★GPT(gpt-image-2) 재실행 — v5g: 텍스트만 / v3g: 2단 / v1g: 콘티→배경 i2i / v4g: 가이드선 3단

g_v5: 텍스트만
g_v3 StageA 콘티
g_v3 StageB 스틸
비교: E2E9 확정본(nb2)

GPT v1g·v4g

g_v1 Stage1 콘티+엔티티
g_v1 Stage2 배경 i2i
g_v4 StageA 가이드선 콘티
g_v4 StageB 배경 삽입
g_v4 StageC 최종

실험 v5 — 참조 0, 프롬프트만

v5: 텍스트만
비교: E2E9 확정본

실험 v4 — ①배경만→가이드선 콘티 ②배경 삽입 합성 ③최종 실사

입력: 배경 플레이트 L09B03
StageA: 가이드선 콘티(배경만 참조)
StageB: 배경 삽입 합성
StageC: 최종 실사
비교: E2E9 확정본

실험 v3 — ①배경+엔티티→콘티 ②배경+엔티티+콘티→스틸

StageA: 콘티(배경+엔티티 참조)
StageB: 스틸(배경+엔티티+콘티)

실험 v2 — ①배경→콘티 ②콘티+엔티티(배경 제외) ③배경 i2i

StageA: 배경 참조 콘티
StageB: 콘티+엔티티만
StageC: 배경 i2i 수정

실험 v1 (E2E9 기존 콘티 재사용 2단)

Stage1: 콘티+엔티티만
Stage2: 배경 i2i 수정

스틸 공간 계약 fix1(CAMERA&FRAME)·fix2(실내외 정합) 전후 비교 (2026-07-19)

base=E2E9 record 프롬프트 재조립(검증 통과) / fix1=staging 구도·스케일 절 주입 / fix2=샷별 서브공간 place + 장소 중립 time_of_day / fix12=병합

공간 계약 fix 비교 — S19sh4 (단롤 nb2, 참조=E2E9 확정 자산 동일)

e2e9_final
base
fix1
fix2
fix12
주입 델타 보기
== CAMERA & FRAME (fix1) ==
CAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):
- CAMERA: Outside the market, frame 수리영 from near eye level at her side and complete the upward tilt so her lifted profile holds the lower-left while the wall-mounted CCTV camera lands in the upper-right. Keep the distance at a medium side view, allowing her eyeline to connect the two anchors without converting the shot into device footage.
- FRAMING SCALE: medium shot
- FRAME LAYOUT: 수리영 in the middle-left of the frame, midground, looks toward exterior CCTV camera; exterior CCTV camera in the upper-right of the frame, background.
- KEY BACKGROUND ELEMENTS: 마트 외부 CCTV 카메라 (Mounted on the market exterior wall) — The lens side of the mounted camera faces the area 수리영 is checking; used as Upper-frame eyeline destination establishing that the relevant area may have been recorded; 마트 외부 건물 벽 (Supporting the mounted CCTV camera); used as Spatial support for the high CCTV position.
Compose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.

== fix2 place_en ==
Outside the supermarket, directly beside the building wall where an exterior CCTV camera is mounted.
== fix2 time_of_day_en ==
early morning

공간 계약 fix 비교 — S15sh4 (단롤 nb2, 참조=E2E9 확정 자산 동일)

e2e9_final
base
fix1
fix2
fix12
주입 델타 보기
== CAMERA & FRAME (fix1) ==
CAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):
- CAMERA: At waist height behind 수리영, the camera tracks along her departure line while briefly holding the established distance, isolating her rear silhouette at the instant one foot is suspended. She remains near the lower center with the coastal road opening ahead in the upper frame, allowing her to begin increasing the gap before the camera later pans back.
- FRAMING SCALE: wide shot
- FRAME LAYOUT: 수리영 in the lower-center of the frame, midground, moves toward coastal road ahead; coastal road ahead in the upper-center of the frame, background.
- KEY BACKGROUND ELEMENTS: Coastal road (Visible under night conditions) — The road extends away from the camera along 수리영's running line; used as Defines the direction of 수리영's escape from the bench area; Bus-stop area (Left behind as 수리영 runs away) — The bench area lies behind the camera-facing side of 수리영's route; used as Recedes behind the running figure as a continuity marker for her departure.
Compose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.

