니다.
B — Gemini 3점
인체가 아닌 빈 신발만 바닥에 놓여 있어 살아있는 사람으로 표현하라는 지시를 크게 위반했습니다.
C — Gemini 5점
신발과 다리가 묘사되었으나 실내가 아닌 밖을 향하고 있어 이동 방향 지시와 어긋납니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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 appear unless the shot text itself says so.

No text, captions, watermarks or annotations anywhere.

S10sh7 배경 전용 샷 → 플레이트 강제 — Gemini winner=C 랭킹=C>A>B

불이 켜진 옥탑방 창문에 거대한 그림자가 작은 그림자의 어깨 쪽으로 고개를 꺾은 형태가 맺혀 있는 정지 구도
A — Gemini 4점
레퍼런스 이미지의 광각 구도를 그대로 답습하여 지시를 어겼으며, 묘사된 두 그림자의 크기 차이가 지문만큼 극명하지 않습니다.
B — Gemini 3점
역시 레퍼런스의 구도를 복사하는 오류를 범했으며, 그림자가 프레임을 차지하는 비율과 크기 대비 조건이 제대로 반영되지 않았습니다.
★ 선정
C — Gemini 7점
레퍼런스의 카메라 구도를 복사하지 말라는 지시를 잘 따랐으며, 창문에 맺힌 거대한 그림자와 작은 그림자의 크기 대비 및 동작이 가장 정확히 묘사되었습니다.
참조 (1장) — 배경 플레이트 (★배경 전용 샷 — prev 무시)
LOCATION PHOTOGRAPH
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 appear unless the shot text itself says so.

No text, captions, watermarks or annotations anywhere.

S11sh5 prev=S10sh6 — Gemini winner=A 랭킹=A>B>C

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
★ 선정
A — Gemini 7점
인물이 문을 향하는 자세와 크기/깊이 구도 지시를 가장 잘 따랐으나, 문의 개폐 방향이 레퍼런스와 다름.
B — Gemini 5점
레퍼런스의 문 구조(바깥으로 열림)는 일치하나, 인물이 문이 아닌 카메라를 응시하여 시선 지시를 위반함.
C — Gemini 4점
인물의 시선이 문을 향하지 않으며, 문의 구조와 안으로 열리는 방향도 레퍼런스와 불일치함.
참조 (1장) — prev 선택본
PREVIOUS SHOT STILL
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.

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 — never anyone else, and never add a person the shot text does not show.

No text, captions, watermarks or annotations anywhere.

S17sh2 배경 플레이트 — Gemini winner=C 랭킹=C>B>A

옥상 담벼락 위에서 한쪽 앞발을 허공으로 뻗은 검은 고양이의 측면
A — Gemini 3점
고양이의 자세가 공간적으로 어색하게 떠 있으며, 담벼락을 가로지르는 움직임이 물리적으로 자연스럽게 구현되지 않았습니다.
B — Gemini 5점
고양이가 앞발을 뻗고 있으나, 담벼락을 가로지르지 않고 위를 따라 걷고 있어 동선 지시(across and over)와 어긋납니다.
★ 선정
C — Gemini 7점
고양이가 담벼락을 가로지르며 한쪽 앞발을 허공으로 뻗는 측면의 모습을 정확히 묘사하여 위치 및 동작 지시를 가장 잘 충족했습니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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 appear unless the shot text itself 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 배경 플레이트 — Gemini winner=A 랭킹=A>B>C

철제 파이프 난간을 손으로 잡은 수리영이 코끝을 찡그린 채 계단 중간에 서 있는 얼굴 클로즈업
★ 선정
A — Gemini 7점
얼굴이 가장 가까운 피사체여야 한다는 깊이 조건과 클로즈업 비율을 잘 충족했으며, 장소와 찡그린 표정도 정확히 구현했습니다.
B — Gemini 5점
장소와 표정은 일치하나 손이 얼굴보다 앞에 위치해 깊이 조건을 위반했고, 샷이 너무 넓어 클로즈업 지시를 어겼습니다.
C — Gemini 4점
원본 장소에 없는 거대한 파이프가 전경에 임의로 추가되어 공간을 왜곡했으며, 손이 얼굴보다 앞에 있어 깊이 조건도 위반했습니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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 — never anyone else, and never add a person the shot text does not show.

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 배경 플레이트 — Gemini winner=C 랭킹=C>A>B

수리영이 초점을 잃은 눈으로 허공을 응시하며 서 있는 모습
A — Gemini 6점
배경과 인물 배치는 훌륭하나, 시선이 다소 특정 지점을 향하는 듯해 초점을 잃었다는 느낌이 덜합니다.
B — Gemini 6점
레퍼런스 환경을 잘 재현했으나, 인물의 자세가 지나치게 경직되어 자연스러운 멍함이 부족합니다.
★ 선정
C — Gemini 7점
지정된 장소에서 초점을 잃고 허공을 응시하는 인물의 멍한 상태를 가장 자연스럽고 충실하게 표현했습니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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 — never anyone else, and never add a person the shot text does not show.

