forest_exp — 'bg_rooftop_unit' 총괄 파이프라인 실험

읽는 법 — 흐름: 0.입력(fp/배치도) → 1.뿌리(조감 스케치) → 2.실내 탑레이어 → 3.실내 샷별 체인 → 4.실외 샷별 체인(v1→v2→v3 버전순).
각 샷 블록은 생성 순서(①②③…) 행 다음에 경로별 결과(A=직행 / B=VLM구도 / C=i2i윤곽 / m=마네킹) 행. 모든 셀 하단 prompt/refs 를 펼치면 실제 사용 프롬프트와 참조 이미지가 나옵니다. 실외 버전: v1=계약 없음(실패 증거) → v2=인원/시점/마커 계약 3줄 → v3=sketch-hop(라인아트 경유) → v3.1=CONTROL을 스케치로 교체.

0. 입력 데이터 — 실제 생성에 참조로 사용된 것만

각 셀 주석 = runlog 기준 그 이미지를 실제 소비한 생성 호출 목록. 사용되지 않은 보유 자산은 표시하지 않음.
floor plans + production 배치도
입력 L03 floor plan — fp_l03_rooftop_entry_main
✅ 사용된 호출: root_C_fp_anchor, root_v2_whole_property
입력 L04 floor plan — fp_l04_rooftop_room_main
✅ 사용된 호출: S14_Shot4_fpvar, S5_Shot10_fpvar, S5_Shot3_fpvar, root_C_fp_anchor, top_TL1_bedroom_bathroom, top_TL2_living_kitchen_entry
입력 L10 floor plan — fp_l10_cement_stairs
✅ 사용된 호출: root_v2_whole_property
입력 L10 floor plan — fp_l10_exterior_alley
✅ 사용된 호출: root_v2_whole_property
입력 production 통합 배치도 (root_B의 베이스)
✅ 사용된 호출: root_B_from_plan · ⚠ fp_l03 과 배치 불일치+실내 노출(3라운드 진단 원인)
캐릭터 passport (최종샷 IDENTITY 참조로 실사용된 것만)
입력 passport C01
✅ 사용된 호출: S11_Shot3_final_A, S11_Shot3_final_A_v2, S11_Shot3_final_B, S11_Shot3_final_B_v2, S11_Shot3_final_C, S11_Shot3_final_C_m_r2, S11_Shot3_final_C_v2, S5_Shot10_final_A …
입력 passport C04
✅ 사용된 호출: S5_Shot10_final_A, S5_Shot10_final_B, S5_Shot10_final_C, S5_Shot3_final_A, S5_Shot3_final_B, S5_Shot3_final_C, S5_Shot3_final_C_m_r2

1. 뿌리 — 통합 조감 스케치 (전 샷 포괄, 원기호+영어 범례)

판정: 기호/범례 렌더는 A·B 모두 신뢰(오탈자 0, readback 10/10). 그러나 기하가 문제 — root_A 는 자체 발명, root_B 는 production 배치도의 틀린 배치(fp_l03 대비 방 축소·계단/물탱크 위치 오류)를 상속 → 실외 하류 전체가 '오두막' 으로 붕괴. 3라운드: fp_l03 을 기하 SOT 로 앵커한 root_C 검증.
root 변형
R-A 순수 T2I (기하 자체발명 — 결격) gpt-image-2 · 108.0s
prompt/refs (실제 호출 기록)
ONE hand-drawn TOP-DOWN aerial SITE SKETCH of a single real-world place,
in clean technical sketch style: dark ink outlines, light flat colour
washes, straight-down view. NOT a photograph, NOT a 3D render, no
perspective, no photo textures.

The place consists of these connected parts — draw them TOGETHER as one
coherent site (one main structure plus its immediate surroundings):
- (outdoor, L03) 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)
- (indoor, L04) 옥탑방 내부: 작은 창문으로 빛이 들어오는 낡은 주거 공간. 싱크대, 식탁, TV가 있는 거실과 침대, 커튼, 거울 등이 있는 방/욕실로 구성된다. 약초 끓이는 냄비 등 생활 소품이 있으며, 간헐적으로 벽면에 붉은 원 형태의 환영과 핏자국이 생겨난다. (특징: 작은 창문의 햇살; 싱크대와 약초(석창포); 가스레인지 위 끓는 냄비와 수증기; 거실 TV와 스탠드; 침대, 커튼, 거울; 벽과 거울 표면에 나타나는 붉은 원 환영; 바닥과 벽의 핏자국 (특정 시점); 어지럽혀진 가재도구 (특정 시점))
- (outdoor, L10) 옥탑방 외곽 골목·시멘트 계단: 다세대 빌라 마당의 후미진 구석과 옥탑방으로 올라가는 가파르고 낡은 시멘트 계단. (특징: 다세대 빌라 입구 마당; 후미진 구석 공간; 낡고 가파른 시멘트 계단)

Overall massing/orientation guidance:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

Draw ONLY what is visible from above and from outside: the structure's
roof outline and what stands on top of it, open ground areas, approach
paths and stairs, and each opening (door, gate, window, level access) as
part of the boundary it belongs to. Do NOT draw any interior room layout
or interior furniture — buildings show their roof plane only.

Mark each of the following elements at its position with a small circle
containing its single capital letter:
(A) Rooftop room — Center the small roof outline on the rooftop terrace, with its entrance edge facing the terrace landing and exterior stair approach.
(B) Iron door — Place on the entrance edge of the rooftop-room outline, opening directly onto the rooftop terrace landing; mark the flyer at the door seam.
(C) Exterior windows — Draw window slots on the outer walls of the rooftop-room outline: one small/living window on a side wall visible from the terrace, and one curtained bedroom window on another outer wall.
(D) Inner doorways — Inside the rooftop-room roof outline, mark only abstract doorway openings for the bedroom and bathroom access; do not draw interior walls, rooms, or furniture.
(E) Rooftop terrace — Surround the rooftop-room outline with worn cement rooftop surface, widest in front of the iron door where the stair arrives.
(F) Low wall — Run along the exposed perimeter of the rooftop terrace, outside the room and beside the cat/window line of sight.
(G) Roof fixtures — Cluster the water tank, clothesline, and herb-drying platform on open terrace space away from the iron-door landing so the entrance remains clear.
(H) Exterior stair — Attach the steep concrete stair to the rooftop terrace landing below the iron-door side, rising up from the villa yard/alley approach.
(I) Alley approach — Draw the narrow wet alley and small villa-yard/back-corner approach at the foot of the exterior stair, leaving space for a parked vehicle beside the alley.
(J) Neighbor roofs — Frame the rooftop terrace with adjacent flat villa roof planes and tight surrounding blocks, outside the main rooftop site.

On the RIGHT side of the image, add a clean legend panel listing each
circled letter with its English name in small neat capital letters:
A: ROOFTOP ROOM, B: IRON DOOR, C: EXTERIOR WINDOWS, D: INNER DOORWAYS, E: ROOFTOP TERRACE, F: LOW WALL, G: ROOF FIXTURES, H: EXTERIOR STAIR, I: ALLEY APPROACH, J: NEIGHBOR ROOFS

The circled letters and the legend panel are the ONLY text and the ONLY
circular marks allowed. No other labels, numbers, logos or watermarks.
Include a modest margin of the immediate surroundings so the place reads
in context; keep geometry simple, unambiguous and physically plausible.
R-B 배치도 I2I (1-2라운드 뿌리 — 틀린 기하 상속) gpt-image-2 · 163.9s
prompt/refs (실제 호출 기록)
ONE hand-drawn TOP-DOWN aerial SITE SKETCH of a single real-world place,
in clean technical sketch style: dark ink outlines, light flat colour
washes, straight-down view. NOT a photograph, NOT a 3D render, no
perspective, no photo textures.

The place consists of these connected parts — draw them TOGETHER as one
coherent site (one main structure plus its immediate surroundings):
- (outdoor, L03) 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)
- (indoor, L04) 옥탑방 내부: 작은 창문으로 빛이 들어오는 낡은 주거 공간. 싱크대, 식탁, TV가 있는 거실과 침대, 커튼, 거울 등이 있는 방/욕실로 구성된다. 약초 끓이는 냄비 등 생활 소품이 있으며, 간헐적으로 벽면에 붉은 원 형태의 환영과 핏자국이 생겨난다. (특징: 작은 창문의 햇살; 싱크대와 약초(석창포); 가스레인지 위 끓는 냄비와 수증기; 거실 TV와 스탠드; 침대, 커튼, 거울; 벽과 거울 표면에 나타나는 붉은 원 환영; 바닥과 벽의 핏자국 (특정 시점); 어지럽혀진 가재도구 (특정 시점))
- (outdoor, L10) 옥탑방 외곽 골목·시멘트 계단: 다세대 빌라 마당의 후미진 구석과 옥탑방으로 올라가는 가파르고 낡은 시멘트 계단. (특징: 다세대 빌라 입구 마당; 후미진 구석 공간; 낡고 가파른 시멘트 계단)

Overall massing/orientation guidance:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

Draw ONLY what is visible from above and from outside: the structure's
roof outline and what stands on top of it, open ground areas, approach
paths and stairs, and each opening (door, gate, window, level access) as
part of the boundary it belongs to. Do NOT draw any interior room layout
or interior furniture — buildings show their roof plane only.

Mark each of the following elements at its position with a small circle
containing its single capital letter:
(A) Rooftop room — Center the small roof outline on the rooftop terrace, with its entrance edge facing the terrace landing and exterior stair approach.
(B) Iron door — Place on the entrance edge of the rooftop-room outline, opening directly onto the rooftop terrace landing; mark the flyer at the door seam.
(C) Exterior windows — Draw window slots on the outer walls of the rooftop-room outline: one small/living window on a side wall visible from the terrace, and one curtained bedroom window on another outer wall.
(D) Inner doorways — Inside the rooftop-room roof outline, mark only abstract doorway openings for the bedroom and bathroom access; do not draw interior walls, rooms, or furniture.
(E) Rooftop terrace — Surround the rooftop-room outline with worn cement rooftop surface, widest in front of the iron door where the stair arrives.
(F) Low wall — Run along the exposed perimeter of the rooftop terrace, outside the room and beside the cat/window line of sight.
(G) Roof fixtures — Cluster the water tank, clothesline, and herb-drying platform on open terrace space away from the iron-door landing so the entrance remains clear.
(H) Exterior stair — Attach the steep concrete stair to the rooftop terrace landing below the iron-door side, rising up from the villa yard/alley approach.
(I) Alley approach — Draw the narrow wet alley and small villa-yard/back-corner approach at the foot of the exterior stair, leaving space for a parked vehicle beside the alley.
(J) Neighbor roofs — Frame the rooftop terrace with adjacent flat villa roof planes and tight surrounding blocks, outside the main rooftop site.

On the RIGHT side of the image, add a clean legend panel listing each
circled letter with its English name in small neat capital letters:
A: ROOFTOP ROOM, B: IRON DOOR, C: EXTERIOR WINDOWS, D: INNER DOORWAYS, E: ROOFTOP TERRACE, F: LOW WALL, G: ROOF FIXTURES, H: EXTERIOR STAIR, I: ALLEY APPROACH, J: NEIGHBOR ROOFS

The circled letters and the legend panel are the ONLY text and the ONLY
circular marks allowed. No other labels, numbers, logos or watermarks.
Include a modest margin of the immediate surroundings so the place reads
in context; keep geometry simple, unambiguous and physically plausible.

The attached image is the existing clean top-down site plan of this place. KEEP its geometry, proportions and layout EXACTLY — same structures, same openings, same surroundings. Restyle it into the hand-drawn sketch style described above and ADD the circled capital letters and the right-side legend panel. Change nothing else.
참조 이미지(역할 라벨 포함): aerial_bg_rooftop_unit.png
R-C fp_l03 기하 앵커 (3라운드) gpt-image-2 · 186.5s
prompt/refs (실제 호출 기록)
The FIRST attached image is the TOP-DOWN zone plan of one real place's
outdoor level. Its GEOMETRY is the absolute ground truth: keep every
boundary line, every zone's position, size and PROPORTION, the stair,
the fixtures and every opening EXACTLY where and how large the plan
puts them. Do not move, resize, mirror or re-arrange anything.

Redraw that exact layout as ONE hand-drawn TOP-DOWN aerial SITE SKETCH:
dark ink outlines with light flat colour washes, straight-down view,
NOT a photograph, NOT 3D. Translate each zone into its real surface:
an enclosed dwelling zone becomes that dwelling's plain ROOF PLANE
(never draw its interior rooms or furniture); open zones become the
worn open terrace surface; a service zone keeps its fixtures (tank,
laundry line) as drawn; a threshold/entry zone keeps its door and the
stair stays exactly where the plan places it.
The SECOND attached image is the dwelling's indoor floor plan — use it
ONLY to confirm the dwelling's outer boundary shape and where openings
sit on that boundary. Never draw any interior layout.

THE PLACE (production data):
- (outdoor, L03) 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)
- (indoor, L04) 옥탑방 내부: 작은 창문으로 빛이 들어오는 낡은 주거 공간. 싱크대, 식탁, TV가 있는 거실과 침대, 커튼, 거울 등이 있는 방/욕실로 구성된다. 약초 끓이는 냄비 등 생활 소품이 있으며, 간헐적으로 벽면에 붉은 원 형태의 환영과 핏자국이 생겨난다. (특징: 작은 창문의 햇살; 싱크대와 약초(석창포); 가스레인지 위 끓는 냄비와 수증기; 거실 TV와 스탠드; 침대, 커튼, 거울; 벽과 거울 표면에 나타나는 붉은 원 환영; 바닥과 벽의 핏자국 (특정 시점); 어지럽혀진 가재도구 (특정 시점))
- (outdoor, L10) 옥탑방 외곽 골목·시멘트 계단: 다세대 빌라 마당의 후미진 구석과 옥탑방으로 올라가는 가파르고 낡은 시멘트 계단. (특징: 다세대 빌라 입구 마당; 후미진 구석 공간; 낡고 가파른 시멘트 계단)

Mark each of the following elements at its position with a small circle
containing its single capital letter:
(A) Rooftop room — Center the small roof outline on the rooftop terrace, with its entrance edge facing the terrace landing and exterior stair approach.
(B) Iron door — Place on the entrance edge of the rooftop-room outline, opening directly onto the rooftop terrace landing; mark the flyer at the door seam.
(C) Exterior windows — Draw window slots on the outer walls of the rooftop-room outline: one small/living window on a side wall visible from the terrace, and one curtained bedroom window on another outer wall.
(D) Inner doorways — Inside the rooftop-room roof outline, mark only abstract doorway openings for the bedroom and bathroom access; do not draw interior walls, rooms, or furniture.
(E) Rooftop terrace — Surround the rooftop-room outline with worn cement rooftop surface, widest in front of the iron door where the stair arrives.
(F) Low wall — Run along the exposed perimeter of the rooftop terrace, outside the room and beside the cat/window line of sight.
(G) Roof fixtures — Cluster the water tank, clothesline, and herb-drying platform on open terrace space away from the iron-door landing so the entrance remains clear.
(H) Exterior stair — Attach the steep concrete stair to the rooftop terrace landing below the iron-door side, rising up from the villa yard/alley approach.
(I) Alley approach — Draw the narrow wet alley and small villa-yard/back-corner approach at the foot of the exterior stair, leaving space for a parked vehicle beside the alley.
(J) Neighbor roofs — Frame the rooftop terrace with adjacent flat villa roof planes and tight surrounding blocks, outside the main rooftop site.