== fix2 place_en ==
On the dark coastal road near the bus stop, facing away from the seaside waiting area.
== fix2 time_of_day_en ==
night

원근 가이드 콘티 실험 — S19sh4 (2026-07-19 밤)

콘티 재저작=기존 계약+샷별 장소(마트 외벽)+staging 구도 계약+원근·크기·방향 가이드(수평선·소실선·실크기 비례·시선/동선 화살표). 스틸=nb2, 참조=[플레이트+가이드 콘티+엔티티].

콘티 2종

콘티(nb2 저작)
콘티(gpt 저작)
참고: E2E9 기존 콘티 기반 스틸(base)

가이드 콘티 기반 nb2 스틸

nb2 콘티 × base 텍스트
nb2 콘티 × fix12 텍스트
gpt 콘티 × base 텍스트
gpt 콘티 × fix12 텍스트
비교: E2E9 확정본
콘티 프롬프트 전문
Draw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.

STYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible
director's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR
LINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO
hatching, NO texture, NO grayscale fill, NO light-and-shadow, NO
facial features beyond a bare head outline, NO clothing detail, NO
material rendering. The frame contains ONLY: the camera framing,
each figure as a simple correct-proportion human contour in its
exact pose and screen position/size, and the few major set masses
as plain outline shapes. It must read as a quick layout guide,
never as a finished drawing.

The attached photograph is the LOCATION where this shot happens.
Use it ONLY as a LOOSE spatial reference — the rough set masses
and where things sit relative to each other. You do NOT need to
follow it exactly: do not copy its camera, its lighting or its
details. Choose the camera and framing the SHOT TEXT needs, and
draw only the few set masses that matter as plain outline shapes.

THE LOCATION: Outside the supermarket, directly beside the building wall where an exterior CCTV camera is mounted.

SHOT TEXT (authoritative, Korean): 마트 외부 건물 벽에 달린 CCTV 카메라를 올려다보는 수리영의 옆얼굴.

CARRIED STATE (persist exactly): Su-ri-yeong’s bicycle remains parked outside the mart, and she continues carrying her doll-adorned backpack and mobile phone. The exterior CCTV camera stays fixed in the identified position.

ABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.

CAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):
- CAMERA: Outside the market, frame 수리영 from near eye level at her side and complete the upward tilt so her lifted profile holds the lower-left while the wall-mounted CCTV camera lands in the upper-right. Keep the distance at a medium side view, allowing her eyeline to connect the two anchors without converting the shot into device footage.
- FRAMING SCALE: medium shot
- FRAME LAYOUT: 수리영 in the middle-left of the frame, midground, looks toward exterior CCTV camera; exterior CCTV camera in the upper-right of the frame, background.
- KEY BACKGROUND ELEMENTS: 마트 외부 CCTV 카메라 (Mounted on the market exterior wall) — The lens side of the mounted camera faces the area 수리영 is checking; used as Upper-frame eyeline destination establishing that the relevant area may have been recorded; 마트 외부 건물 벽 (Supporting the mounted CCTV camera); used as Spatial support for the high CCTV position.
Compose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.

PERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):
- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.
- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.
- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.
- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.

원근 콘티 2단 분리 실사화 — A(배경 먼저) vs B(엔티티 먼저) (2026-07-19 밤)

시작점=GPT 원근 가이드 콘티. 최종 텍스트=fix12. 엔진=nb2.

방식 A — 배경 먼저

입력: GPT 원근 콘티
A1: 배경 실사화(인물 선화 유지)
A2: 최종(엔티티 실사화)
비교: 1단 직행(gpt콘티×fix12)

방식 B — 엔티티 먼저

입력: GPT 원근 콘티
B1: 인물 실사화(배경 선화 유지)
B2: 최종(배경 실사화)
비교: E2E9 확정본

배경 먼저 v2 — Step1 재투영=GPT (S22sh2·S8sh4, 2026-07-20)

순서: Step1'=기존 플레이트를 콘티 카메라로 재투영한 인물 0 배경(gpt-image-2 — nb2 는 플레이트 프레이밍 고수 실측) → Step2'=그 배경+콘티 배치+캐릭터 참조로 인물 삽입(nb2). 각 이미지 아래=사용한 입력·프롬프트 전문.

S22sh2 — 핸들을 꽉 쥐고 허리를 한껏 숙인 채 페달을 밟으며 앞으로 나아가는 중간 순간의 수리영 측면, 머리카락과 옷자락이 움직임의 반대 방향으로 흩날리는 모습.