No text, captions, watermarks or annotations anywhere.

S13sh6 prev=S13sh4 — Gemini winner=B 랭킹=B>C>A

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 3점
수리영의 자세는 반영되었으나, 지정된 장소(건물, 마당)의 고정된 디테일을 완전히 무시하고 다른 배경을 생성했습니다.
★ 선정
B — Gemini 7점
레퍼런스의 배경 요소를 정확히 유지했고, 고개를 든 수리영의 측면 구도와 시선을 프롬프트에 맞게 훌륭히 구현했습니다.
C — Gemini 5점
배경과 인물 배치는 레퍼런스와 잘 일치하나, 수리영이 고개를 든 동작의 묘사가 다소 부족합니다.
참조 (1장) — prev 선택본
PREVIOUS SHOT STILL
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.

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, 혜수 — never anyone else, and never add a person the shot text does not show.

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 배경 플레이트 — Gemini winner=B 랭킹=B>A>C

다급하게 상체를 기울이며 손가락 끝으로 TV 전원 버튼을 세게 누르고 있는 민숙의 측면 구도
A — Gemini 4점
TV 위치가 기준 사진과 맞지 않으며 텍스트에 없는 인물이 배경에 등장해 인물 제한 규칙을 위반했습니다.
★ 선정
B — Gemini 7점
기준 사진의 공간 구조를 정확히 반영하고 텍스트에 명시된 인물(민숙)만 등장시켜 지침을 가장 잘 따랐습니다.
C — Gemini 3점
공간 구조가 어긋나고 지시문에 없는 여러 인물이 배경에 나타나 규칙을 크게 위반했습니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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 — never anyone else, and never add a person the shot text does not show.

No text, captions, watermarks or annotations anywhere.

S5sh9 prev=S5sh5 — Gemini winner=A 랭킹=A>C>B

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
레퍼런스의 팔 자세와 복장을 정확히 유지하면서 요구된 타이트 샷과 얕은 심도를 가장 충실하게 구현했습니다.
B — Gemini 3점
지시된 타이트 샷을 무시하고 너무 넓게 촬영했으며, 레퍼런스와 달리 앉아있는 자세로 연속성을 깼습니다.
C — Gemini 4점
프레이밍은 타이트하지만 레퍼런스의 뻗은 팔 자세를 무시하고 손목을 꺾은 채로 포즈를 임의로 변경했습니다.
참조 (1장) — prev 선택본
PREVIOUS SHOT STILL
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.

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 — never anyone else, and never add a person the shot text does not show.

No text, captions, watermarks or annotations anywhere.

S12sh11 배경 플레이트 — Gemini winner=B 랭킹=B>C>A

옷과 피부가 피투성이가 된 민숙이 바닥에 주저앉아 고개를 푹 숙인 정지 상태
A — Gemini 4점
발자국과 인물 묘사는 준수하나, 지정된 장소 레퍼런스(문, 방 구조)를 완전히 무시하여 일치도가 낮습니다.
★ 선정
B — Gemini 7점
배경 레퍼런스와 인물 크기(2/3), 움켜쥔 사진 등 지정된 자세를 잘 따랐으나 바닥의 발자국이 누락되었습니다.
C — Gemini 5점
지정된 배경과 발자국 묘사는 우수하나, 인물 크기(2/3) 지시를 무시했고 사진을 움켜쥐지 않았습니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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.

No text, captions, watermarks or annotations anywhere.

S12sh18 prev=S12sh11 — Gemini winner=A 랭킹=A>C>B

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
★ 선정
A — Gemini 7점
레퍼런스의 손 방향, 붉은 자국, 조명을 정확히 유지하며 크기 비율과 깊이감 등 프롬프트의 구도를 훌륭하게 구현했습니다.
B — Gemini 3점
사진 표면에 텍스트가 생성되어 텍스트 배제 조건을 위반했으며, 손의 방향도 레퍼런스와 일치하지 않습니다.
C — Gemini 6점
요구사항을 대체로 잘 따랐으나, 구겨진 사진을 쥐고 있는 손의 형태가 A에 비해 다소 부자연스럽습니다.
참조 (1장) — prev 선택본
PREVIOUS SHOT STILL
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.

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.

No text, captions, watermarks or annotations anywhere.