On the RIGHT side of the image, add a clean legend panel listing each
circled letter with its English name in small neat capital letters:
A: ROOFTOP ROOM, B: IRON DOOR, C: EXTERIOR WINDOWS, D: INNER DOORWAYS, E: ROOFTOP TERRACE, F: LOW WALL, G: ROOF FIXTURES, H: EXTERIOR STAIR, I: ALLEY APPROACH, J: NEIGHBOR ROOFS

Replace the plan's zone captions and numbers — the circled letters and
the legend panel are the ONLY text and the ONLY circular marks allowed.
Add a modest margin of the immediate surroundings (neighbouring roofs,
the alley the stair descends into) so the place reads in context.
참조 이미지(역할 라벨 포함): fp_l03_rooftop_entry_main.png fp_l04_rooftop_room_main.png
R1 요소 선정 JSON (뿌리 텍스트 계약)
{
 "coverage": [
  {
   "element_ids": [
    "B"
   ],
   "shot_key": "S10_Shot5"
  },
  {
   "element_ids": [
    "C",
    "D"
   ],
   "shot_key": "S10_Shot6"
  },
  {
   "element_ids": [
    "H",
    "E"
   ],
   "shot_key": "S11_Shot3"
  },
  {
   "element_ids": [
    "B",
    "E",
    "F"
   ],
   "shot_key": "S11_Shot4"
  },
  {
   "element_ids": [
    "D",
    "C"
   ],
   "shot_key": "S12_Shot15"
  },
  {
   "element_ids": [
    "D"
   ],
   "shot_key": "S12_Shot4"
  },
  {
   "element_ids": [
    "D"
   ],
   "shot_key": "S12_Shot8"
  },
  {
   "element_ids": [
    "I"
   ],
   "shot_key": "S13_Shot3"
  },
  {
   "element_ids": [
    "I"
   ],
   "shot_key": "S13_Shot5"
  },
  {
   "element_ids": [
    "D",
    "C"
   ],
   "shot_key": "S14_Shot4"
  },
  {
   "element_ids": [
    "D"
   ],
   "shot_key": "S14_Shot6"
  },
  {
   "element_ids": [
    "B",
    "C",
    "D"
   ],
   "shot_key": "S14_Shot8"
  },
  {
   "element_ids": [
    "C",
    "F",
    "E"
   ],
   "shot_key": "S17_Shot1"
  },
  {
   "element_ids": [
    "D"
   ],
   "shot_key": "S18_Shot15"
  },
  {
   "element_ids": [
    "B",
    "C",
    "D"
   ],
   "shot_key": "S18_Shot20"
  },
  {
   "element_ids": [
    "D",
    "C"
   ],
   "shot_key": "S18_Shot6"
  },
  {
   "element_ids": [
    "D"
   ],
   "shot_key": "S25_Shot4"
  },
  {
   "element_ids": [
    "B",
    "C",
    "E"
   ],
   "shot_key": "S25_Shot8"
  },
  {
   "element_ids": [
    "B",
    "C"
   ],
   "shot_key": "S27_Shot1"
  },
  {
   "element_ids": [
    "A",
    "J",
    "I"
   ],
   "shot_key": "S4_Shot1"
  },
  {
   "element_ids": [
    "B"
   ],
   "shot_key": "S5_Shot10"
  },
  {
   "element_ids": [
    "B"
   ],
   "shot_key": "S5_Shot12"
  },
  {
   "element_ids": [
    "B",
    "C"
   ],
   "shot_key": "S5_Shot3"
  }
 ],
 "elements": [
  {
   "category": "structure",
   "grounding": "L03 rooftop-room exterior; L04 interior is inside this roof outline; S4 aerial reveal centers on the old rooftop room.",
   "id": "A",
   "name_en": "Rooftop room",
   "placement": "Center the small roof outline on the rooftop terrace, with its entrance edge facing the terrace landing and exterior stair approach."
  },
  {
   "category": "opening",
   "grounding": "L03 iron front door with flyer; S10_Shot5, S11_Shot4, S25_Shot8, S27_Shot1, S5_Shot10, S5_Shot12 use the front-door seam, threshold, or entrance area.",
   "id": "B",
   "name_en": "Iron door",
   "placement": "Place on the entrance edge of the rooftop-room outline, opening directly onto the rooftop terrace landing; mark the flyer at the door seam."
  },
  {
   "category": "opening",
   "grounding": "L04 small window; S5_Shot3 small living-room window; S10_Shot6 room window reflection; S17_Shot1 lit rooftop-room window; S18_Shot6 bedroom window with curtains; S25_Shot8 and S27_Shot1 open/grimy living-room window.",
   "id": "C",
   "name_en": "Exterior windows",
   "placement": "Draw window slots on the outer walls of the rooftop-room outline: one small/living window on a side wall visible from the terrace, and one curtained bedroom window on another outer wall."
  },
  {
   "category": "opening",
   "grounding": "S12_Shot4, S14_Shot4, S18_Shot6 use the opened bedroom door; S18_Shot15 reaches the bathroom/mirror area; S12_Shot15, S25_Shot4 bedroom wall actions are interior actions located only by access openings.",
   "id": "D",
   "name_en": "Inner doorways",
   "placement": "Inside the rooftop-room roof outline, mark only abstract doorway openings for the bedroom and bathroom access; do not draw interior walls, rooms, or furniture."
  },
  {
   "category": "approach",
   "grounding": "L03 rooftop exterior has old cement floor; S11_Shot4 viewpoint from rooftop landing; S17_Shot1 cat moves along rooftop wall; S25_Shot8 exits into exterior dusk.",
   "id": "E",
   "name_en": "Rooftop terrace",
   "placement": "Surround the rooftop-room outline with worn cement rooftop surface, widest in front of the iron door where the stair arrives."
  },
  {
   "category": "structure",
   "grounding": "S11_Shot4 low rooftop wall; S17_Shot1 low concrete rooftop wall guiding the cat.",
   "id": "F",
   "name_en": "Low wall",
   "placement": "Run along the exposed perimeter of the rooftop terrace, outside the room and beside the cat/window line of sight."
  },
  {
   "category": "fixture",
   "grounding": "L03 lists water tank, wind-blown clothesline, flat drying platform, and dried medicinal herbs on the rooftop exterior.",
   "id": "G",
   "name_en": "Roof fixtures",
   "placement": "Cluster the water tank, clothesline, and herb-drying platform on open terrace space away from the iron-door landing so the entrance remains clear."
  },
  {
   "category": "approach",
   "grounding": "L10 old steep concrete stair to the rooftop room; S11_Shot3 close-up midway up the staircase.",
   "id": "H",
   "name_en": "Exterior stair",
   "placement": "Attach the steep concrete stair to the rooftop terrace landing below the iron-door side, rising up from the villa yard/alley approach."
  },
  {
   "category": "approach",
   "grounding": "L10 villa entrance yard, back corner, alley; S13_Shot3 and S13_Shot5 police-car/alley encounter; S4 aerial includes narrow alleys around the villa.",
   "id": "I",
   "name_en": "Alley approach",
   "placement": "Draw the narrow wet alley and small villa-yard/back-corner approach at the foot of the exterior stair, leaving space for a parked vehicle beside the alley."
  },
  {
   "category": "surround",
   "grounding": "S4 aerial reveal shows neighboring old villa rooftops and faded concrete blocks around the rooftop room.",
   "id": "J",
   "name_en": "Neighbor roofs",
   "placement": "Frame the rooftop terrace with adjacent flat villa roof planes and tight surrounding blocks, outside the main rooftop site."
  }
 ],
 "legend_order": [
  "A",
  "B",
  "C",
  "D",
  "E",
  "F",
  "G",
  "H",
  "I",
  "J"
 ],
 "sketch_notes": "Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers."
}
root_A VLM readback
{
 "interior_layout_exposed": false,
 "legend_entries": [
  "A ROOFTOP ROOM",
  "B IRON DOOR",
  "C EXTERIOR WINDOWS",
  "D INNER DOORWAYS",
  "E ROOFTOP TERRACE",
  "F LOW WALL",
  "G ROOF FIXTURES",
  "H EXTERIOR STAIR",
  "I ALLEY APPROACH",
  "J NEIGHBOR ROOFS"
 ],
 "letters_found": [
  "A",
  "B",
  "C",
  "D",
  "E",
  "F",
  "G",
  "H",
  "I",
  "J"
 ],
 "notes": "Circled capital letters visible on the sketch include A through J. The view is top-down of rooftops/terrace areas; no interior room layout is exposed."
}
root_B VLM readback
{
 "interior_layout_exposed": true,
 "legend_entries": [
  "A ROOFTOP ROOM",
  "B IRON DOOR",
  "C EXTERIOR WINDOWS",
  "D INNER DOORWAYS",
  "E ROOFTOP TERRACE",
  "F LOW WALL",
  "G ROOF FIXTURES",
  "H EXTERIOR STAIR",
  "I ALLEY APPROACH",
  "J NEIGHBOR ROOFS"
 ],
 "letters_found": [
  "A",
  "B",
  "C",
  "D",
  "E",
  "F",
  "G",
  "H",
  "I",
  "J"
 ],
 "notes": "Circled letters visible on the sketch include A through J. The rooftop room is shown from above with its inner doorways and wall/window placements visible, so an interior layout is exposed."
}
root_C VLM readback
{
 "interior_layout_exposed": false,
 "legend_entries": [
  "ROOFTOP ROOM",
  "IRON DOOR",
  "EXTERIOR WINDOWS",
  "INNER DOORWAYS",
  "ROOFTOP TERRACE",
  "LOW WALL",
  "ROOF FIXTURES",
  "EXTERIOR STAIR",
  "ALLEY APPROACH",
  "NEIGHBOR ROOFS"
 ],
 "letters_found": [
  "A",
  "B",
  "C",
  "D",
  "E",
  "F",
  "G",
  "H",
  "I",
  "J"
 ],
 "notes": "Circled letters A through J are visible. No interior room layout or partition plan is exposed; the sketch shows rooftop/site elements."
}

1.5 뿌리 v2 — 건물 전체 통합 도면 (4라운드, 사용자 재정의)

사용자 의도 반영: 옥탑방 레벨만이 아니라 건물 전체 — 지상 출입구/마당(인물 도착 지점), 외부 계단, 옥상 레벨 — 를 한 장 top-down 으로. 기하 앵커 = 그룹 실외 fp 전부(옥상+마당+계단, 이전 미사용이던 fp_l10 2장 포함).
root v2
R-v2 건물 전체 통합 도면 (실외 fp 3장 앵커) gpt-image-2 · 106.9s
prompt/refs (실제 호출 기록)
ONE hand-drawn TOP-DOWN aerial SITE PLAN of a single real-world
property, seen straight from above: dark ink outlines with light flat
colour washes. NOT a photograph, NOT 3D, no perspective.

Draw the WHOLE property in one coherent drawing:
- the full multi-storey BUILDING footprint (roof plane seen from above),
- the upper-level dwelling on that roof: its outline, terrace, fixtures
  (draw ONLY what its attached plan shows — never interior rooms),
- the exterior STAIR route connecting the ground to the top level,
- the GROUND level around the building: the yard/alley, the street-side
  building ENTRANCE and the approach path where people arrive,
- a modest margin of neighbouring structures and the street.
Make the levels readable from above: the building's roof edge/parapet
outline separates the top level from the ground around it; the stair
visibly connects them; the ground entrance sits on the building's
street side.

The attached images are the property's real top-down plans — compose
them into this ONE plan, keeping each part's geometry, proportions and
opening positions EXACTLY (do not move, resize, mirror or invent):
- attached image #1: top-down plan of one part of the property (its geometry for that part is ground truth)
- attached image #2: top-down plan of one part of the property (its geometry for that part is ground truth)
- attached image #3: top-down plan of one part of the property (its geometry for that part is ground truth)

THE PLACE (production data):
- (outdoor, L03) 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)
- (indoor, L04) 옥탑방 내부: 작은 창문으로 빛이 들어오는 낡은 주거 공간. 싱크대, 식탁, TV가 있는 거실과 침대, 커튼, 거울 등이 있는 방/욕실로 구성된다. 약초 끓이는 냄비 등 생활 소품이 있으며, 간헐적으로 벽면에 붉은 원 형태의 환영과 핏자국이 생겨난다. (특징: 작은 창문의 햇살; 싱크대와 약초(석창포); 가스레인지 위 끓는 냄비와 수증기; 거실 TV와 스탠드; 침대, 커튼, 거울; 벽과 거울 표면에 나타나는 붉은 원 환영; 바닥과 벽의 핏자국 (특정 시점); 어지럽혀진 가재도구 (특정 시점))
- (outdoor, L10) 옥탑방 외곽 골목·시멘트 계단: 다세대 빌라 마당의 후미진 구석과 옥탑방으로 올라가는 가파르고 낡은 시멘트 계단. (특징: 다세대 빌라 입구 마당; 후미진 구석 공간; 낡고 가파른 시멘트 계단)

Mark each element with a small circle containing its capital letter:
(A) Villa footprint — Main rectangular building mass in the center of the plan; draw the complete multi-storey footprint below the rooftop room and roof terrace, with no interior subdivisions.
(B) Arrival alley — Narrow exterior lane along the street-facing side of the villa footprint; leave space beside it for the vehicle stop and characters arriving before entering the property.
(C) Street entrance — Opening on the street-facing edge of the property, between the arrival alley and the ground entry yard; mark only the gate or doorway line, not any interior plan.
(D) Entry yard — Small ground-level court just inside the street entrance and beside the villa footprint, leading toward the more secluded stair corner.
(E) Rear corner — Darker, tucked ground-level corner at the far side of the entry yard, tight against the building footprint where the exterior stairs begin.
(F) Exterior stairs — Narrow stair run attached to the outside edge of the villa, rising from the rear corner up to the roof terrace landing; show as a continuous exterior route.
(G) Roof terrace — Open cement roof deck over the villa footprint, surrounding the upper room shell; include a low parapet boundary around the exposed edges and a clear landing at the stair top.
(H) Upper shell — Small enclosed rooftop dwelling outline set on the roof terrace, slightly offset within the villa roof; draw only the outer walls and roof outline, with no interior rooms or furniture.
(I) Iron door — Exterior opening on the side of the upper shell facing the roof terrace landing and stair arrival; show the door leaf swing/open state symbol outside the shell.
(J) Room windows — A small set of perimeter window openings on the upper shell walls, including one facing the roof terrace/parapet line; mark only openings in the outer walls.
(K) Roof fixtures — Clustered on the open roof terrace away from the iron door path: water tank near one roof edge, clothesline spanning open space, and low drying platform on the cement surface.
(L) Neighbor blocks — Simplified adjacent building and roof outlines around the property margin, outside the arrival alley and beyond the villa footprint, kept secondary to the main site.

On the RIGHT side, add a clean legend panel listing each circled letter
with its English name in small neat capital letters:
A: VILLA FOOTPRINT, B: ARRIVAL ALLEY, C: STREET ENTRANCE, D: ENTRY YARD, E: REAR CORNER, F: EXTERIOR STAIRS, G: ROOF TERRACE, H: UPPER SHELL, I: IRON DOOR, J: ROOM WINDOWS, K: ROOF FIXTURES, L: NEIGHBOR BLOCKS