입력 배경 플레이트(원본)
입력: E2E9 background_chain/L16B01.png (인물 없음)
GPT 원근 콘티
입력: 플레이트 + 수리영 참조 + 콘티 프롬프트(기존 계약+샷별 장소+CAMERA/FRAME+원근 가이드)
Step1(구, nb2): 플레이트 구도로 수렴 — 재투영 실패
입력: 콘티+플레이트, nb2 — S22sh2 는 콘티 카메라 무시 실측
Step1'(신, GPT): 콘티 카메라 재투영·인물 0
입력: 콘티(1st)+플레이트(2nd), gpt-image-2 + 아래 프롬프트
프롬프트 전문
Create the EMPTY BACKGROUND PLATE for one film shot — NO PEOPLE, no figures, no body parts, no sketch lines, no arrows anywhere.
The FIRST attached image is a thin-line storyboard sketch: use ONLY its camera angle, horizon, perspective and the placement/size of buildings and set masses — ignore the sketched people and arrows entirely. The SECOND attached image (LOCATION PHOTOGRAPH) is the real place: take its architecture, materials, signage and fixed features, and RE-PROJECT them into the sketch's camera. If the photograph's camera differs from the sketch's, the sketch's camera wins.

SHOT TEXT this background must serve (Korean): 핸들을 꽉 쥐고 허리를 한껏 숙인 채 페달을 밟으며 앞으로 나아가는 중간 순간의 수리영 측면, 머리카락과 옷자락이 움직임의 반대 방향으로 흩날리는 모습.

LOCATION (lock): On the exterior frontage immediately outside the police station, where the parked bicycle is ridden away.

TIME OF DAY (lock): day.

CAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):
- CAMERA: At torso height beside 수리영, track parallel to the bicycle's forward path in a medium side view as she accelerates. Keep her and the bicycle centered with travel space ahead, her torso folded low over the handlebars and her hair and clothing trailing opposite the direction of movement; the tracking speed holds her scale stable while the surroundings slide backward.
- FRAMING SCALE: medium shot
- FRAME LAYOUT: 수리영 in the middle-center of the frame, midground, moves toward frame right along the bicycle path.
- KEY BACKGROUND ELEMENTS: 자전거 (In motion as 수리영 pedals away from the police station) — Its side faces the parallel-tracking camera, with the front wheel oriented toward frame right; used as Moving support that defines her acceleration and forward direction.
Compose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.

Render ONE photorealistic empty location photograph, 16:9, that this shot can be staged inside later. No text or watermarks.
Step2' 최종: 인물 삽입(nb2)
입력: Step1' 배경 + 콘티(인물 배치만) + 수리영 참조 + 아래 프롬프트
프롬프트 전문
Stage the shot. The FIRST attached image (SHOT BACKGROUND) is the finished empty background of this shot — keep it EXACTLY: its camera, perspective, architecture, lighting and every fixed feature stay untouched. The SECOND attached image (LAYOUT SKETCH) tells you ONLY where the people go: each sketched person's position, screen size, pose and the gaze/motion arrows. Ignore the sketch's background lines. The CHARACTER REFERENCE photographs show the real people.
Place the real people into the background at exactly the sketched positions, sizes and poses, following the arrow directions. No sketch lines or arrows may remain.

Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): day.

SHOT TEXT (authoritative, Korean): 핸들을 꽉 쥐고 허리를 한껏 숙인 채 페달을 밟으며 앞으로 나아가는 중간 순간의 수리영 측면, 머리카락과 옷자락이 움직임의 반대 방향으로 흩날리는 모습.

LOCATION (lock): On the exterior frontage immediately outside the police station, where the parked bicycle is ridden away. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot.

CAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):
- CAMERA: At torso height beside 수리영, track parallel to the bicycle's forward path in a medium side view as she accelerates. Keep her and the bicycle centered with travel space ahead, her torso folded low over the handlebars and her hair and clothing trailing opposite the direction of movement; the tracking speed holds her scale stable while the surroundings slide backward.
- FRAMING SCALE: medium shot
- FRAME LAYOUT: 수리영 in the middle-center of the frame, midground, moves toward frame right along the bicycle path.
- KEY BACKGROUND ELEMENTS: 자전거 (In motion as 수리영 pedals away from the police station) — Its side faces the parallel-tracking camera, with the front wheel oriented toward frame right; used as Moving support that defines her acceleration and forward direction.
Compose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.

REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot
text may describe characters metaphorically, figuratively or with
exaggeration. Photograph what a real movie camera would actually
record on a physical set — exaggerated or figurative impressions
become realistic staging choices (lighting, distance, angle,
wardrobe), not literal fantasy imagery.
EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly
features non-human or virtual beings (as in science fiction or
fantasy), every character — however indirectly, vaguely or
figuratively the text describes them — IS a real human. When the
text gives no direct visual description of a person, IMAGINE one
and still show them as a concrete, fully-formed human being:
always render the human form to the maximum extent — build,
posture, face, hands, clothing — never reduce a person to a shape,
blob, solid silhouette or abstract mass.

EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a
person's eyes, face or presence emotionally or figuratively (vacant,
hollow, dazed, burning, lifeless gaze and the like), it describes an
ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY
through gaze direction, focus, eyelids, facial muscles, stillness
and posture. Every living person's eyes remain anatomically normal
human eyes with a natural iris and pupil, natural sclera and normal
proportions; NEVER whiten, blank out, cloud over, glow, enlarge or
otherwise alter eyeballs, skin or anatomy — unless the story
explicitly declares that being non-human or supernatural in form.

PROPS FACE THE RIGHT WAY: every handheld or used object must be
oriented exactly as its real-world use requires. A person reading,
watching or operating something (a phone, a photograph, a paper,
any device) has its functional side — screen, front, page — facing
THEIR OWN eyes; the camera then sees whatever side the staging
geometry implies (often its back). Show the functional side to the
camera ONLY when the shot text itself stages it toward the viewer.
Never flip, mirror or reverse an object's front and back.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong rides her bicycle with the folded coordinate note in her pocket, while her doll-adorned backpack and mobile phone remain with her.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above.

No text, captions, watermarks or annotations anywhere.
비교: E2E9 확정본
입력: 기존 파이프라인 산출

S8sh4 — 마트 남자 직원과 마주 본 상태로 눈을 동그랗게 뜬 수리영의 측면

입력 배경 플레이트(원본)
입력: E2E9 background_chain/L09B01.png — ★플레이트 자체에 인물이 구워져 있음(상류 결함, 별도 기록)
GPT 원근 콘티
입력: 플레이트 + 수리영 참조 + 콘티 프롬프트(기존 계약+샷별 장소+CAMERA/FRAME+원근 가이드)
Step1(구, nb2): 플레이트 구도로 수렴 — 재투영 실패
입력: 콘티+플레이트, nb2 — S22sh2 는 콘티 카메라 무시 실측
Step1'(신, GPT): 콘티 카메라 재투영·인물 0
입력: 콘티(1st)+플레이트(2nd), gpt-image-2 + 아래 프롬프트
프롬프트 전문
Create the EMPTY BACKGROUND PLATE for one film shot — NO PEOPLE, no figures, no body parts, no sketch lines, no arrows anywhere.
The FIRST attached image is a thin-line storyboard sketch: use ONLY its camera angle, horizon, perspective and the placement/size of buildings and set masses — ignore the sketched people and arrows entirely. The SECOND attached image (LOCATION PHOTOGRAPH) is the real place: take its architecture, materials, signage and fixed features, and RE-PROJECT them into the sketch's camera. If the photograph's camera differs from the sketch's, the sketch's camera wins.

SHOT TEXT this background must serve (Korean): 마트 남자 직원과 마주 본 상태로 눈을 동그랗게 뜬 수리영의 측면

LOCATION (lock): Inside the large market, on the merchandise sales floor beside the stocking and display area.

TIME OF DAY (lock): dusk.

CAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):
- CAMERA: From eye level beside 수리영, continue the prescribed dolly inward from a medium-close side view to a close profile, placing her widened eye and cheek in the right half while the 마트 남자 직원 remains soft but recognizable across from her at the left edge. Preserve the conversation axis and emphasize only the shrinking camera distance as his information lands.
- FRAMING SCALE: close-up
- KEY BACKGROUND ELEMENTS: 마트 진열대 (Present in the stocking area) — The aisle-facing sides recede behind the 마트 남자 직원; used as Supplies limited supermarket context behind the employee while remaining out of primary focus; 진열용 박스 (Being carried for stocking) — One side faces the camera while the box is held near the shelving; used as Connects the employee’s interrupted task to the conversation.
Compose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.