S12sh21 배경 전용 샷 → 플레이트 강제 — Gemini winner=C 랭킹=C>B>A

침대 위쪽 벽면에 붉은색 원형 표식이 절반쯤 나타난 상태
A — Gemini 4점
레퍼런스에 없는 두 번째 침대가 화면을 차지하고 있으며, 원형 표식 또한 절반이 아닌 거의 완성된 형태로 묘사되었습니다.
B — Gemini 5점
원형 표식이 절반쯤 그려진 프롬프트의 지시를 정확히 따랐으나, 내부 목재 방문을 우편함이 달린 철문으로 왜곡하는 심각한 구조적 오류가 있습니다.
★ 선정
C — Gemini 7점
장소의 구조와 인테리어를 레퍼런스와 매우 흡사하게 구현했으나, 붉은색 원형 표식이 절반(50%)보다 더 많이 그려진 점이 아쉽습니다.
참조 (1장) — 배경 플레이트 (★배경 전용 샷 — prev 무시)
LOCATION PHOTOGRAPH
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 배경 전용 샷 → 플레이트 강제 — Gemini winner=B 랭킹=B>C>A

핏자국 없이 깨끗한 방 내부 전경
A — Gemini 3점
공간 내 필수 고정 요소로 명시된 침대가 완전히 누락되어 프롬프트와 레퍼런스 지시를 심각하게 위반했습니다.
★ 선정
B — Gemini 7점
레퍼런스의 공간을 충실히 재현하면서 프롬프트에 명시된 대로 인형의 위치를 다르게 배치하여 디테일을 잘 살렸습니다.
C — Gemini 5점
공간과 인물 부재 조건은 잘 맞췄으나, 인형의 위치가 레퍼런스와 거의 동일하고 우측 하단에 불필요한 가구가 추가되었습니다.
참조 (1장) — 배경 플레이트 (★배경 전용 샷 — prev 무시)
LOCATION PHOTOGRAPH
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.

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.

S14sh7 prev=S14sh5 — Gemini winner=B 랭킹=B>C>A

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 3점
인형이 캐릭터의 어깨에 붙어 있는 오류가 있고 멍한 표정 대신 울고 있어 프롬프트와 어긋납니다.
★ 선정
B — Gemini 8점
얼굴 크기 비율(2/3)과 멍한 시선 묘사가 훌륭하며, 배경의 방 구조와 소품 위치도 정확하게 유지되었습니다.
C — Gemini 5점
시선이 빈 방이 아닌 카메라를 향해 있으며, 클로즈업 지시에도 불구하고 배경이 너무 넓게 포함되었습니다.
참조 (1장) — prev 선택본
PREVIOUS SHOT STILL
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 배경 플레이트 — Gemini winner=A 랭킹=A>C>B

혜수가 날카로운 눈빛으로 김형사를 노려보는 모습
★ 선정
A — Gemini 8점
얼굴과 신체 방향이 지침과 완벽히 일치하며, 레퍼런스의 배경 상태와 소품 배치를 충실하게 재현했습니다.
B — Gemini 4점
몸이 다른 곳을 향한 채 고개만 돌리고 있어 '얼굴과 몸이 직접 대상을 향함' 지침을 위반했습니다.
C — Gemini 6점
신체 방향은 맞으나, 벽과 문에 원본 레퍼런스에 없는 심한 오염 자국을 추가하여 장소 고정 지침을 어겼습니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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 — never anyone else, and never add a person the shot text does not show.

No text, captions, watermarks or annotations anywhere.

S18sh11 배경 플레이트 — Gemini winner=B 랭킹=B>A>C

거울 속 반사된 욕실 타일 벽면에 붉은색 원형 표식이 절반쯤 나타난 상태
A — Gemini 5점
거울이 화면을 채우지 못하고 침실이 보이며, 붉은 원이 절반을 넘어 거의 다 그려졌습니다.
★ 선정
B — Gemini 7점
거울이 화면의 대부분을 채우는 구도와 절반쯤 나타난 붉은 원의 형태를 지문대로 충실히 구현했습니다.
C — Gemini 4점
지문에 없는 인물이 화면에 등장했고 붉은 원이 온전한 형태로 그려져 지시를 위반했습니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 — never anyone else, and never add a person the shot text does not show.

No text, captions, watermarks or annotations anywhere.

S18sh15 배경 전용 샷 → 플레이트 강제 — Gemini winner=C 랭킹=C>A>B

액자 속 민숙의 얼굴 부분 이미지가 아래로 일그러지며 흘러내리는 찰나
A — Gemini 5점
가방은 등장하지만, 이미지가 액자 밖으로 쏟아져 나와 3D 액체처럼 표현되어 유리 아래에 있어야 한다는 지시를 어겼습니다.
B — Gemini 4점
인형이 달린 가방이 누락되었으며, 얼굴 이미지가 액자 밖으로 흘러넘쳐 프롬프트의 심도 제약을 위반했습니다.
★ 선정
C — Gemini 7점
유리 표면 아래에서 이미지가 흘러내리는 심도 표현을 잘 지켰고, 인형이 달린 가방과 배경의 디테일도 레퍼런스와 가장 일치합니다.
참조 (1장) — 배경 플레이트 (★배경 전용 샷 — prev 무시)
LOCATION PHOTOGRAPH
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 appear unless the shot text itself says so.