The circled letters and the legend are the ONLY text and the ONLY
circular marks allowed. No zone captions, no numbers, no other labels.
참조 이미지(역할 라벨 포함): fp_l03_rooftop_entry_main.png fp_l10_cement_stairs.png fp_l10_exterior_alley.png
R1v2 요소 선정 JSON
{
 "coverage": [
  {
   "element_ids": [
    "G",
    "H",
    "I"
   ],
   "shot_key": "S10_Shot5"
  },
  {
   "element_ids": [
    "H",
    "J"
   ],
   "shot_key": "S10_Shot6"
  },
  {
   "element_ids": [
    "D",
    "E",
    "F",
    "G"
   ],
   "shot_key": "S11_Shot3"
  },
  {
   "element_ids": [
    "F",
    "G",
    "H",
    "I"
   ],
   "shot_key": "S11_Shot4"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S12_Shot15"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S12_Shot4"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S12_Shot8"
  },
  {
   "element_ids": [
    "B",
    "C",
    "D",
    "A"
   ],
   "shot_key": "S13_Shot3"
  },
  {
   "element_ids": [
    "B",
    "C",
    "D"
   ],
   "shot_key": "S13_Shot5"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S14_Shot4"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S14_Shot6"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S14_Shot8"
  },
  {
   "element_ids": [
    "G",
    "H",
    "J"
   ],
   "shot_key": "S17_Shot1"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S18_Shot15"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S18_Shot20"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S18_Shot6"
  },
  {
   "element_ids": [
    "H"
   ],
   "shot_key": "S25_Shot4"
  },
  {
   "element_ids": [
    "H",
    "I",
    "G"
   ],
   "shot_key": "S25_Shot8"
  },
  {
   "element_ids": [
    "H",
    "I",
    "J"
   ],
   "shot_key": "S27_Shot1"
  },
  {
   "element_ids": [
    "A",
    "G",
    "H",
    "L",
    "B"
   ],
   "shot_key": "S4_Shot1"
  },
  {
   "element_ids": [
    "H",
    "I"
   ],
   "shot_key": "S5_Shot10"
  },
  {
   "element_ids": [
    "H",
    "I"
   ],
   "shot_key": "S5_Shot12"
  },
  {
   "element_ids": [
    "H",
    "J"
   ],
   "shot_key": "S5_Shot3"
  }
 ],
 "elements": [
  {
   "category": "structure",
   "grounding": "Full old multi-unit villa required by place text; aerial exterior in S4_Shot1; ground-to-roof relation in L10 and rooftop location in L03.",
   "id": "A",
   "name_en": "Villa footprint",
   "placement": "Main rectangular building mass in the center of the plan; draw the complete multi-storey footprint below the rooftop room and roof terrace, with no interior subdivisions."
  },
  {
   "category": "approach",
   "grounding": "Narrow alley and arrival space in S13_Shot3, S13_Shot5; surrounding alleys in S4_Shot1; L10 exterior alley context.",
   "id": "B",
   "name_en": "Arrival alley",
   "placement": "Narrow exterior lane along the street-facing side of the villa footprint; leave space beside it for the vehicle stop and characters arriving before entering the property."
  },
  {
   "category": "opening",
   "grounding": "Building street-side entrance and approach path required by prompt; villa entrance yard in L10; alley-to-yard arrival in S13 shots.",
   "id": "C",
   "name_en": "Street entrance",
   "placement": "Opening on the street-facing edge of the property, between the arrival alley and the ground entry yard; mark only the gate or doorway line, not any interior plan."
  },
  {
   "category": "approach",
   "grounding": "Multi-unit villa entrance yard in L10; approach from alley before the stair route; connects S13 exterior approach to S11 stair climb.",
   "id": "D",
   "name_en": "Entry yard",
   "placement": "Small ground-level court just inside the street entrance and beside the villa footprint, leading toward the more secluded stair corner."
  },
  {
   "category": "approach",
   "grounding": "Secluded corner space in L10, described as the tucked-away base area near the stairs.",
   "id": "E",
   "name_en": "Rear corner",
   "placement": "Darker, tucked ground-level corner at the far side of the entry yard, tight against the building footprint where the exterior stairs begin."
  },
  {
   "category": "approach",
   "grounding": "Steep old cement stairs in L10; close-up midway on stairs in S11_Shot3; route to rooftop landing in S11_Shot4.",
   "id": "F",
   "name_en": "Exterior stairs",
   "placement": "Narrow stair run attached to the outside edge of the villa, rising from the rear corner up to the roof terrace landing; show as a continuous exterior route."
  },
  {
   "category": "structure",
   "grounding": "Rooftop exterior space in L03; rooftop landing darkness and low rooftop wall in S11_Shot4; cat tracking along rooftop wall in S17_Shot1.",
   "id": "G",
   "name_en": "Roof terrace",
   "placement": "Open cement roof deck over the villa footprint, surrounding the upper room shell; include a low parapet boundary around the exposed edges and a clear landing at the stair top."
  },
  {
   "category": "structure",
   "grounding": "Rooftop room exterior in L03 and S4_Shot1; all L04 indoor action is contained within this upper dwelling; no interior floor plan is exposed.",
   "id": "H",
   "name_en": "Upper shell",
   "placement": "Small enclosed rooftop dwelling outline set on the roof terrace, slightly offset within the villa roof; draw only the outer walls and roof outline, with no interior rooms or furniture."
  },
  {
   "category": "opening",
   "grounding": "Iron front door with flyer in L03; door seam in S10_Shot5; half-open rooftop door in S11_Shot4; entry/exit threshold in S25_Shot8; entrance area in S5 shots and S27_Shot1.",
   "id": "I",
   "name_en": "Iron door",
   "placement": "Exterior opening on the side of the upper shell facing the roof terrace landing and stair arrival; show the door leaf swing/open state symbol outside the shell."
  },
  {
   "category": "opening",
   "grounding": "Small window in L04; reflected window action in S10_Shot6; lit rooftop-room window in S17_Shot1; living-room/window references in S5_Shot3, S25_Shot8, S27_Shot1.",
   "id": "J",
   "name_en": "Room windows",
   "placement": "A small set of perimeter window openings on the upper shell walls, including one facing the roof terrace/parapet line; mark only openings in the outer walls."
  },
  {
   "category": "fixture",
   "grounding": "Rooftop water tank, clothesline, drying platform and medicinal herbs in L03; rooftop exterior domestic texture across L03 shots.",
   "id": "K",
   "name_en": "Roof fixtures",
   "placement": "Clustered on the open roof terrace away from the iron door path: water tank near one roof edge, clothesline spanning open space, and low drying platform on the cement surface."
  },
  {
   "category": "surround",
   "grounding": "Neighboring old villa rooftops and cramped urban grid in S4_Shot1; modest immediate surroundings required by prompt.",
   "id": "L",
   "name_en": "Neighbor blocks",
   "placement": "Simplified adjacent building and roof outlines around the property margin, outside the arrival alley and beyond the villa footprint, kept secondary to the main site."
  }
 ],
 "legend_order": [
  "A",
  "B",
  "C",
  "D",
  "E",
  "F",
  "G",
  "H",
  "I",
  "J",
  "K",
  "L"
 ],
 "sketch_notes": "Draw one composite top-down plan of the whole property. Use the villa footprint as the base layer, the ground approach along one street-facing side, and the roof terrace/upper shell overlaid on the roof level. The exterior stairs must visibly connect the ground rear corner to the roof terrace landing. Do not draw any interior room divisions, interior furniture, blood marks, mirrors, beds, tables, or appliances; indoor scenes are located only by the upper shell plus its boundary openings. Add only a modest border of neighboring blocks and alley space."
}
root_v2 VLM readback
{
 "interior_layout_exposed": false,
 "legend_entries": [
  "A VILLA FOOTPRINT",
  "B ARRIVAL ALLEY",
  "C STREET ENTRANCE",
  "D ENTRY YARD",
  "E REAR CORNER",
  "F EXTERIOR STAIRS",
  "G ROOF TERRACE",
  "H UPPER SHELL",
  "I IRON DOOR",
  "J ROOM WINDOWS",
  "K ROOF FIXTURES",
  "L NEIGHBOR BLOCKS"
 ],
 "letters_found": [
  "B",
  "C",
  "D",
  "E",
  "F",
  "G",
  "H",
  "I",
  "J",
  "K",
  "L"
 ],
 "notes": "Circled capital letters visible on the plan are B through L; A appears only in the legend. No interior room layout is exposed, only exterior/roof/site elements are shown."
}

실외샷 (무마킹·무인) — S11_Shot4 loc=L10

옥상 위, 어둠 속에 반쯤 열려 멈춰 있는 옥탑방 현관 철문의 정적 구도.

root v2 → camview → 빈 plate
camview 라인아트 (마킹 없음, staging 텍스트) gpt-image-2 · 115.1s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN site plan of one real property
(circled letters are site markers, never people).

Draw the clean LINE-ART sketch of the EYE-LEVEL view described below:
thin dark ink lines on plain white, no colour, no shading. The camera
stands ON the ground INSIDE the scene at human eye height (about
1.6 m) — NOT above it. Correct perspective at real-world human scale,
horizon at natural eye level. Show the structures, surfaces, openings
and approaches the plan places in front of that camera.
No people, no text, no letters, no circles — pure line drawing.

CAMERA (from production staging):
After the hard eyeline cut, the camera adopts 수리영’s direct viewpoint from the rooftop landing, several meters from the entrance and at human eye level, facing the iron front door squarely. The half-open door is held in rigid symmetry at the center of the frame, surrounded by still rooftop darkness, with no figure entering to relieve the threat.
CAMERA: After the hard eyeline cut, the camera adopts 수리영’s direct viewpoint from the rooftop landing, several meters from the entrance and at human eye level, facing the iron front door squarely. The half-open door is held in rigid symmetry at the center of the frame, surrounded by still rooftop darkness, with no figure entering to relieve the threat.
FRAMING: wide
LIGHTING: Muted moon-blue darkness surrounds the door, with a thin sickly amber leak from inside making the opening feel contaminated rather than welcoming.
SPATIAL CONSTRAINTS: [{"depth_plane": "background", "gesture_action": "none", "gesture_target_label": "", "label": "half-open rooftop iron door", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]
참조 이미지(역할 라벨 포함): root_v2.png
빈 배경 plate (무인·무마커) gpt-image-2 · 114.3s
prompt/refs (실제 호출 기록)
The FIRST attached image is a LINE-ART sketch of one camera's
eye-level view of a real outdoor place — composition and perspective
ground truth. The SECOND attached image is the property's top-down
site plan — use it ONLY for spatial relations and fixtures; never
copy its top-down viewpoint or markers.

Render the PHOTOREALISTIC EMPTY view exactly as the line-art frames
it: same framing, perspective, structures, real-world human scale.
Completely unpopulated — no people, no figures. No text, letters,
circles, arrows or sketch lines. Pure photographic realism, natural
weathered materials.

WHAT THIS PLACE LOOKS LIKE (production data):
- 옥탑방 외곽 골목·시멘트 계단: 다세대 빌라 마당의 후미진 구석과 옥탑방으로 올라가는 가파르고 낡은 시멘트 계단. (특징: 다세대 빌라 입구 마당; 후미진 구석 공간; 낡고 가파른 시멘트 계단)

CAMERA: After the hard eyeline cut, the camera adopts 수리영’s direct viewpoint from the rooftop landing, several meters from the entrance and at human eye level, facing the iron front door squarely. The half-open door is held in rigid symmetry at the center of the frame, surrounded by still rooftop darkness, with no figure entering to relieve the threat.
FRAMING: wide
LIGHTING: Muted moon-blue darkness surrounds the door, with a thin sickly amber leak from inside making the opening feel contaminated rather than welcoming.
SPATIAL CONSTRAINTS: [{"depth_plane": "background", "gesture_action": "none", "gesture_target_label": "", "label": "half-open rooftop iron door", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
참조 이미지(역할 라벨 포함): sketch.png root_v2.png

2. 실내 탑레이어 배경 (zone/material master)

판정: 재질/무드 연속(체이닝 성공) but TL2 가 TL1 구도까지 복사(구도 수렴) — 침실 마스터 부재. 하류는 fpvar 가 카메라 SOT 를 쥐고 있어 버텨냄.
탑레이어 (생성 순서)
TL1 1번째 마스터 (fp 첨부=LLM 판단 ON) gpt-image-2 · 139.3s
prompt/refs (실제 호출 기록)
Create ONE photorealistic EMPTY interior master background plate of a
real dwelling interior — a wide, clean view with NO people, no text, no
markers. Real-world human scale (doorways adult height).

THE PLACE (from production data): 옥탑방 내부: 작은 창문으로 빛이 들어오는 낡은 주거 공간. 싱크대, 식탁, TV가 있는 거실과 침대, 커튼, 거울 등이 있는 방/욕실로 구성된다. 약초 끓이는 냄비 등 생활 소품이 있으며, 간헐적으로 벽면에 붉은 원 형태의 환영과 핏자국이 생겨난다. (특징: 작은 창문의 햇살; 싱크대와 약초(석창포); 가스레인지 위 끓는 냄비와 수증기; 거실 TV와 스탠드; 침대, 커튼, 거울; 벽과 거울 표면에 나타나는 붉은 원 환영; 바닥과 벽의 핏자국 (특정 시점); 어지럽혀진 가재도구 (특정 시점))
THIS PLATE'S PURPOSE: Cover all bedroom and bathroom-access shots: clean bedroom evidence views, doorway/gap views, bed-wall occult-surface views, curtain/bed close backgrounds, and the bathroom mirror reflection setup.
THE VIEW: A wide, clean, empty-room master from the inner doorway side of the bedroom/bathroom zone, eye level, showing the opened bedroom doorway alignment, the made bed position, the bare dark wall above the bed, the clean floor, the curtained bedroom window, and a bathroom/mirror access area with damp tile/mirror geometry readable at the edge or as a connected secondary sightline. No blood, red circles, pinned photographs, hallucination marks, bodies, or scattered debris.

Site orientation notes from the aerial root contract:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

The FIRST attached image is the TOP-DOWN floor plan of this dwelling — use it ONLY to get the room geometry, openings and furniture positions right. NEVER copy its drawing style, numbered circles or any marks into the photorealistic output.
참조 이미지(역할 라벨 포함): fp_l04_rooftop_room_main.png
TL1' 강제 fp OFF 비교쌍 gpt-image-2 · 104.9s
prompt/refs (실제 호출 기록)
Create ONE photorealistic EMPTY interior master background plate of a
real dwelling interior — a wide, clean view with NO people, no text, no
markers. Real-world human scale (doorways adult height).

THE PLACE (from production data): 옥탑방 내부: 작은 창문으로 빛이 들어오는 낡은 주거 공간. 싱크대, 식탁, TV가 있는 거실과 침대, 커튼, 거울 등이 있는 방/욕실로 구성된다. 약초 끓이는 냄비 등 생활 소품이 있으며, 간헐적으로 벽면에 붉은 원 형태의 환영과 핏자국이 생겨난다. (특징: 작은 창문의 햇살; 싱크대와 약초(석창포); 가스레인지 위 끓는 냄비와 수증기; 거실 TV와 스탠드; 침대, 커튼, 거울; 벽과 거울 표면에 나타나는 붉은 원 환영; 바닥과 벽의 핏자국 (특정 시점); 어지럽혀진 가재도구 (특정 시점))
THIS PLATE'S PURPOSE: Cover all bedroom and bathroom-access shots: clean bedroom evidence views, doorway/gap views, bed-wall occult-surface views, curtain/bed close backgrounds, and the bathroom mirror reflection setup.
THE VIEW: A wide, clean, empty-room master from the inner doorway side of the bedroom/bathroom zone, eye level, showing the opened bedroom doorway alignment, the made bed position, the bare dark wall above the bed, the clean floor, the curtained bedroom window, and a bathroom/mirror access area with damp tile/mirror geometry readable at the edge or as a connected secondary sightline. No blood, red circles, pinned photographs, hallucination marks, bodies, or scattered debris.

Site orientation notes from the aerial root contract:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.
TL2 2번째 마스터 (TL1 체이닝) gpt-image-2 · 145.9s
prompt/refs (실제 호출 기록)
Create ONE photorealistic EMPTY interior master background plate of a
real dwelling interior — a wide, clean view with NO people, no text, no
markers. Real-world human scale (doorways adult height).

THE PLACE (from production data): 옥탑방 내부: 작은 창문으로 빛이 들어오는 낡은 주거 공간. 싱크대, 식탁, TV가 있는 거실과 침대, 커튼, 거울 등이 있는 방/욕실로 구성된다. 약초 끓이는 냄비 등 생활 소품이 있으며, 간헐적으로 벽면에 붉은 원 형태의 환영과 핏자국이 생겨난다. (특징: 작은 창문의 햇살; 싱크대와 약초(석창포); 가스레인지 위 끓는 냄비와 수증기; 거실 TV와 스탠드; 침대, 커튼, 거울; 벽과 거울 표면에 나타나는 붉은 원 환영; 바닥과 벽의 핏자국 (특정 시점); 어지럽혀진 가재도구 (특정 시점))
THIS PLATE'S PURPOSE: Cover the living, dining, kitchen, and entrance shots: side dining-table pointing view, tabletop photo inserts, exit through the front door, ransacked living-room phone view, entryway embrace/wrist insert, and kitchen-to-TV domestic view.
THE VIEW: A wide, clean, empty-room master of the compact rooftop-room living/kitchen/entry zone, chained to the same dwelling and materials as the bedroom master: from an interior corner at chest height looking diagonally across the sink and small living-room window toward the dining table, living-room TV direction, stand lamp, narrow entry wall, shoe area, front door seam, and threshold. Keep the space worn and dim with small-window light, but do not include blood, red circles, hallucinated photo distortion, overturned chairs, or ransacked debris in the clean top layer.

Site orientation notes from the aerial root contract:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

The LAST attached image shows ANOTHER part of THE SAME dwelling —
match its wall colours, floor material, trim, door style, lighting
mood and renovation age EXACTLY so both read as the same home. Do
NOT copy its camera angle or composition.