Render ONE photorealistic empty location photograph, 16:9, that this shot can be staged inside later. No text or watermarks.
Step2' 최종: 인물 삽입(nb2)
입력: Step1' 배경 + 콘티(인물 배치만) + 수리영 참조 + 아래 프롬프트
프롬프트 전문
Stage the shot. The FIRST attached image (SHOT BACKGROUND) is the finished empty background of this shot — keep it EXACTLY: its camera, perspective, architecture, lighting and every fixed feature stay untouched. The SECOND attached image (LAYOUT SKETCH) tells you ONLY where the people go: each sketched person's position, screen size, pose and the gaze/motion arrows. Ignore the sketch's background lines. The CHARACTER REFERENCE photographs show the real people.
Place the real people into the background at exactly the sketched positions, sizes and poses, following the arrow directions. No sketch lines or arrows may remain.

Create ONE FINAL photorealistic live-action film still of the moment below — Incheon, South Korea, 2026; all people are Korean unless stated. TIME OF DAY (lock): dusk.

SHOT TEXT (authoritative, Korean): 마트 남자 직원과 마주 본 상태로 눈을 동그랗게 뜬 수리영의 측면

LOCATION (lock): Inside the large market, on the merchandise sales floor beside the stocking and display area. The shot takes place here — the attached LOCATION PHOTOGRAPH shows the exact spot.

CAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):
- CAMERA: From eye level beside 수리영, continue the prescribed dolly inward from a medium-close side view to a close profile, placing her widened eye and cheek in the right half while the 마트 남자 직원 remains soft but recognizable across from her at the left edge. Preserve the conversation axis and emphasize only the shrinking camera distance as his information lands.
- FRAMING SCALE: close-up
- KEY BACKGROUND ELEMENTS: 마트 진열대 (Present in the stocking area) — The aisle-facing sides recede behind the 마트 남자 직원; used as Supplies limited supermarket context behind the employee while remaining out of primary focus; 진열용 박스 (Being carried for stocking) — One side faces the camera while the box is held near the shelving; used as Connects the employee’s interrupted task to the conversation.
Compose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.

REALIZE FIGURATIVE LANGUAGE AS A LIVE-ACTION SHOT: the Korean shot
text may describe characters metaphorically, figuratively or with
exaggeration. Photograph what a real movie camera would actually
record on a physical set — exaggerated or figurative impressions
become realistic staging choices (lighting, distance, angle,
wardrobe), not literal fantasy imagery.
EVERY CHARACTER IS A HUMAN BEING: unless the story explicitly
features non-human or virtual beings (as in science fiction or
fantasy), every character — however indirectly, vaguely or
figuratively the text describes them — IS a real human. When the
text gives no direct visual description of a person, IMAGINE one
and still show them as a concrete, fully-formed human being:
always render the human form to the maximum extent — build,
posture, face, hands, clothing — never reduce a person to a shape,
blob, solid silhouette or abstract mass.

EXPRESSIONS ARE ACTED, NEVER ANATOMICAL: when the text describes a
person's eyes, face or presence emotionally or figuratively (vacant,
hollow, dazed, burning, lifeless gaze and the like), it describes an
ACTOR'S PERFORMANCE captured by a real camera — realize it ONLY
through gaze direction, focus, eyelids, facial muscles, stillness
and posture. Every living person's eyes remain anatomically normal
human eyes with a natural iris and pupil, natural sclera and normal
proportions; NEVER whiten, blank out, cloud over, glow, enlarge or
otherwise alter eyeballs, skin or anatomy — unless the story
explicitly declares that being non-human or supernatural in form.

PROPS FACE THE RIGHT WAY: every handheld or used object must be
oriented exactly as its real-world use requires. A person reading,
watching or operating something (a phone, a photograph, a paper,
any device) has its functional side — screen, front, page — facing
THEIR OWN eyes; the camera then sees whatever side the staging
geometry implies (often its back). Show the functional side to the
camera ONLY when the shot text itself stages it toward the viewer.
Never flip, mirror or reverse an object's front and back.

CARRIED STATE (persist exactly — must match the neighbouring shots of this scene): Su-ri-yeong’s bicycle remains parked outside the mart, and she still has her mobile phone with her.

PEOPLE: the SHOT TEXT alone decides whether any person is visible in this shot. IF a person appears, they must be one of: 수리영 (한국인 여성, 20대 초반, 앳된 타원형 얼굴, 자연스러운 검은 머리) — never anyone else, and never add a person the shot text does not show. IF only part of a person is in frame (a hand, arm, foot, back, silhouette), that body part belongs to the specific person the shot text names — its sex, age, build, skin and grooming must unmistakably match that person's profile above.

No text, captions, watermarks or annotations anywhere.
비교: E2E9 확정본
입력: 기존 파이프라인 산출