No text, captions, watermarks or annotations anywhere.

S18sh16 prev=S5sh5 — Gemini winner=C 랭킹=C>A>B

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
A — Gemini 4점
인물의 표정과 소품은 적절하나, 참조 이미지에 고정된 배경(주방)을 전혀 반영하지 않고 완전히 다른 공간을 생성했습니다.
B — Gemini 3점
배경은 참조 이미지와 일치하나, 명시적으로 제외하도록 지시된 앞치마를 입은 중년 여성을 그대로 피사체로 등장시켰습니다.
★ 선정
C — Gemini 7점
지시된 배경(주방)과 인물(젊은 여성), 소품(정상적인 액자, 인형 가방)의 위치와 상태를 가장 정확히 구현했습니다.
참조 (1장) — prev 선택본
PREVIOUS SHOT STILL
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.

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 — never anyone else, and never add a person the shot text does not show.

No text, captions, watermarks or annotations anywhere.

S25sh1 배경 플레이트 — Gemini winner=A 랭킹=A>C>B

해질 무렵 옥탑방 거실, 흙 묻은 발자국들이 찍힌 바닥과 쓰러진 식탁 의자들이 보이는 전경
★ 선정
A — Gemini 7점
열린 창문, 전경의 발자국과 쓰러진 의자, 붉은 원과 사진 등 프롬프트의 모든 세부 사항을 기준 장소에 정확히 구현했습니다.
B — Gemini 3점
기준 이미지의 미닫이 창문이 여닫이로 왜곡되었으며, 필수 요소인 붉은 원과 사진이 완전히 누락되었습니다.
C — Gemini 4점
기준 장소와의 일관성은 준수하나, 열려 있어야 할 창문이 닫혀 있고 붉은 원 안에 사진이 없습니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 — never anyone else, and never add a person the shot text does not show.

No text, captions, watermarks or annotations anywhere.

S25sh5 배경 플레이트 — Gemini winner=C 랭킹=C>A>B

붉은 원 한가운데 피 묻은 낡은 흑백 사진이 벽에 꽂혀 있는 타이트 샷
A — Gemini 5점
주요 피사체는 존재하지만 사진이 벽에 완전히 밀착되어 입체감이 부족하고 장소의 맥락을 알 수 없습니다.
B — Gemini 3점
배경의 어질러진 상태를 보여주기 위해 벽을 투명하게 처리하여, 사진과 붉은 원이 공중에 떠 있는 구조적 오류를 범했습니다.
★ 선정
C — Gemini 7점
벽에서 앞쪽으로 튀어나온 사진의 입체감과 붉은 원을 지시대로 잘 구현했으며, 해질녘의 조명과 공간감도 적절합니다.
참조 (1장) — 배경 플레이트
LOCATION PHOTOGRAPH
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.

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 appear unless the shot text itself says so.

No text, captions, watermarks or annotations anywhere.

S25sh9 prev=S25sh5 — Gemini winner=A 랭킹=A>C>B

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 8점
레퍼런스의 배경, 질감, 조명을 정확히 유지하며, 지시된 대로 구겨진 사진을 꽉 쥔 손의 너클이 카메라 쪽을 향하는 깊이감을 완벽하게 구현했습니다.
B — Gemini 3점
사진을 움켜쥔 동작은 있으나, 레퍼런스와 완전히 다른 배경(벽면, 가구 등)이 묘사되어 장소 고정 지침을 크게 위반했습니다.
C — Gemini 6점
장소와 배경 요소는 레퍼런스를 잘 따랐으나, 사진을 구겨지게 꽉 쥐는 힘이 부족해 보이고 손가락 관절이 카메라 정면을 향하는 구도 지침에 다소 미흡합니다.
참조 (1장) — prev 선택본
PREVIOUS SHOT STILL
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.

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 prev=S25sh1 — Gemini winner=C 랭킹=C>A>B

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 5점
표정과 구도는 요구사항에 부합하나, 배경의 코르크 보드에 있어야 할 붉은 원이 누락되었습니다.
B — Gemini 3점
스마트폰 화면이 카메라를 향해 있어 소품 방향 규칙을 어겼으며, 화면에 금지된 텍스트가 포함되었습니다.
★ 선정
C — Gemini 7점
스마트폰의 방향이 올바르며, 프롬프트가 요구한 배경의 '빈 붉은 원'까지 정확히 구현하여 가장 충실합니다.
참조 (1장) — prev 선택본
PREVIOUS SHOT STILL
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.