The FIRST attached image is the TOP-DOWN floor plan of this dwelling — use it ONLY to get the room geometry, openings and furniture positions right. NEVER copy its drawing style, numbered circles or any marks into the photorealistic output.
참조 이미지(역할 라벨 포함): fp_l04_rooftop_room_main.png TL1_bedroom_bathroom.png
I0 실내 계획 JSON (배경 리스팅→탑레이어 병합/순서/fp판단)
{
 "shot_assignments": [
  {
   "needed_background": "Bedroom wall area from low bedside height looking upward/straight toward the dark wall above the bed, with only a thin bed edge as scale; this shot later adds the red circular mark as shot-specific content.",
   "shot_key": "S12_Shot15",
   "top_layer_key": "TL1_bedroom_bathroom"
  },
  {
   "needed_background": "Bedroom doorway view from outside the room, low waist height, looking through an opened door gap to the floor just beyond the threshold; blood is shot-specific and should not be in the clean master.",
   "shot_key": "S12_Shot4",
   "top_layer_key": "TL1_bedroom_bathroom"
  },
  {
   "needed_background": "Dark bedroom recess and a narrow bedroom doorway edge behind a close face, viewed from directly in front at eye level; only minimal room edges are needed.",
   "shot_key": "S12_Shot8",
   "top_layer_key": "TL1_bedroom_bathroom"
  },
  {
   "needed_background": "Wide clean bedroom view from just inside the bedroom doorway at eye level, looking inward toward the bed, bare wall above it, curtain line, and spotless floor.",
   "shot_key": "S14_Shot4",
   "top_layer_key": "TL1_bedroom_bathroom"
  },
  {
   "needed_background": "Bedroom interior near the bed and curtain side, frontal close background with a blank wall, bed corner, and curtain edge behind/around the character.",
   "shot_key": "S14_Shot6",
   "top_layer_key": "TL1_bedroom_bathroom"
  },
  {
   "needed_background": "Living/dining area from chest height beside the dining table, side-on to the table, with bare tabletop, living-room wall/doorway depth, and a stand lamp in the background.",
   "shot_key": "S14_Shot8",
   "top_layer_key": "TL2_living_kitchen_entry"
  },
  {
   "needed_background": "Bathroom mirror area from eye level about three feet from the mirror, tightened on the mirror reflecting the rear bathroom wall and damp tile context; the red circle in reflection is shot-specific.",
   "shot_key": "S18_Shot15",
   "top_layer_key": "TL1_bedroom_bathroom"
  },
  {
   "needed_background": "Dining tabletop insert context at table height, showing the table surface/edge for a framed photograph close-up; the distorted photo content is shot-specific.",
   "shot_key": "S18_Shot20",
   "top_layer_key": "TL2_living_kitchen_entry"
  },
  {
   "needed_background": "Wide clean bedroom view from just outside the room, eye level, looking straight through the opened bedroom door toward the made bed, smooth floor, and curtained window.",
   "shot_key": "S18_Shot6",
   "top_layer_key": "TL1_bedroom_bathroom"
  },
  {
   "needed_background": "Bedroom wall close view nearly perpendicular to a rough/torn wall area where a red circular wall mark and pinned photograph will be added as shot-specific details.",
   "shot_key": "S25_Shot4",
   "top_layer_key": "TL1_bedroom_bathroom"
  },
  {
   "needed_background": "Interior-wide view from inside the rooftop room looking toward the open front-door threshold, including living/dining disorder zones and the open living-room window; debris and overturned chairs are shot-specific dressing over the clean master.",
   "shot_key": "S25_Shot8",
   "top_layer_key": "TL2_living_kitchen_entry"
  },
  {
   "needed_background": "Ransacked living-room medium background at chest height, with entrance door, small grimy window, and general clutter zones behind the seated/standing character; the mess is shot-specific dressing over the clean master.",
   "shot_key": "S27_Shot1",
   "top_layer_key": "TL2_living_kitchen_entry"
  },
  {
   "needed_background": "Narrow entrance area side-on at shoulder height, compressed along the wall, showing worn entrance wall, entryway shoe area, and front door seam.",
   "shot_key": "S5_Shot10",
   "top_layer_key": "TL2_living_kitchen_entry"
  },
  {
   "needed_background": "Very close entrance insert background behind a wrist, with the entryway falling into warm-gray blur; only the entrance background tone and depth are needed.",
   "shot_key": "S5_Shot12",
   "top_layer_key": "TL2_living_kitchen_entry"
  },
  {
   "needed_background": "Kitchen-to-living view from near the sink and small window at chest height, looking across the counter line toward the living-room TV area, with sink/herb area, pot/steam zone, small window, and TV glow direction.",
   "shot_key": "S5_Shot3",
   "top_layer_key": "TL2_living_kitchen_entry"
  }
 ],
 "top_layers": [
  {
   "attach_fp": true,
   "attach_fp_reason": "Helpful for geometry anchoring because multiple shots depend on the relationship between bedroom doorway, bed, wall above bed, curtained window, and bathroom/mirror access. The plan is for the same indoor location and can keep openings consistent; style leakage risk is limited if used only as a layout guide, since the master must remain an empty-room photographic view without blood, marks, or extra invented objects.",
   "chain_prev_key": null,
   "key": "TL1_bedroom_bathroom",
   "loc_id": "L04",
   "order": 1,
   "purpose": "Cover all bedroom and bathroom-access shots: clean bedroom evidence views, doorway/gap views, bed-wall occult-surface views, curtain/bed close backgrounds, and the bathroom mirror reflection setup.",
   "view_description": "A wide, clean, empty-room master from the inner doorway side of the bedroom/bathroom zone, eye level, showing the opened bedroom doorway alignment, the made bed position, the bare dark wall above the bed, the clean floor, the curtained bedroom window, and a bathroom/mirror access area with damp tile/mirror geometry readable at the edge or as a connected secondary sightline. No blood, red circles, pinned photographs, hallucination marks, bodies, or scattered debris."
  },
  {
   "attach_fp": true,
   "attach_fp_reason": "Helpful for geometry anchoring because the shots need consistent placement of the front door/threshold, narrow entry wall, dining table, living-room wall/doorway, stand lamp, small window, sink, gas-stove/pot area, and TV direction within one compact rooftop room. It should be used only for spatial layout; the generated style should come from the shot descriptions, not from plan graphics.",
   "chain_prev_key": "TL1_bedroom_bathroom",
   "key": "TL2_living_kitchen_entry",
   "loc_id": "L04",
   "order": 2,
   "purpose": "Cover the living, dining, kitchen, and entrance shots: side dining-table pointing view, tabletop photo inserts, exit through the front door, ransacked living-room phone view, entryway embrace/wrist insert, and kitchen-to-TV domestic view.",
   "view_description": "A wide, clean, empty-room master of the compact rooftop-room living/kitchen/entry zone, chained to the same dwelling and materials as the bedroom master: from an interior corner at chest height looking diagonally across the sink and small living-room window toward the dining table, living-room TV direction, stand lamp, narrow entry wall, shoe area, front door seam, and threshold. Keep the space worn and dim with small-window light, but do not include blood, red circles, hallucinated photo distortion, overturned chairs, or ransacked debris in the clean top layer."
  }
 ]
}

3. 실내 샷별 체인

판정: 전 경로 성립 — fp 기하 정합, 정체성 교차샷 일관, 마커/마네킹 누출 0.

S14_Shot4 loc=L04 · framing=wide · 인물=없음

핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.

생성 순서 ① control/임시
fp변형 (카메라 콘+인물 서클) [CONTROL] gpt-image-2 · 146.8s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN floor plan of one dwelling: numbered circles mark fixed rooms and furniture. Keep the plan EXACTLY as it is — same walls, rooms, furniture and numbered circles, do not redraw or restyle anything.
ADD exactly these annotations for ONE camera setup:
- ONE green camera icon with a green triangular view-CONE showing where the camera stands and what it looks at, following this staging description:
Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
- This shot has NO people — add no lettered circles.
Add NOTHING else — no new rooms, no new furniture, no text other than the existing numbers and the new capital letters.
참조 이미지(역할 라벨 포함): fp_l04_rooftop_room_main.png
임시샷 β (ENV=탑레이어+CONTROL) nb2 · 17.6s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → TL1_bedroom_bathroom.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → fpvar.png
②' 임시배경 α (실험변수) gpt-image-2 · 144.6s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY interior background seen by the
camera marked on the attached top-down diagram (green icon+cone),
at eye level, real-world scale. Use the other attached image as the
material/lighting ground truth of the same dwelling. NO people, no
text, no markers.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.
참조 이미지(역할 라벨 포함): fpvar.png TL1_bedroom_bathroom.png
②'' 임시샷 α (ENV=임시배경) nb2 · 16.1s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → temp_bg.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → fpvar.png
윤곽 (temp→라인아트) gpt-image-2 · 122.4s
prompt/refs (실제 호출 기록)
Convert the attached photograph into a clean LINE-ART CONTOUR drawing: thin dark ink lines on a plain white background. Preserve the EXACT composition, framing, perspective and proportions — trace the outline of every structure, surface edge and human figure as it appears. No shading, no colour fills, no photo texture, no text, no added or removed objects.
참조 이미지(역할 라벨 포함): temp.png
경로 A — 직행 (temp 없이 최종)
A 최종샷 (ENV+CONTROL+passport) nb2 · 15.9s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → TL1_bedroom_bathroom.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → fpvar.png
경로 B — 임시샷→VLM 구도 텍스트→배경 재생성→최종
B1 재생성 배경 (VLM comp 기반) gpt-image-2 · 123.4s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "Straight-on view into a bedroom from an adjacent darker doorway/corridor; optical axis aimed almost perpendicular to the back wall/curtain wall, with slight rightward reveal of the room’s right wall and bed.", "height": "Approximately standing eye/chest height, around 1.4–1.6 m; high enough to see the bed top and floor expanse, but below the ceiling line. Camera is level, not noticeably tilted.", "lens_feel": "Wide, panoramic/anamorphic-feeling frame with rectilinear perspective; moderate-wide lens, deep focus, symmetrical architectural composition with strong vertical doorway borders."}, "empty_background_requirements": "The empty plate must be the same locked-off doorway view with no people: dark foreground door jambs/walls framing both far left and far right edges; the open warm-lit wooden door and door frame on the left; the blue-gray bedroom walls, ceiling, crown molding, baseboards, wood floorboards, central full-height curtains and black curtain rod with finials; the single bed on the right with wooden headboard, blue-gray blanket, pillow, visible bed legs/shadow; identical cool ambient light in the bedroom and warm spill from the left doorway. Since there are no people in the provided still, the plate is effectively the complete visible room as shown, preserving all furniture, curtains, shadows, reflections, and floor contact areas for any later insertion.", "horizon_and_depth": "Horizon/eye line is roughly mid-to-upper frame, around the curtain rod/upper wall zone implied by level verticals; the room is organized in layered depth: very near dark doorway frame in foreground, left open door slightly deeper, broad empty floor plane leading to the back curtain wall, and bed occupying the right mid/back plane. Strong depth is created by converging floorboard seams and side-wall/baseboard lines toward the back wall, while the back curtain plane remains mostly flat and frontal.", "major_surfaces": ["Foreground dark doorway/wall surfaces forming vertical black-blue borders at left and right edges.", "Left-side open wooden door and door frame with warm interior light visible beyond it.", "Cool blue-gray left wall, back wall, and right wall with subtle plaster texture.", "White/gray ceiling plane with crown molding around perimeter.", "Large central window/curtain surface: beige-gray pleated curtains hanging from a black rod with rings/finials.", "Wood laminate floor spanning foreground to back wall, with long plank seams running into depth.", "Gray/brown baseboards along back and side walls.", "Right-side single bed: dark wooden frame/headboard, checkered pillow, pale blue-gray blanket/comforter, visible underside shadow and legs."], "occlusion_order": "Closest layer: dark foreground doorway jambs/walls partially crop the scene on both edges. Behind that on the left, the open wooden door/frame overlaps the left wall and floor. The central curtains sit against the back wall and occlude the window behind them. On the right, the bed is in front of the right/back wall and partly overlaps the lower right curtain/wall area in depth. No human subjects are present; therefore there is no person-to-person occlusion.", "subjects": []}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): TL1_bedroom_bathroom.png
B2 최종샷 nb2 · 17.3s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png
경로 C — 임시샷→i2i 윤곽→배경 재생성→최종
C1 재생성 배경 (윤곽 기반) gpt-image-2 · 129.5s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png TL1_bedroom_bathroom.png
C2 최종샷 nb2 · 15.5s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C.png
m1 재생성 배경+마네킹 gpt-image-2 · 134.8s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

Where each person would stand or sit, place a featureless matte-grey
artist mannequin in that exact pose and scale (no face, no clothing
detail) — everything else stays an empty environment.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png TL1_bedroom_bathroom.png
m2 최종샷 (마네킹 경유) nb2 · 18.7s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
CAMERA: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
FRAMING: wide
LIGHTING: The room is washed in unnaturally clean blue-gray shadow with thin sick amber spill, making the absence feel colder than darkness.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C_m.png
S14_Shot4 VLM 구도 분석 JSON (경로 B 입력)
{
 "camera": {
  "angle": "Straight-on view into a bedroom from an adjacent darker doorway/corridor; optical axis aimed almost perpendicular to the back wall/curtain wall, with slight rightward reveal of the room’s right wall and bed.",
  "height": "Approximately standing eye/chest height, around 1.4–1.6 m; high enough to see the bed top and floor expanse, but below the ceiling line. Camera is level, not noticeably tilted.",
  "lens_feel": "Wide, panoramic/anamorphic-feeling frame with rectilinear perspective; moderate-wide lens, deep focus, symmetrical architectural composition with strong vertical doorway borders."
 },
 "empty_background_requirements": "The empty plate must be the same locked-off doorway view with no people: dark foreground door jambs/walls framing both far left and far right edges; the open warm-lit wooden door and door frame on the left; the blue-gray bedroom walls, ceiling, crown molding, baseboards, wood floorboards, central full-height curtains and black curtain rod with finials; the single bed on the right with wooden headboard, blue-gray blanket, pillow, visible bed legs/shadow; identical cool ambient light in the bedroom and warm spill from the left doorway. Since there are no people in the provided still, the plate is effectively the complete visible room as shown, preserving all furniture, curtains, shadows, reflections, and floor contact areas for any later insertion.",
 "horizon_and_depth": "Horizon/eye line is roughly mid-to-upper frame, around the curtain rod/upper wall zone implied by level verticals; the room is organized in layered depth: very near dark doorway frame in foreground, left open door slightly deeper, broad empty floor plane leading to the back curtain wall, and bed occupying the right mid/back plane. Strong depth is created by converging floorboard seams and side-wall/baseboard lines toward the back wall, while the back curtain plane remains mostly flat and frontal.",
 "major_surfaces": [
  "Foreground dark doorway/wall surfaces forming vertical black-blue borders at left and right edges.",
  "Left-side open wooden door and door frame with warm interior light visible beyond it.",
  "Cool blue-gray left wall, back wall, and right wall with subtle plaster texture.",
  "White/gray ceiling plane with crown molding around perimeter.",
  "Large central window/curtain surface: beige-gray pleated curtains hanging from a black rod with rings/finials.",
  "Wood laminate floor spanning foreground to back wall, with long plank seams running into depth.",
  "Gray/brown baseboards along back and side walls.",
  "Right-side single bed: dark wooden frame/headboard, checkered pillow, pale blue-gray blanket/comforter, visible underside shadow and legs."
 ],
 "occlusion_order": "Closest layer: dark foreground doorway jambs/walls partially crop the scene on both edges. Behind that on the left, the open wooden door/frame overlaps the left wall and floor. The central curtains sit against the back wall and occlude the window behind them. On the right, the bed is in front of the right/back wall and partly overlaps the lower right curtain/wall area in depth. No human subjects are present; therefore there is no person-to-person occlusion.",
 "subjects": []
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

S5_Shot3 loc=L04 · framing=medium · 인물=민숙

앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.

생성 순서 ① control/임시
fp변형 (카메라 콘+인물 서클) [CONTROL] gpt-image-2 · 170.8s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN floor plan of one dwelling: numbered circles mark fixed rooms and furniture. Keep the plan EXACTLY as it is — same walls, rooms, furniture and numbered circles, do not redraw or restyle anything.
ADD exactly these annotations for ONE camera setup:
- ONE green camera icon with a green triangular view-CONE showing where the camera stands and what it looks at, following this staging description:
The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
- 1 red circle(s) with capital letters (A) inside the view-cone where the staging places the people:
  * {"angle": "three_quarter_left", "body_pose": "frozen by TV", "character": "민숙", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "alive"}
Add NOTHING else — no new rooms, no new furniture, no text other than the existing numbers and the new capital letters.
참조 이미지(역할 라벨 포함): fp_l04_rooftop_room_main.png
임시샷 β (ENV=탑레이어+CONTROL) nb2 · 19.2s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.
PEOPLE IN SHOT: 민숙
CAMERA: The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
FRAMING: medium
LIGHTING: Cold TV blue fights a weak amber kitchen practical and pale window light, turning the cramped home into a damp, anxious interior.
PERSON: {"angle": "three_quarter_left", "body_pose": "frozen by TV", "character": "민숙", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "alive"}

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → TL2_living_kitchen_entry.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → fpvar.png
윤곽 (temp→라인아트) gpt-image-2 · 120.4s
prompt/refs (실제 호출 기록)
Convert the attached photograph into a clean LINE-ART CONTOUR drawing: thin dark ink lines on a plain white background. Preserve the EXACT composition, framing, perspective and proportions — trace the outline of every structure, surface edge and human figure as it appears. No shading, no colour fills, no photo texture, no text, no added or removed objects.
참조 이미지(역할 라벨 포함): temp.png
경로 A — 직행 (temp 없이 최종)
A 최종샷 (ENV+CONTROL+passport) nb2 · 17.3s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.
PEOPLE IN SHOT: 민숙
CAMERA: The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
FRAMING: medium
LIGHTING: Cold TV blue fights a weak amber kitchen practical and pale window light, turning the cramped home into a damp, anxious interior.
PERSON: {"angle": "three_quarter_left", "body_pose": "frozen by TV", "character": "민숙", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → TL2_living_kitchen_entry.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → fpvar.png [IDENTITY REFERENCE photo of the person referred to as: 민숙] → d6b8ea09-1c0a-453c-93fa-be38348df5a6.png
경로 B — 임시샷→VLM 구도 텍스트→배경 재생성→최종
B1 재생성 배경 (VLM comp 기반) gpt-image-2 · 99.3s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.
PEOPLE IN SHOT: 민숙
CAMERA: The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
FRAMING: medium
LIGHTING: Cold TV blue fights a weak amber kitchen practical and pale window light, turning the cramped home into a damp, anxious interior.
PERSON: {"angle": "three_quarter_left", "body_pose": "frozen by TV", "character": "민숙", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "alive"}

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "Straight-on to slightly oblique interior view down a narrow kitchen/dining corridor; camera axis runs lengthwise toward the back room, with the kitchen counter receding on the left and the woman held on the far right edge in profile/three-quarter profile.", "height": "Approximately chest to eye height, around 1.45–1.60 m; verticals are mostly upright, suggesting a level camera with little tilt.", "lens_feel": "Wide cinematic anamorphic/very wide horizontal framing, roughly 24–28 mm equivalent feel: strong lateral coverage of kitchen, doorway, dining area and subject, with moderate depth exaggeration but controlled distortion."}, "empty_background_requirements": "The empty plate must be the same locked-off wide interior composition with no people, preserving all practical objects and lighting: left kitchen run with frosted window, wooden frame, sink, faucet, dish rack, counter, gas hob, pot, tiled backsplash, extractor hood, upper/lower cabinets, and foreground refrigerator edge; central structural column/wall, ceiling light, doorway into the back room with visible wooden floor, curtains and bright rear window; right living/dining wall with crown molding, door frames, TV cabinet and TV showing the blue-toned image, floor lamp casting warm light on the wall, dining table and chairs. It must also include the unobstructed area behind the woman: right wall, doorway trim, light switch, table edge, chair backs/seats, floor and baseboard where her body currently covers them, so she can be composited back in at the same right-edge position with correct contact shadows and occlusions.", "horizon_and_depth": "Horizon/eye line sits around the upper third of the frame, near the height of the door lintels and upper wall trim. Depth is organized in strong layers: foreground kitchen fixtures at left and dining furniture at right; midground woman and TV/lamp area; central doorway opening to a deeper back room; far window and curtains at the deepest plane. Parallel floorboards, counter edges, cabinet lines, ceiling trim and doorway frames converge gently toward the central rear room, giving a corridor-like perspective. The composition balances a dense, cool kitchen foreground on the left against the human figure and warm lamp on the right, with negative wall space in the middle-right.", "major_surfaces": ["Left foreground refrigerator side plane, cropped at the extreme left edge.", "Left kitchen countertop: reflective metal sink surface, drainboard, gas hob and counter edge receding into depth.", "Vertical tiled backsplash wall behind hob and sink, cream square tiles with grout grid.", "Upper kitchen cabinets and extractor hood forming a heavy overhead plane in the upper-left quadrant.", "Wood-framed frosted kitchen window on the left wall, bright cool exterior light source.", "Central vertical partition/column and door jamb separating kitchen from living/dining area.", "Wood plank floor running from foreground into the central back room, with visible reflections and perspective lines.", "Rear doorway opening into a darker back room with curtains and a bright rectangular window.", "Right living/dining wall with pale wallpaper/paint, crown molding, baseboard, switch plate and door trim.", "TV console surface and cabinet below the lit television.", "Warm floor-lamp shade and its cast light patch on the right wall.", "Dining table top and chair backs/seats in the right foreground/midground.", "Ceiling plane with fluorescent fixture near the center-left/top."], "occlusion_order": "From nearest to farthest: extreme-left refrigerator edge and kitchen counter/sink foreground occlude the lower-left space; faucet, dish rack and hob sit in front of the tiled wall; upper cabinets and hood overlap the ceiling and window area. On the right, the woman is the foremost subject, occluding the right wall, doorway trim, dining table edge and part of the nearest chair/table area. Dining chairs and table occupy foreground/midground in front of the wall and floor. TV and console sit behind the woman’s plane but in front of the right wall. Floor lamp stands behind/near the TV console and casts onto the wall. Central doorway trim occludes the back room, which contains the far curtains/window and floor at the deepest plane.", "subjects": [{"depth_plane": "Right foreground to midground, closer than the TV/lamp and central doorway; approximately beside the dining table near the right wall.", "label": "woman in apron", "pose": "Standing upright, still and tense, body angled slightly toward camera-left; head turned left in profile/three-quarter profile, eyes looking off-frame or toward the kitchen/left side. Arms hang down by her sides, shoulders slightly lowered; expression serious or concerned.", "screen_zone": "Far right third, cropped close to the right edge; head in upper-right quadrant, torso running from mid-right to lower-right, with lower body partially visible near bottom-right.", "support_contact": "Standing on the wooden floor; feet are out of frame or near the bottom crop, so contact is implied by vertical posture. Her right side overlaps the dining table/chair area but she is not visibly leaning on furniture."}]}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): TL2_living_kitchen_entry.png
B2 최종샷 nb2 · 25.3s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.
PEOPLE IN SHOT: 민숙
CAMERA: The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
FRAMING: medium
LIGHTING: Cold TV blue fights a weak amber kitchen practical and pale window light, turning the cramped home into a damp, anxious interior.
PERSON: {"angle": "three_quarter_left", "body_pose": "frozen by TV", "character": "민숙", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png [IDENTITY REFERENCE photo of the person referred to as: 민숙] → d6b8ea09-1c0a-453c-93fa-be38348df5a6.png
경로 C — 임시샷→i2i 윤곽→배경 재생성→최종
C1 재생성 배경 (윤곽 기반) gpt-image-2 · 102.5s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.
PEOPLE IN SHOT: 민숙
CAMERA: The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
FRAMING: medium
LIGHTING: Cold TV blue fights a weak amber kitchen practical and pale window light, turning the cramped home into a damp, anxious interior.
PERSON: {"angle": "three_quarter_left", "body_pose": "frozen by TV", "character": "민숙", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "alive"}

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png TL2_living_kitchen_entry.png
C2 최종샷 nb2 · 16.8s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.
PEOPLE IN SHOT: 민숙
CAMERA: The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
FRAMING: medium
LIGHTING: Cold TV blue fights a weak amber kitchen practical and pale window light, turning the cramped home into a damp, anxious interior.
PERSON: {"angle": "three_quarter_left", "body_pose": "frozen by TV", "character": "민숙", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C.png [IDENTITY REFERENCE photo of the person referred to as: 민숙] → d6b8ea09-1c0a-453c-93fa-be38348df5a6.png
m1 재생성 배경+마네킹 gpt-image-2 · 125.3s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.
PEOPLE IN SHOT: 민숙
CAMERA: The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
FRAMING: medium
LIGHTING: Cold TV blue fights a weak amber kitchen practical and pale window light, turning the cramped home into a damp, anxious interior.
PERSON: {"angle": "three_quarter_left", "body_pose": "frozen by TV", "character": "민숙", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "alive"}

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

Where each person would stand or sit, place a featureless matte-grey
artist mannequin in that exact pose and scale (no face, no clothing
detail) — everything else stays an empty environment.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png TL2_living_kitchen_entry.png
m2 최종샷 (마네킹 경유) nb2 · 16.9s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.
PEOPLE IN SHOT: 민숙
CAMERA: The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
FRAMING: medium
LIGHTING: Cold TV blue fights a weak amber kitchen practical and pale window light, turning the cramped home into a damp, anxious interior.
PERSON: {"angle": "three_quarter_left", "body_pose": "frozen by TV", "character": "민숙", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C_m.png [IDENTITY REFERENCE photo of the person referred to as: 민숙] → d6b8ea09-1c0a-453c-93fa-be38348df5a6.png
S5_Shot3 VLM 구도 분석 JSON (경로 B 입력)
{
 "camera": {
  "angle": "Straight-on to slightly oblique interior view down a narrow kitchen/dining corridor; camera axis runs lengthwise toward the back room, with the kitchen counter receding on the left and the woman held on the far right edge in profile/three-quarter profile.",
  "height": "Approximately chest to eye height, around 1.45–1.60 m; verticals are mostly upright, suggesting a level camera with little tilt.",
  "lens_feel": "Wide cinematic anamorphic/very wide horizontal framing, roughly 24–28 mm equivalent feel: strong lateral coverage of kitchen, doorway, dining area and subject, with moderate depth exaggeration but controlled distortion."
 },
 "empty_background_requirements": "The empty plate must be the same locked-off wide interior composition with no people, preserving all practical objects and lighting: left kitchen run with frosted window, wooden frame, sink, faucet, dish rack, counter, gas hob, pot, tiled backsplash, extractor hood, upper/lower cabinets, and foreground refrigerator edge; central structural column/wall, ceiling light, doorway into the back room with visible wooden floor, curtains and bright rear window; right living/dining wall with crown molding, door frames, TV cabinet and TV showing the blue-toned image, floor lamp casting warm light on the wall, dining table and chairs. It must also include the unobstructed area behind the woman: right wall, doorway trim, light switch, table edge, chair backs/seats, floor and baseboard where her body currently covers them, so she can be composited back in at the same right-edge position with correct contact shadows and occlusions.",
 "horizon_and_depth": "Horizon/eye line sits around the upper third of the frame, near the height of the door lintels and upper wall trim. Depth is organized in strong layers: foreground kitchen fixtures at left and dining furniture at right; midground woman and TV/lamp area; central doorway opening to a deeper back room; far window and curtains at the deepest plane. Parallel floorboards, counter edges, cabinet lines, ceiling trim and doorway frames converge gently toward the central rear room, giving a corridor-like perspective. The composition balances a dense, cool kitchen foreground on the left against the human figure and warm lamp on the right, with negative wall space in the middle-right.",
 "major_surfaces": [
  "Left foreground refrigerator side plane, cropped at the extreme left edge.",
  "Left kitchen countertop: reflective metal sink surface, drainboard, gas hob and counter edge receding into depth.",
  "Vertical tiled backsplash wall behind hob and sink, cream square tiles with grout grid.",
  "Upper kitchen cabinets and extractor hood forming a heavy overhead plane in the upper-left quadrant.",
  "Wood-framed frosted kitchen window on the left wall, bright cool exterior light source.",
  "Central vertical partition/column and door jamb separating kitchen from living/dining area.",
  "Wood plank floor running from foreground into the central back room, with visible reflections and perspective lines.",
  "Rear doorway opening into a darker back room with curtains and a bright rectangular window.",
  "Right living/dining wall with pale wallpaper/paint, crown molding, baseboard, switch plate and door trim.",
  "TV console surface and cabinet below the lit television.",
  "Warm floor-lamp shade and its cast light patch on the right wall.",
  "Dining table top and chair backs/seats in the right foreground/midground.",
  "Ceiling plane with fluorescent fixture near the center-left/top."
 ],
 "occlusion_order": "From nearest to farthest: extreme-left refrigerator edge and kitchen counter/sink foreground occlude the lower-left space; faucet, dish rack and hob sit in front of the tiled wall; upper cabinets and hood overlap the ceiling and window area. On the right, the woman is the foremost subject, occluding the right wall, doorway trim, dining table edge and part of the nearest chair/table area. Dining chairs and table occupy foreground/midground in front of the wall and floor. TV and console sit behind the woman’s plane but in front of the right wall. Floor lamp stands behind/near the TV console and casts onto the wall. Central doorway trim occludes the back room, which contains the far curtains/window and floor at the deepest plane.",
 "subjects": [
  {
   "depth_plane": "Right foreground to midground, closer than the TV/lamp and central doorway; approximately beside the dining table near the right wall.",
   "label": "woman in apron",
   "pose": "Standing upright, still and tense, body angled slightly toward camera-left; head turned left in profile/three-quarter profile, eyes looking off-frame or toward the kitchen/left side. Arms hang down by her sides, shoulders slightly lowered; expression serious or concerned.",
   "screen_zone": "Far right third, cropped close to the right edge; head in upper-right quadrant, torso running from mid-right to lower-right, with lower body partially visible near bottom-right.",
   "support_contact": "Standing on the wooden floor; feet are out of frame or near the bottom crop, so contact is implied by vertical posture. Her right side overlaps the dining table/chair area but she is not visibly leaning on furniture."
  }
 ]
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

S5_Shot10 loc=L04 · framing=close · 인물=수리영, 민숙

수리영이 민숙의 어깨에 코를 묻고 멈춘 찰나의 측면.

생성 순서 ① control/임시
fp변형 (카메라 콘+인물 서클) [CONTROL] gpt-image-2 · 160.0s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN floor plan of one dwelling: numbered circles mark fixed rooms and furniture. Keep the plan EXACTLY as it is — same walls, rooms, furniture and numbered circles, do not redraw or restyle anything.
ADD exactly these annotations for ONE camera setup:
- ONE green camera icon with a green triangular view-CONE showing where the camera stands and what it looks at, following this staging description:
The camera follows the flow into the narrow entrance area and holds side-on at shoulder height, about one meter away, lens parallel to the wall to compress mother and daughter together. The tighter profile frame favors the contact point: Suriyeong’s face and nose press into Minsuk’s shoulder at center-left, while Minsuk’s softened profile and apron edge sit center-right.
- 2 red circle(s) with capital letters (A) (B) inside the view-cone where the staging places the people:
  * {"angle": "profile_right", "body_pose": "nose buried in shoulder", "character": "수리영", "gaze_direction_kind": "closed_eyes", "gaze_target_id": null, "subject_state": "alive"}
  * {"angle": "profile_left", "body_pose": "shoulder softened, smiling", "character": "민숙", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C01", "subject_state": "alive"}
Add NOTHING else — no new rooms, no new furniture, no text other than the existing numbers and the new capital letters.
참조 이미지(역할 라벨 포함): fp_l04_rooftop_room_main.png
임시샷 β (ENV=탑레이어+CONTROL) nb2 · 15.8s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 수리영이 민숙의 어깨에 코를 묻고 멈춘 찰나의 측면.
PEOPLE IN SHOT: 수리영, 민숙
CAMERA: The camera follows the flow into the narrow entrance area and holds side-on at shoulder height, about one meter away, lens parallel to the wall to compress mother and daughter together. The tighter profile frame favors the contact point: Suriyeong’s face and nose press into Minsuk’s shoulder at center-left, while Minsuk’s softened profile and apron edge sit center-right.
FRAMING: close
LIGHTING: Soft domestic amber from the room mixes with cool daylight spill near the entrance, giving the affectionate pause a muted warmth under thriller-gray shadows.
PERSON: {"angle": "profile_right", "body_pose": "nose buried in shoulder", "character": "수리영", "gaze_direction_kind": "closed_eyes", "gaze_target_id": null, "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "shoulder softened, smiling", "character": "민숙", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C01", "subject_state": "alive"}

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → TL2_living_kitchen_entry.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → fpvar.png
윤곽 (temp→라인아트) gpt-image-2 · 136.2s
prompt/refs (실제 호출 기록)
Convert the attached photograph into a clean LINE-ART CONTOUR drawing: thin dark ink lines on a plain white background. Preserve the EXACT composition, framing, perspective and proportions — trace the outline of every structure, surface edge and human figure as it appears. No shading, no colour fills, no photo texture, no text, no added or removed objects.
참조 이미지(역할 라벨 포함): temp.png
경로 A — 직행 (temp 없이 최종)
A 최종샷 (ENV+CONTROL+passport) nb2 · 22.1s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 수리영이 민숙의 어깨에 코를 묻고 멈춘 찰나의 측면.
PEOPLE IN SHOT: 수리영, 민숙
CAMERA: The camera follows the flow into the narrow entrance area and holds side-on at shoulder height, about one meter away, lens parallel to the wall to compress mother and daughter together. The tighter profile frame favors the contact point: Suriyeong’s face and nose press into Minsuk’s shoulder at center-left, while Minsuk’s softened profile and apron edge sit center-right.
FRAMING: close
LIGHTING: Soft domestic amber from the room mixes with cool daylight spill near the entrance, giving the affectionate pause a muted warmth under thriller-gray shadows.
PERSON: {"angle": "profile_right", "body_pose": "nose buried in shoulder", "character": "수리영", "gaze_direction_kind": "closed_eyes", "gaze_target_id": null, "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "shoulder softened, smiling", "character": "민숙", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C01", "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → TL2_living_kitchen_entry.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → fpvar.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png [IDENTITY REFERENCE photo of the person referred to as: 민숙] → d6b8ea09-1c0a-453c-93fa-be38348df5a6.png
경로 B — 임시샷→VLM 구도 텍스트→배경 재생성→최종
B1 재생성 배경 (VLM comp 기반) gpt-image-2 · 101.1s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 수리영이 민숙의 어깨에 코를 묻고 멈춘 찰나의 측면.
PEOPLE IN SHOT: 수리영, 민숙
CAMERA: The camera follows the flow into the narrow entrance area and holds side-on at shoulder height, about one meter away, lens parallel to the wall to compress mother and daughter together. The tighter profile frame favors the contact point: Suriyeong’s face and nose press into Minsuk’s shoulder at center-left, while Minsuk’s softened profile and apron edge sit center-right.
FRAMING: close
LIGHTING: Soft domestic amber from the room mixes with cool daylight spill near the entrance, giving the affectionate pause a muted warmth under thriller-gray shadows.
PERSON: {"angle": "profile_right", "body_pose": "nose buried in shoulder", "character": "수리영", "gaze_direction_kind": "closed_eyes", "gaze_target_id": null, "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "shoulder softened, smiling", "character": "민숙", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C01", "subject_state": "alive"}

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "Side-on hallway view, looking slightly down the corridor axis but with subjects in right profile/three-quarter back profile. Camera is positioned just outside or inside a narrow doorway/hall, parallel to the left window wall and right wall, creating strong vertical framing lines.", "height": "Approximately adult chest-to-shoulder height, around the woman’s head/upper torso level and slightly below the man’s eye line. The camera is not low; verticals remain mostly upright.", "lens_feel": "Moderately wide/anamorphic-feeling frame with a broad horizontal field of view. Mild perspective depth down the corridor; background is somewhat soft but readable. Naturalistic shallow-to-medium depth of field, with subjects sharper than the far room."}, "empty_background_requirements": "The empty plate must preserve the same narrow corridor/doorway composition with no people: left beige wall with light switch near lower left, tall frosted/bright window or glass door with blue-gray metal frame, central beige wall strip, dark brown wooden door jambs and open door panels with visible brass hinges, the receding corridor/room beyond, the gray back wall, warm curtains and bright window glow in the far background, right beige wall and right dark wooden door frame where the man currently stands. It must include the portions hidden behind the subjects: the right doorway recess, wall/floor continuation behind their bodies, lower corridor floor, the back-room curtain/window area, and the right wall/jamb surfaces so the two figures can be composited back with correct edge contact and shadows. Lighting should match: cool daylight from the left window, warmer background glow, and soft shadows cast toward the right/interior surfaces.", "horizon_and_depth": "Horizon/eye level sits around the man’s lower face/neck to the woman’s forehead region, roughly upper-middle of frame. Depth is organized by vertical architectural planes: near left wall/window plane in foreground, central doorway/jamb plane, subjects in the near-right doorway plane, and a receding corridor/room behind them. The far background has a gray wall and warm curtained window, softened by distance. Strong verticals dominate; corridor lines and door edges create a tunnel-like depth toward the center background.", "major_surfaces": ["Left foreground beige plaster wall with a light switch low near bottom-left.", "Tall bright frosted glass/window or balcony door along the left third, framed by blue-gray metal mullions.", "Narrow central beige wall strip between window and inner doorway.", "Dark brown wooden door frames/jambs forming vertical borders around the corridor opening; visible brass hinges on both sides.", "Interior corridor/room beyond, with beige ceiling, dark gray rear wall, and warm curtains around a bright window.", "Right foreground beige wall, very close to camera/subjects, forming a tight passage.", "Right dark wooden door frame/recess directly behind and beside the man.", "Partly visible floor in the distant corridor, mostly occluded by the subjects."], "occlusion_order": "From front to back: left/right foreground walls and door jamb edges frame the scene; the two subjects occupy the dominant near-right foreground/midground. The woman is slightly in front of and overlapping the man, her face and upper body occluding his chest/shoulder area where she leans in. The man’s torso and head occlude the right doorway frame and right wall. Both subjects occlude the corridor floor and portions of the distant curtains/window. Behind them are the open door frames, then the receding hallway/room with gray back wall and curtains. The left window/wall plane remains unobstructed by people.", "subjects": [{"depth_plane": "Near-right foreground/midground, just inside the doorway plane; slightly closer to camera than the man at their point of overlap.", "label": "woman", "pose": "Standing in left-facing profile, leaning forward and upward into the man’s right shoulder/upper arm area. Eyes closed, head tilted toward him, mouth/face pressed near his sleeve/shoulder as if kissing or resting against him. Hair tied back in a low ponytail; shoulders sloped forward.", "screen_zone": "Lower center-right, occupying roughly x 38–62% and y 31–96%; her head is just left of the man’s chest/face, body descends toward the bottom edge.", "support_contact": "Standing on the unseen floor; feet are out of frame. Upper face/mouth makes contact with the man’s right shoulder/upper arm. No visible hand support; posture supported by her legs and lean into him."}, {"depth_plane": "Near-right foreground/midground, pressed close to the right doorway/wall plane; slightly behind the woman where she overlaps his torso.", "label": "man", "pose": "Standing upright in right half of frame, body turned mostly away from camera with back/shoulder visible, head in left-facing profile looking down toward the woman with a faint smile. Arms appear held behind his back or close to his sides; floral apron visible around waist/lower back.", "screen_zone": "Right third to right-center, occupying roughly x 58–86% and y 10–100%; head near upper-right, torso fills the right side.", "support_contact": "Standing on the unseen floor; back/right side close to or lightly against the right door frame/wall recess. Shoulder/upper arm is contacted by the woman’s face. Feet out of frame."}]}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): TL2_living_kitchen_entry.png
B2 최종샷 nb2 · 21.2s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 수리영이 민숙의 어깨에 코를 묻고 멈춘 찰나의 측면.
PEOPLE IN SHOT: 수리영, 민숙
CAMERA: The camera follows the flow into the narrow entrance area and holds side-on at shoulder height, about one meter away, lens parallel to the wall to compress mother and daughter together. The tighter profile frame favors the contact point: Suriyeong’s face and nose press into Minsuk’s shoulder at center-left, while Minsuk’s softened profile and apron edge sit center-right.
FRAMING: close
LIGHTING: Soft domestic amber from the room mixes with cool daylight spill near the entrance, giving the affectionate pause a muted warmth under thriller-gray shadows.
PERSON: {"angle": "profile_right", "body_pose": "nose buried in shoulder", "character": "수리영", "gaze_direction_kind": "closed_eyes", "gaze_target_id": null, "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "shoulder softened, smiling", "character": "민숙", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C01", "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png [IDENTITY REFERENCE photo of the person referred to as: 민숙] → d6b8ea09-1c0a-453c-93fa-be38348df5a6.png
경로 C — 임시샷→i2i 윤곽→배경 재생성→최종
C1 재생성 배경 (윤곽 기반) gpt-image-2 · 128.1s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 수리영이 민숙의 어깨에 코를 묻고 멈춘 찰나의 측면.
PEOPLE IN SHOT: 수리영, 민숙
CAMERA: The camera follows the flow into the narrow entrance area and holds side-on at shoulder height, about one meter away, lens parallel to the wall to compress mother and daughter together. The tighter profile frame favors the contact point: Suriyeong’s face and nose press into Minsuk’s shoulder at center-left, while Minsuk’s softened profile and apron edge sit center-right.
FRAMING: close
LIGHTING: Soft domestic amber from the room mixes with cool daylight spill near the entrance, giving the affectionate pause a muted warmth under thriller-gray shadows.
PERSON: {"angle": "profile_right", "body_pose": "nose buried in shoulder", "character": "수리영", "gaze_direction_kind": "closed_eyes", "gaze_target_id": null, "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "shoulder softened, smiling", "character": "민숙", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C01", "subject_state": "alive"}

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png TL2_living_kitchen_entry.png
C2 최종샷 nb2 · 23.0s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 수리영이 민숙의 어깨에 코를 묻고 멈춘 찰나의 측면.
PEOPLE IN SHOT: 수리영, 민숙
CAMERA: The camera follows the flow into the narrow entrance area and holds side-on at shoulder height, about one meter away, lens parallel to the wall to compress mother and daughter together. The tighter profile frame favors the contact point: Suriyeong’s face and nose press into Minsuk’s shoulder at center-left, while Minsuk’s softened profile and apron edge sit center-right.
FRAMING: close
LIGHTING: Soft domestic amber from the room mixes with cool daylight spill near the entrance, giving the affectionate pause a muted warmth under thriller-gray shadows.
PERSON: {"angle": "profile_right", "body_pose": "nose buried in shoulder", "character": "수리영", "gaze_direction_kind": "closed_eyes", "gaze_target_id": null, "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "shoulder softened, smiling", "character": "민숙", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C01", "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png [IDENTITY REFERENCE photo of the person referred to as: 민숙] → d6b8ea09-1c0a-453c-93fa-be38348df5a6.png
S5_Shot10 VLM 구도 분석 JSON (경로 B 입력)
{
 "camera": {
  "angle": "Side-on hallway view, looking slightly down the corridor axis but with subjects in right profile/three-quarter back profile. Camera is positioned just outside or inside a narrow doorway/hall, parallel to the left window wall and right wall, creating strong vertical framing lines.",
  "height": "Approximately adult chest-to-shoulder height, around the woman’s head/upper torso level and slightly below the man’s eye line. The camera is not low; verticals remain mostly upright.",
  "lens_feel": "Moderately wide/anamorphic-feeling frame with a broad horizontal field of view. Mild perspective depth down the corridor; background is somewhat soft but readable. Naturalistic shallow-to-medium depth of field, with subjects sharper than the far room."
 },
 "empty_background_requirements": "The empty plate must preserve the same narrow corridor/doorway composition with no people: left beige wall with light switch near lower left, tall frosted/bright window or glass door with blue-gray metal frame, central beige wall strip, dark brown wooden door jambs and open door panels with visible brass hinges, the receding corridor/room beyond, the gray back wall, warm curtains and bright window glow in the far background, right beige wall and right dark wooden door frame where the man currently stands. It must include the portions hidden behind the subjects: the right doorway recess, wall/floor continuation behind their bodies, lower corridor floor, the back-room curtain/window area, and the right wall/jamb surfaces so the two figures can be composited back with correct edge contact and shadows. Lighting should match: cool daylight from the left window, warmer background glow, and soft shadows cast toward the right/interior surfaces.",
 "horizon_and_depth": "Horizon/eye level sits around the man’s lower face/neck to the woman’s forehead region, roughly upper-middle of frame. Depth is organized by vertical architectural planes: near left wall/window plane in foreground, central doorway/jamb plane, subjects in the near-right doorway plane, and a receding corridor/room behind them. The far background has a gray wall and warm curtained window, softened by distance. Strong verticals dominate; corridor lines and door edges create a tunnel-like depth toward the center background.",
 "major_surfaces": [
  "Left foreground beige plaster wall with a light switch low near bottom-left.",
  "Tall bright frosted glass/window or balcony door along the left third, framed by blue-gray metal mullions.",
  "Narrow central beige wall strip between window and inner doorway.",
  "Dark brown wooden door frames/jambs forming vertical borders around the corridor opening; visible brass hinges on both sides.",
  "Interior corridor/room beyond, with beige ceiling, dark gray rear wall, and warm curtains around a bright window.",
  "Right foreground beige wall, very close to camera/subjects, forming a tight passage.",
  "Right dark wooden door frame/recess directly behind and beside the man.",
  "Partly visible floor in the distant corridor, mostly occluded by the subjects."
 ],
 "occlusion_order": "From front to back: left/right foreground walls and door jamb edges frame the scene; the two subjects occupy the dominant near-right foreground/midground. The woman is slightly in front of and overlapping the man, her face and upper body occluding his chest/shoulder area where she leans in. The man’s torso and head occlude the right doorway frame and right wall. Both subjects occlude the corridor floor and portions of the distant curtains/window. Behind them are the open door frames, then the receding hallway/room with gray back wall and curtains. The left window/wall plane remains unobstructed by people.",
 "subjects": [
  {
   "depth_plane": "Near-right foreground/midground, just inside the doorway plane; slightly closer to camera than the man at their point of overlap.",
   "label": "woman",
   "pose": "Standing in left-facing profile, leaning forward and upward into the man’s right shoulder/upper arm area. Eyes closed, head tilted toward him, mouth/face pressed near his sleeve/shoulder as if kissing or resting against him. Hair tied back in a low ponytail; shoulders sloped forward.",
   "screen_zone": "Lower center-right, occupying roughly x 38–62% and y 31–96%; her head is just left of the man’s chest/face, body descends toward the bottom edge.",
   "support_contact": "Standing on the unseen floor; feet are out of frame. Upper face/mouth makes contact with the man’s right shoulder/upper arm. No visible hand support; posture supported by her legs and lean into him."
  },
  {
   "depth_plane": "Near-right foreground/midground, pressed close to the right doorway/wall plane; slightly behind the woman where she overlaps his torso.",
   "label": "man",
   "pose": "Standing upright in right half of frame, body turned mostly away from camera with back/shoulder visible, head in left-facing profile looking down toward the woman with a faint smile. Arms appear held behind his back or close to his sides; floral apron visible around waist/lower back.",
   "screen_zone": "Right third to right-center, occupying roughly x 58–86% and y 10–100%; head near upper-right, torso fills the right side.",
   "support_contact": "Standing on the unseen floor; back/right side close to or lightly against the right door frame/wall recess. Shoulder/upper arm is contacted by the woman’s face. Feet out of frame."
  }
 ]
}
production 비교
비교 production 최종 스틸 #0

4. 실외 샷별 체인 — 버전순 (v1 → v2 → v3)

판정: v1=실패 증거(항공 고착+군중+지붕 소실). v2=계약 3줄로 군중/topology 해소. v3=sketch-hop 으로 plate 눈높이 성공, 단 임시샷(nb2) 경유 시 시점 재상승(2회 재현) → wide 무인물 establishing 정답 = sketch-hop + 직행(임시샷 생략). 그리고 모든 버전이 뿌리(root_B)의 틀린 기하(작은 오두막)를 물려받음 — 근본 해결은 root_C 몫.

4.1 실외 v1 — 계약 없음 (실패 증거 보존)

S4_Shot1 loc=L03 · framing=wide · 인물=없음

인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.

생성 순서 ① control/plate/임시
뿌리 마킹 (카메라 콘+인물 서클) [CONTROL] gpt-image-2 · 141.0s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch with circled capital letters marking site elements (and possibly a legend panel on the right). Keep the sketch EXACTLY as it is — same geometry, same circled letters, same legend, do not redraw or restyle anything.
ADD exactly these annotations for ONE camera setup:
- ONE green camera icon with a green triangular view-CONE showing where the camera stands and what it looks at, following this staging description:
An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
- This shot has NO people — add no lettered person circles.
Add NOTHING else — no new structures, no new text other than the new capital letters in their small circles.
참조 이미지(역할 라벨 포함): root_B.png
빈 배경 plate [ENV] gpt-image-2 · 119.3s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch of one real place,
with a green camera icon and view-cone marking ONE camera position and
its viewing direction. Circled letters mark site elements; red lettered
circles (if any) mark where people stand — but render NO people.

Draw the PHOTOREALISTIC outdoor view that THAT camera sees from its
marked position at eye level, looking along the view-cone: the
structures, ground surfaces, openings and approaches the sketch places
in front of that camera, at real-world human scale. This is an EMPTY
background plate: absolutely no people, no text, no letters, no
circles, no arrows, no sketch lines — pure photographic realism.

WHAT THIS PLACE LOOKS LIKE (production data):
- 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)

Site orientation notes:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]
참조 이미지(역할 라벨 포함): root_marked.png
임시샷 nb2 · 17.0s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
윤곽 gpt-image-2 · 150.4s
prompt/refs (실제 호출 기록)
Convert the attached photograph into a clean LINE-ART CONTOUR drawing: thin dark ink lines on a plain white background. Preserve the EXACT composition, framing, perspective and proportions — trace the outline of every structure, surface edge and human figure as it appears. No shading, no colour fills, no photo texture, no text, no added or removed objects.
참조 이미지(역할 라벨 포함): temp.png
경로 A — 직행
A 최종샷 (plate+CONTROL+passport) nb2 · 18.4s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
경로 B — VLM 구도 텍스트
B1 재생성 배경 gpt-image-2 · 136.4s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "Very high oblique aerial/rooftop view looking steeply downward, not perfectly vertical; the camera is above and slightly in front of the main roof court, producing strong plan-view geometry with visible wall faces.", "height": "Several stories above the subjects, approximately 2–4 building levels above the main rooftop; subjects appear small and compressed into an architectural grid.", "lens_feel": "Wide panoramic/stitched feel with mild perspective convergence and large horizontal field of view; moderate-wide lens impression, deep focus across foreground roof, central courtyard, and distant neighboring rooftops."}, "empty_background_requirements": "An empty plate must preserve the entire rooftop complex and surrounding city fabric with no people: the central sunken/boxed concrete rooftop court with stained walls, two open metal doors on the upper wall, the warm-lit left-side window/door opening, the front parapet with horizontal window, the open gate/door near the lower-left corner of the main court, staircases and railings at lower left, the left upper rooftop platform, the right rooftop annex with clotheslines, hanging laundry, blue cylindrical water tank, stacked wooden debris/cart, parapet walls, cracked concrete, leaf piles, drainage grates, neighboring flat roofs, red-tile roof, green roofs, utility cables, windows, alley/drive surfaces, parked vehicles at far left, tree foliage at lower right, and the blue corrugated roof in the lower foreground. The plate must include all contact surfaces where people stand: central court floor, door thresholds, parapet-edge walkway, stair treads/landings, right annex roof, far-right rooftop ledge, and bottom exterior walkway. Door positions, laundry, water tank, debris piles, stains, cracks, leaf scatter, and warm interior glows should remain unchanged so subjects can be composited back into the same occlusion layers.", "horizon_and_depth": "No visible sky or true horizon; the frame is dominated by receding horizontal roof planes. Depth is established by stacked parapet walls and rooftops: foreground lower roofs and exterior walkway at bottom, main rooftop court in the center, side annexes left and right, then background apartment roofs and facades at the top. The high angle flattens vertical depth but wall faces, stair runs, open doors, and roof edges create clear stepped depth planes. The central court is the primary mid-depth plane, enclosed by higher parapets and adjacent roof decks.", "major_surfaces": ["Large central concrete rooftop court/floor, cracked and stained, occupying the middle of frame.", "Tall rectangular concrete rooftop room/parapet structure around the central court, with stained vertical walls and two open metal doors on the upper wall.", "Front/lower parapet wall of the central court with a narrow horizontal warm-lit window.", "Left upper rooftop terrace/platform separated by low concrete walls, with leaf debris and weathered concrete.", "Lower-left staircase system with concrete steps, landings, rust-colored metal railings, and surrounding parapet walls.", "Right-side rooftop annex/deck with cracked dark concrete, clothesline poles, hanging laundry, blue cylindrical water tank, and pile/cart of wood debris.", "Far-right higher/outer rooftop walkway and parapet edge where a lone figure stands.", "Surrounding neighboring buildings: flat gray roofs, green roof panels, red tiled roof, brick and concrete facades, windows, balconies, overhead utility wires.", "Bottom foreground exterior walkway/roof lane and blue corrugated roof, plus tree foliage at lower right.", "Left edge alley/drive area with parked vehicles and building walls."], "occlusion_order": "Nearest/lowest foreground elements are the bottom exterior roof lane, blue corrugated roof, lower parapets, tree branches, and stair railings, which would occlude lower bodies if overlapping. The main central court subjects sit behind the front parapet lip but in front of the rear wall and open doors. Doorway subjects are partially framed/occluded by door jambs and metal door panels. The man at the left window is adjacent to/partly occluded by the central building side wall and window frame. The right-annex subjects are behind the central court’s right parapet wall but in front of the laundry, tank, and debris unless overlapping. The upper-left pair are behind the nearer left parapet edge and in front of background apartment roofs. The far-right rooftop figure is on a background/right roof plane, visually behind the right annex parapets and utility cables. Background buildings, roofs, cables, and distant facades are the rearmost layers.", "subjects": [{"depth_plane": "Upper-left adjacent rooftop terrace, behind the central court and above/left of it.", "label": "Upper-left pair, man A", "pose": "Standing upright in dark jacket and jeans, body angled slightly toward the other man as if conversing; arms close to body.", "screen_zone": "Upper left-of-center, on narrow roof strip just above the left side of the central structure.", "support_contact": "Both feet planted on the weathered concrete roof surface near the parapet edge."}, {"depth_plane": "Upper-left adjacent rooftop terrace, same plane as man A.", "label": "Upper-left pair, man B", "pose": "Standing upright in dark jacket, turned toward man A, slight contrapposto/conversation stance.", "screen_zone": "Upper left-of-center, just to the right of man A near the same parapet line.", "support_contact": "Feet on the concrete rooftop strip, close to the central roof wall edge."}, {"depth_plane": "Central rooftop room threshold, rear/upper wall of central court.", "label": "Left rear doorway figure", "pose": "Standing partly inside/open doorway, body facing outward into the courtyard, dark clothing with light shirt visible; relaxed vertical posture.", "screen_zone": "Upper middle-left of the central court, framed by the left open metal door.", "support_contact": "Feet at the doorway threshold/interior floor level, contacting the sill/door landing."}, {"depth_plane": "Central rooftop room threshold, rear/upper wall of central court.", "label": "Right rear doorway figure", "pose": "Standing in the right doorway, facing outward; dark coat and trousers, arms low, framed by the open door panel.", "screen_zone": "Upper middle-right of central court, inside the right open doorway.", "support_contact": "Feet planted on the doorway threshold/interior floor, just behind the court floor plane."}, {"depth_plane": "Central court left side, beside the building wall/window; mid-ground.", "label": "Left wall/window man", "pose": "Standing side-on to the courtyard, facing the warm-lit window/opening, hands raised near chest as if holding phone or manipulating the frame.", "screen_zone": "Left-middle edge of the central court, adjacent to the vertical wall.", "support_contact": "Feet on central concrete court floor immediately beside the wall/window base."}, {"depth_plane": "Central court floor, primary mid-ground group.", "label": "Central group man 1, left of cluster", "pose": "Standing facing inward toward the group, dark puffer jacket, head slightly down toward the others/phone.", "screen_zone": "Lower middle-right of the central court cluster.", "support_contact": "Both feet on central cracked concrete floor."}, {"depth_plane": "Central court floor, primary mid-ground group.", "label": "Central group man 2, phone-holder/inner left", "pose": "Standing close to the group, looking down with hands together as if holding or showing an object/phone.", "screen_zone": "Center-right of the central court, slightly above the left member of the group.", "support_contact": "Feet planted on central court concrete."}, {"depth_plane": "Central court floor, primary mid-ground group.", "label": "Central group man 3, tall upper-right of cluster", "pose": "Standing upright in dark jacket, facing inward/down toward group; slightly separated behind the others.", "screen_zone": "Right-center of the central court cluster.", "support_contact": "Feet on central concrete floor."}, {"depth_plane": "Central court floor, primary mid-ground group.", "label": "Central group man 4, back-to-camera foreground of cluster", "pose": "Standing with back to camera in dark padded jacket, facing the rest of the group; legs apart slightly.", "screen_zone": "Lower center-right of central court cluster.", "support_contact": "Feet on central concrete floor, closest member of the central group to the lower edge."}, {"depth_plane": "Central court floor, primary mid-ground group.", "label": "Central group man 5, patterned-coat/right member", "pose": "Standing facing the back-to-camera man and the group, slightly turned left; patterned/dark coat visible.", "screen_zone": "Lower right side of the central group.", "support_contact": "Feet on central concrete floor."}, {"depth_plane": "Right side of central court near parapet/wall, slightly separated from main group.", "label": "Right wall phone man", "pose": "Standing alone, side-on, head down toward hands as if using a phone; light gray/brown coat.", "screen_zone": "Right-middle of central court, near the right parapet and warm wall light.", "support_contact": "Feet on central court floor close to the right wall/parapet edge."}, {"depth_plane": "Right rooftop annex/deck beyond the central court wall.", "label": "Right annex lower figure", "pose": "Standing near laundry/debris area, dark jacket and jeans, head down; body angled diagonally toward lower right.", "screen_zone": "Right side of frame, lower half of the right annex, next to hanging laundry and debris pile.", "support_contact": "Feet on cracked dark concrete roof surface of the right annex."}, {"depth_plane": "Far-right outer rooftop/walkway, background-right plane.", "label": "Far-right rooftop figure", "pose": "Standing/walking slowly along roof edge in dark coat, body facing left/downward, one leg advanced.", "screen_zone": "Extreme upper-right quadrant near the right border.", "support_contact": "Feet on the far-right flat roof/walkway surface near a parapet edge."}, {"depth_plane": "Lower-left staircase, foreground-midground transition.", "label": "Staircase descending man", "pose": "Standing or descending on the stair run, dark coat, body facing down the steps toward camera/lower frame.", "screen_zone": "Lower left-of-center on the stairwell between railings.", "support_contact": "Feet on separate stair treads, partially enclosed by metal railings."}, {"depth_plane": "Bottom exterior walkway/roof lane, foreground.", "label": "Bottom-left standing man", "pose": "Standing still in long coat, mostly back/side to camera, looking upward/right toward the rooftop complex.", "screen_zone": "Lower left quadrant, just below the staircase base and inside the foreground roof lane.", "support_contact": "Feet planted on the lower concrete walkway/roof surface."}]}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): plate.png
B2 최종샷 nb2 · 17.2s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png
경로 C — i2i 윤곽
C1 재생성 배경 gpt-image-2 · 139.2s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png plate.png
C2 최종샷 nb2 · 20.1s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C.png
m1 재생성 배경+마네킹 gpt-image-2 · 117.3s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

Where each person would stand or sit, place a featureless matte-grey
artist mannequin in that exact pose and scale (no face, no clothing
detail) — everything else stays an empty environment.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png plate.png
m2 최종샷 (마네킹 경유) nb2 · 17.1s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C_m.png
S4_Shot1 VLM 구도 분석 JSON
{
 "camera": {
  "angle": "Very high oblique aerial/rooftop view looking steeply downward, not perfectly vertical; the camera is above and slightly in front of the main roof court, producing strong plan-view geometry with visible wall faces.",
  "height": "Several stories above the subjects, approximately 2–4 building levels above the main rooftop; subjects appear small and compressed into an architectural grid.",
  "lens_feel": "Wide panoramic/stitched feel with mild perspective convergence and large horizontal field of view; moderate-wide lens impression, deep focus across foreground roof, central courtyard, and distant neighboring rooftops."
 },
 "empty_background_requirements": "An empty plate must preserve the entire rooftop complex and surrounding city fabric with no people: the central sunken/boxed concrete rooftop court with stained walls, two open metal doors on the upper wall, the warm-lit left-side window/door opening, the front parapet with horizontal window, the open gate/door near the lower-left corner of the main court, staircases and railings at lower left, the left upper rooftop platform, the right rooftop annex with clotheslines, hanging laundry, blue cylindrical water tank, stacked wooden debris/cart, parapet walls, cracked concrete, leaf piles, drainage grates, neighboring flat roofs, red-tile roof, green roofs, utility cables, windows, alley/drive surfaces, parked vehicles at far left, tree foliage at lower right, and the blue corrugated roof in the lower foreground. The plate must include all contact surfaces where people stand: central court floor, door thresholds, parapet-edge walkway, stair treads/landings, right annex roof, far-right rooftop ledge, and bottom exterior walkway. Door positions, laundry, water tank, debris piles, stains, cracks, leaf scatter, and warm interior glows should remain unchanged so subjects can be composited back into the same occlusion layers.",
 "horizon_and_depth": "No visible sky or true horizon; the frame is dominated by receding horizontal roof planes. Depth is established by stacked parapet walls and rooftops: foreground lower roofs and exterior walkway at bottom, main rooftop court in the center, side annexes left and right, then background apartment roofs and facades at the top. The high angle flattens vertical depth but wall faces, stair runs, open doors, and roof edges create clear stepped depth planes. The central court is the primary mid-depth plane, enclosed by higher parapets and adjacent roof decks.",
 "major_surfaces": [
  "Large central concrete rooftop court/floor, cracked and stained, occupying the middle of frame.",
  "Tall rectangular concrete rooftop room/parapet structure around the central court, with stained vertical walls and two open metal doors on the upper wall.",
  "Front/lower parapet wall of the central court with a narrow horizontal warm-lit window.",
  "Left upper rooftop terrace/platform separated by low concrete walls, with leaf debris and weathered concrete.",
  "Lower-left staircase system with concrete steps, landings, rust-colored metal railings, and surrounding parapet walls.",
  "Right-side rooftop annex/deck with cracked dark concrete, clothesline poles, hanging laundry, blue cylindrical water tank, and pile/cart of wood debris.",
  "Far-right higher/outer rooftop walkway and parapet edge where a lone figure stands.",
  "Surrounding neighboring buildings: flat gray roofs, green roof panels, red tiled roof, brick and concrete facades, windows, balconies, overhead utility wires.",
  "Bottom foreground exterior walkway/roof lane and blue corrugated roof, plus tree foliage at lower right.",
  "Left edge alley/drive area with parked vehicles and building walls."
 ],
 "occlusion_order": "Nearest/lowest foreground elements are the bottom exterior roof lane, blue corrugated roof, lower parapets, tree branches, and stair railings, which would occlude lower bodies if overlapping. The main central court subjects sit behind the front parapet lip but in front of the rear wall and open doors. Doorway subjects are partially framed/occluded by door jambs and metal door panels. The man at the left window is adjacent to/partly occluded by the central building side wall and window frame. The right-annex subjects are behind the central court’s right parapet wall but in front of the laundry, tank, and debris unless overlapping. The upper-left pair are behind the nearer left parapet edge and in front of background apartment roofs. The far-right rooftop figure is on a background/right roof plane, visually behind the right annex parapets and utility cables. Background buildings, roofs, cables, and distant facades are the rearmost layers.",
 "subjects": [
  {
   "depth_plane": "Upper-left adjacent rooftop terrace, behind the central court and above/left of it.",
   "label": "Upper-left pair, man A",
   "pose": "Standing upright in dark jacket and jeans, body angled slightly toward the other man as if conversing; arms close to body.",
   "screen_zone": "Upper left-of-center, on narrow roof strip just above the left side of the central structure.",
   "support_contact": "Both feet planted on the weathered concrete roof surface near the parapet edge."
  },
  {
   "depth_plane": "Upper-left adjacent rooftop terrace, same plane as man A.",
   "label": "Upper-left pair, man B",
   "pose": "Standing upright in dark jacket, turned toward man A, slight contrapposto/conversation stance.",
   "screen_zone": "Upper left-of-center, just to the right of man A near the same parapet line.",
   "support_contact": "Feet on the concrete rooftop strip, close to the central roof wall edge."
  },
  {
   "depth_plane": "Central rooftop room threshold, rear/upper wall of central court.",
   "label": "Left rear doorway figure",
   "pose": "Standing partly inside/open doorway, body facing outward into the courtyard, dark clothing with light shirt visible; relaxed vertical posture.",
   "screen_zone": "Upper middle-left of the central court, framed by the left open metal door.",
   "support_contact": "Feet at the doorway threshold/interior floor level, contacting the sill/door landing."
  },
  {
   "depth_plane": "Central rooftop room threshold, rear/upper wall of central court.",
   "label": "Right rear doorway figure",
   "pose": "Standing in the right doorway, facing outward; dark coat and trousers, arms low, framed by the open door panel.",
   "screen_zone": "Upper middle-right of central court, inside the right open doorway.",
   "support_contact": "Feet planted on the doorway threshold/interior floor, just behind the court floor plane."
  },
  {
   "depth_plane": "Central court left side, beside the building wall/window; mid-ground.",
   "label": "Left wall/window man",
   "pose": "Standing side-on to the courtyard, facing the warm-lit window/opening, hands raised near chest as if holding phone or manipulating the frame.",
   "screen_zone": "Left-middle edge of the central court, adjacent to the vertical wall.",
   "support_contact": "Feet on central concrete court floor immediately beside the wall/window base."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 1, left of cluster",
   "pose": "Standing facing inward toward the group, dark puffer jacket, head slightly down toward the others/phone.",
   "screen_zone": "Lower middle-right of the central court cluster.",
   "support_contact": "Both feet on central cracked concrete floor."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 2, phone-holder/inner left",
   "pose": "Standing close to the group, looking down with hands together as if holding or showing an object/phone.",
   "screen_zone": "Center-right of the central court, slightly above the left member of the group.",
   "support_contact": "Feet planted on central court concrete."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 3, tall upper-right of cluster",
   "pose": "Standing upright in dark jacket, facing inward/down toward group; slightly separated behind the others.",
   "screen_zone": "Right-center of the central court cluster.",
   "support_contact": "Feet on central concrete floor."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 4, back-to-camera foreground of cluster",
   "pose": "Standing with back to camera in dark padded jacket, facing the rest of the group; legs apart slightly.",
   "screen_zone": "Lower center-right of central court cluster.",
   "support_contact": "Feet on central concrete floor, closest member of the central group to the lower edge."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 5, patterned-coat/right member",
   "pose": "Standing facing the back-to-camera man and the group, slightly turned left; patterned/dark coat visible.",
   "screen_zone": "Lower right side of the central group.",
   "support_contact": "Feet on central concrete floor."
  },
  {
   "depth_plane": "Right side of central court near parapet/wall, slightly separated from main group.",
   "label": "Right wall phone man",
   "pose": "Standing alone, side-on, head down toward hands as if using a phone; light gray/brown coat.",
   "screen_zone": "Right-middle of central court, near the right parapet and warm wall light.",
   "support_contact": "Feet on central court floor close to the right wall/parapet edge."
  },
  {
   "depth_plane": "Right rooftop annex/deck beyond the central court wall.",
   "label": "Right annex lower figure",
   "pose": "Standing near laundry/debris area, dark jacket and jeans, head down; body angled diagonally toward lower right.",
   "screen_zone": "Right side of frame, lower half of the right annex, next to hanging laundry and debris pile.",
   "support_contact": "Feet on cracked dark concrete roof surface of the right annex."
  },
  {
   "depth_plane": "Far-right outer rooftop/walkway, background-right plane.",
   "label": "Far-right rooftop figure",
   "pose": "Standing/walking slowly along roof edge in dark coat, body facing left/downward, one leg advanced.",
   "screen_zone": "Extreme upper-right quadrant near the right border.",
   "support_contact": "Feet on the far-right flat roof/walkway surface near a parapet edge."
  },
  {
   "depth_plane": "Lower-left staircase, foreground-midground transition.",
   "label": "Staircase descending man",
   "pose": "Standing or descending on the stair run, dark coat, body facing down the steps toward camera/lower frame.",
   "screen_zone": "Lower left-of-center on the stairwell between railings.",
   "support_contact": "Feet on separate stair treads, partially enclosed by metal railings."
  },
  {
   "depth_plane": "Bottom exterior walkway/roof lane, foreground.",
   "label": "Bottom-left standing man",
   "pose": "Standing still in long coat, mostly back/side to camera, looking upward/right toward the rooftop complex.",
   "screen_zone": "Lower left quadrant, just below the staircase base and inside the foreground roof lane.",
   "support_contact": "Feet planted on the lower concrete walkway/roof surface."
  }
 ]
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

S11_Shot3 loc=L10 · framing=close · 인물=수리영

계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.

생성 순서 ① control/plate/임시
뿌리 마킹 (카메라 콘+인물 서클) [CONTROL] gpt-image-2 · 151.1s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch with circled capital letters marking site elements (and possibly a legend panel on the right). Keep the sketch EXACTLY as it is — same geometry, same circled letters, same legend, do not redraw or restyle anything.
ADD exactly these annotations for ONE camera setup:
- ONE green camera icon with a green triangular view-CONE showing where the camera stands and what it looks at, following this staging description:
Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
- 1 red circle(s) with capital letters (P) inside the view-cone where the staging places the people:
  * {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}
Add NOTHING else — no new structures, no new text other than the new capital letters in their small circles.
참조 이미지(역할 라벨 포함): root_B.png
빈 배경 plate [ENV] gpt-image-2 · 117.9s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch of one real place,
with a green camera icon and view-cone marking ONE camera position and
its viewing direction. Circled letters mark site elements; red lettered
circles (if any) mark where people stand — but render NO people.

Draw the PHOTOREALISTIC outdoor view that THAT camera sees from its
marked position at eye level, looking along the view-cone: the
structures, ground surfaces, openings and approaches the sketch places
in front of that camera, at real-world human scale. This is an EMPTY
background plate: absolutely no people, no text, no letters, no
circles, no arrows, no sketch lines — pure photographic realism.

WHAT THIS PLACE LOOKS LIKE (production data):
- 옥탑방 외곽 골목·시멘트 계단: 다세대 빌라 마당의 후미진 구석과 옥탑방으로 올라가는 가파르고 낡은 시멘트 계단. (특징: 다세대 빌라 입구 마당; 후미진 구석 공간; 낡고 가파른 시멘트 계단)

Site orientation notes:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}
참조 이미지(역할 라벨 포함): root_marked.png
임시샷 nb2 · 17.4s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
윤곽 gpt-image-2 · 106.3s
prompt/refs (실제 호출 기록)
Convert the attached photograph into a clean LINE-ART CONTOUR drawing: thin dark ink lines on a plain white background. Preserve the EXACT composition, framing, perspective and proportions — trace the outline of every structure, surface edge and human figure as it appears. No shading, no colour fills, no photo texture, no text, no added or removed objects.
참조 이미지(역할 라벨 포함): temp.png
경로 A — 직행
A 최종샷 (plate+CONTROL+passport) nb2 · 31.5s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png
경로 B — VLM 구도 텍스트
B1 재생성 배경 gpt-image-2 · 119.8s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "Tight close-up from a slight low angle, looking marginally upward at the subject’s face. The frame is mostly level, not strongly canted; vertical wall lines remain near-vertical and stair edges remain mostly horizontal.", "height": "Camera is around the subject’s seated/crouched head height but a little below her eyeline, close enough to crop the top of hair and lower torso.", "lens_feel": "Moderate wide-to-normal close lens feel with very close subject distance; face is large and intimate with mild perspective expansion, while the background stairs and wall fall softly out of focus."}, "empty_background_requirements": "An empty plate must preserve the same cool-lit concrete stairwell/corner: the right two-thirds should contain the vertical grey concrete wall with stains, speckling, vertical seams and mottled texture; the left third should contain the dim stair flight with horizontal step edges/risers receding upward/backward. Areas currently hidden by the woman must be filled with continuous wall and stair detail: concrete wall behind her face, hair, shoulder and coat on the right/center; the blurred steps and dark stairwell behind the hair mass on the left; and the lower foreground/background where her black clothing occupies the frame. Lighting must match the blue-grey ambient shade with a faint warm rim/highlight from upper left, and the background depth of field should remain soft so the person can be reinserted sharply in the foreground.", "horizon_and_depth": "No natural horizon is visible. Depth is defined by the shallow foreground portrait plane against a close concrete wall and a stairwell receding diagonally backward on the left. The right wall reads as a near vertical plane just behind the subject, while the left stairs create the main depth cue through repeated horizontal tread lines fading into blur. Background focus is soft, emphasizing the subject as the nearest object.", "major_surfaces": ["Near vertical concrete wall on the right and behind the subject, blue-grey, stained and speckled, with subtle seams and weathering.", "Concrete staircase on the left background, visible as stacked horizontal treads/risers receding away and upward, darker and blurrier than the wall.", "Dark lower foreground occupied by the subject’s black clothing; no clear floor plane is visible.", "Shadowed stairwell/corner space between the wall and stairs, providing a cool, dim architectural backdrop."], "occlusion_order": "Closest to camera: loose strands of the subject’s black hair, then her face, hair mass, neck and black coat. These occlude the concrete wall across the center/right and the stairwell across the left/center. Behind her is the near concrete wall on the right/center. Farther back, the blurred stair flight occupies the left background. No other people or foreground objects intervene.", "subjects": [{"depth_plane": "Extreme foreground / primary portrait plane, very close to camera and only a short distance in front of the concrete wall.", "label": "young woman", "pose": "Crouched or seated low, leaning slightly back/sideways near the wall. Head tilted and turned toward screen right while eyes look upward off-screen right. Brow is tightly furrowed, eyes squinting, mouth slightly open, conveying strain or alarm. Long dark hair falls around both sides of the face, with many loose strands.", "screen_zone": "Dominates the center and right half of the frame. Forehead and hair reach the top edge; face spans center-right; nose and mouth sit in the right-center/lower-right; hair mass fills much of the center-left and lower center. Black shoulder/coat fills the bottom-right corner.", "support_contact": "Hands and feet are not visible. Lower body is cropped out. Support is implied below the frame, likely seated/crouched on a step or floor, with the back/shoulder close to or lightly against the concrete wall."}]}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): plate.png
B2 최종샷 nb2 · 17.0s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png
경로 C — i2i 윤곽
C1 재생성 배경 gpt-image-2 · 106.5s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png plate.png
C2 최종샷 nb2 · 15.2s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png
S11_Shot3 VLM 구도 분석 JSON
{
 "camera": {
  "angle": "Tight close-up from a slight low angle, looking marginally upward at the subject’s face. The frame is mostly level, not strongly canted; vertical wall lines remain near-vertical and stair edges remain mostly horizontal.",
  "height": "Camera is around the subject’s seated/crouched head height but a little below her eyeline, close enough to crop the top of hair and lower torso.",
  "lens_feel": "Moderate wide-to-normal close lens feel with very close subject distance; face is large and intimate with mild perspective expansion, while the background stairs and wall fall softly out of focus."
 },
 "empty_background_requirements": "An empty plate must preserve the same cool-lit concrete stairwell/corner: the right two-thirds should contain the vertical grey concrete wall with stains, speckling, vertical seams and mottled texture; the left third should contain the dim stair flight with horizontal step edges/risers receding upward/backward. Areas currently hidden by the woman must be filled with continuous wall and stair detail: concrete wall behind her face, hair, shoulder and coat on the right/center; the blurred steps and dark stairwell behind the hair mass on the left; and the lower foreground/background where her black clothing occupies the frame. Lighting must match the blue-grey ambient shade with a faint warm rim/highlight from upper left, and the background depth of field should remain soft so the person can be reinserted sharply in the foreground.",
 "horizon_and_depth": "No natural horizon is visible. Depth is defined by the shallow foreground portrait plane against a close concrete wall and a stairwell receding diagonally backward on the left. The right wall reads as a near vertical plane just behind the subject, while the left stairs create the main depth cue through repeated horizontal tread lines fading into blur. Background focus is soft, emphasizing the subject as the nearest object.",
 "major_surfaces": [
  "Near vertical concrete wall on the right and behind the subject, blue-grey, stained and speckled, with subtle seams and weathering.",
  "Concrete staircase on the left background, visible as stacked horizontal treads/risers receding away and upward, darker and blurrier than the wall.",
  "Dark lower foreground occupied by the subject’s black clothing; no clear floor plane is visible.",
  "Shadowed stairwell/corner space between the wall and stairs, providing a cool, dim architectural backdrop."
 ],
 "occlusion_order": "Closest to camera: loose strands of the subject’s black hair, then her face, hair mass, neck and black coat. These occlude the concrete wall across the center/right and the stairwell across the left/center. Behind her is the near concrete wall on the right/center. Farther back, the blurred stair flight occupies the left background. No other people or foreground objects intervene.",
 "subjects": [
  {
   "depth_plane": "Extreme foreground / primary portrait plane, very close to camera and only a short distance in front of the concrete wall.",
   "label": "young woman",
   "pose": "Crouched or seated low, leaning slightly back/sideways near the wall. Head tilted and turned toward screen right while eyes look upward off-screen right. Brow is tightly furrowed, eyes squinting, mouth slightly open, conveying strain or alarm. Long dark hair falls around both sides of the face, with many loose strands.",
   "screen_zone": "Dominates the center and right half of the frame. Forehead and hair reach the top edge; face spans center-right; nose and mouth sit in the right-center/lower-right; hair mass fills much of the center-left and lower center. Black shoulder/coat fills the bottom-right corner.",
   "support_contact": "Hands and feet are not visible. Lower body is cropped out. Support is implied below the frame, likely seated/crouched on a step or floor, with the back/shoulder close to or lightly against the concrete wall."
  }
 ]
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

S10_Shot6 loc=L03 · framing=medium · 인물=없음

방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.

생성 순서 ① control/plate/임시
뿌리 마킹 (카메라 콘+인물 서클) [CONTROL] gpt-image-2 · 112.4s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch with circled capital letters marking site elements (and possibly a legend panel on the right). Keep the sketch EXACTLY as it is — same geometry, same circled letters, same legend, do not redraw or restyle anything.
ADD exactly these annotations for ONE camera setup:
- ONE green camera icon with a green triangular view-CONE showing where the camera stands and what it looks at, following this staging description:
Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
- 2 red circle(s) with capital letters (P) (Q) inside the view-cone where the staging places the people:
  * {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
  * {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
Add NOTHING else — no new structures, no new text other than the new capital letters in their small circles.
참조 이미지(역할 라벨 포함): root_B.png
빈 배경 plate [ENV] gpt-image-2 · 160.5s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch of one real place,
with a green camera icon and view-cone marking ONE camera position and
its viewing direction. Circled letters mark site elements; red lettered
circles (if any) mark where people stand — but render NO people.

Draw the PHOTOREALISTIC outdoor view that THAT camera sees from its
marked position at eye level, looking along the view-cone: the
structures, ground surfaces, openings and approaches the sketch places
in front of that camera, at real-world human scale. This is an EMPTY
background plate: absolutely no people, no text, no letters, no
circles, no arrows, no sketch lines — pure photographic realism.

WHAT THIS PLACE LOOKS LIKE (production data):
- 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)

Site orientation notes:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]
참조 이미지(역할 라벨 포함): root_marked.png
임시샷 nb2 · 20.0s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
윤곽 gpt-image-2 · 145.2s
prompt/refs (실제 호출 기록)
Convert the attached photograph into a clean LINE-ART CONTOUR drawing: thin dark ink lines on a plain white background. Preserve the EXACT composition, framing, perspective and proportions — trace the outline of every structure, surface edge and human figure as it appears. No shading, no colour fills, no photo texture, no text, no added or removed objects.
참조 이미지(역할 라벨 포함): temp.png
경로 A — 직행
A 최종샷 (plate+CONTROL+passport) nb2 · 19.3s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
경로 B — VLM 구도 텍스트
B1 재생성 배경 gpt-image-2 · 93.7s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "Exterior view looking almost square-on into a rooftop-room window wall; very slight left-to-right obliqueness, with verticals kept nearly parallel and no dramatic tilt.", "height": "Camera is roughly at window mid-height / adult chest-to-shoulder height, slightly above the low sill but below the standing subject’s head level.", "lens_feel": "Moderate-to-long normal lens feel with compressed, flattened planes through glass; shallow atmospheric separation comes from dirty/reflective glass rather than strong optical blur."}, "empty_background_requirements": "The empty plate must be the same locked-off exterior view of the rooftop-room facade with no people behind the glass. It must preserve the full window assembly: open iron door on the left, dark interior doorway beyond it, concrete facade and side jambs, sliding window frames and central mullion, dirty blue-gray reflective glass panels, bottom sill/low parapet, faint warm interior/reflection glow on the left pane, cooler blue reflection across the right pane, interior back wall texture visible through the glass, and the dark vertical frame at far right. Reflections, grime, smudges, and the glass opacity must remain, because the people would need to be reinserted as dark silhouettes behind/through this glass layer, partially veiled by reflections and window dirt.", "horizon_and_depth": "No exterior horizon is visible. Depth is organized as flat architectural layers: foreground terrace/low sill at the bottom, the exterior door and window frame plane, reflective dirty glass as the dominant occluding plane, then the dim rooftop room interior with a back wall. The figures sit behind the glass and read mostly as silhouettes, so the composition is deliberately compressed and voyeuristic.", "major_surfaces": ["Weathered concrete facade surrounding the window opening.", "Open iron door at far left, angled outward toward camera, with dark interior doorway behind it.", "Large exterior window/glass wall occupying most of the frame, divided by metal mullions and sliding-window frames.", "Dirty reflective glass surface with blue-gray cast, grime, streaks, and layered reflections.", "Interior back wall seen through the glass, mottled and cool-toned.", "Bottom exterior sill / low wall running horizontally across the lower frame.", "Dark vertical frame/jamb at far right.", "Partial foreground rooftop railing/fixture at lower left edge."], "occlusion_order": "Closest to camera are the left foreground railing/fixture and the open iron door edge, then the exterior window frames/mullions and low sill. The dirty reflective glass plane lies in front of both people and partially masks them with grime/reflections. Behind the glass, P overlaps and visually dominates Q: P’s bent torso and head hover over Q’s head/upper body. Q is lower and slightly farther/right, with lower body partly hidden by the bottom frame/sill. The interior wall is the deepest visible plane.", "subjects": [{"depth_plane": "Behind the exterior glass inside the rooftop room, close to the window but visually flattened by the reflective pane; slightly left/behind Q in the action grouping.", "label": "P - standing/bending figure", "pose": "Tall dark silhouette bent sharply forward at the waist, head and shoulders leaning down toward the second figure; one arm appears lowered near Q, posture suggesting looming, assisting, or grappling.", "screen_zone": "Center-right, spanning from lower middle to upper middle of the window; head near the upper-right quadrant of the main glass panel, torso crossing the central vertical area.", "support_contact": "Feet/legs are on the interior floor but mostly obscured by the bottom window frame and dark glass; body weight appears carried through both legs while leaning forward."}, {"depth_plane": "Behind the same exterior glass plane, lower and slightly to the right of P, inside the room near the window/interior floor line.", "label": "Q - crouched/kneeling figure", "pose": "Compact figure bent over or crouched/kneeling, head lowered forward; torso angles down toward the lower right, with one arm/hand possibly braced downward.", "screen_zone": "Lower right-center of the main window, below P’s head and torso; head and shoulders sit just right of center, body descends toward the lower-right edge.", "support_contact": "Likely kneeling or crouching on the interior floor; knees/feet and possible hand contact are mostly hidden by the sill, bottom frame, darkness, and glass reflections."}]}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): plate.png
B2 최종샷 nb2 · 17.0s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png
경로 C — i2i 윤곽
C1 재생성 배경 gpt-image-2 · 170.9s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png plate.png
C2 최종샷 nb2 · 17.3s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C.png
S10_Shot6 VLM 구도 분석 JSON
{
 "camera": {
  "angle": "Exterior view looking almost square-on into a rooftop-room window wall; very slight left-to-right obliqueness, with verticals kept nearly parallel and no dramatic tilt.",
  "height": "Camera is roughly at window mid-height / adult chest-to-shoulder height, slightly above the low sill but below the standing subject’s head level.",
  "lens_feel": "Moderate-to-long normal lens feel with compressed, flattened planes through glass; shallow atmospheric separation comes from dirty/reflective glass rather than strong optical blur."
 },
 "empty_background_requirements": "The empty plate must be the same locked-off exterior view of the rooftop-room facade with no people behind the glass. It must preserve the full window assembly: open iron door on the left, dark interior doorway beyond it, concrete facade and side jambs, sliding window frames and central mullion, dirty blue-gray reflective glass panels, bottom sill/low parapet, faint warm interior/reflection glow on the left pane, cooler blue reflection across the right pane, interior back wall texture visible through the glass, and the dark vertical frame at far right. Reflections, grime, smudges, and the glass opacity must remain, because the people would need to be reinserted as dark silhouettes behind/through this glass layer, partially veiled by reflections and window dirt.",
 "horizon_and_depth": "No exterior horizon is visible. Depth is organized as flat architectural layers: foreground terrace/low sill at the bottom, the exterior door and window frame plane, reflective dirty glass as the dominant occluding plane, then the dim rooftop room interior with a back wall. The figures sit behind the glass and read mostly as silhouettes, so the composition is deliberately compressed and voyeuristic.",
 "major_surfaces": [
  "Weathered concrete facade surrounding the window opening.",
  "Open iron door at far left, angled outward toward camera, with dark interior doorway behind it.",
  "Large exterior window/glass wall occupying most of the frame, divided by metal mullions and sliding-window frames.",
  "Dirty reflective glass surface with blue-gray cast, grime, streaks, and layered reflections.",
  "Interior back wall seen through the glass, mottled and cool-toned.",
  "Bottom exterior sill / low wall running horizontally across the lower frame.",
  "Dark vertical frame/jamb at far right.",
  "Partial foreground rooftop railing/fixture at lower left edge."
 ],
 "occlusion_order": "Closest to camera are the left foreground railing/fixture and the open iron door edge, then the exterior window frames/mullions and low sill. The dirty reflective glass plane lies in front of both people and partially masks them with grime/reflections. Behind the glass, P overlaps and visually dominates Q: P’s bent torso and head hover over Q’s head/upper body. Q is lower and slightly farther/right, with lower body partly hidden by the bottom frame/sill. The interior wall is the deepest visible plane.",
 "subjects": [
  {
   "depth_plane": "Behind the exterior glass inside the rooftop room, close to the window but visually flattened by the reflective pane; slightly left/behind Q in the action grouping.",
   "label": "P - standing/bending figure",
   "pose": "Tall dark silhouette bent sharply forward at the waist, head and shoulders leaning down toward the second figure; one arm appears lowered near Q, posture suggesting looming, assisting, or grappling.",
   "screen_zone": "Center-right, spanning from lower middle to upper middle of the window; head near the upper-right quadrant of the main glass panel, torso crossing the central vertical area.",
   "support_contact": "Feet/legs are on the interior floor but mostly obscured by the bottom window frame and dark glass; body weight appears carried through both legs while leaning forward."
  },
  {
   "depth_plane": "Behind the same exterior glass plane, lower and slightly to the right of P, inside the room near the window/interior floor line.",
   "label": "Q - crouched/kneeling figure",
   "pose": "Compact figure bent over or crouched/kneeling, head lowered forward; torso angles down toward the lower right, with one arm/hand possibly braced downward.",
   "screen_zone": "Lower right-center of the main window, below P’s head and torso; head and shoulders sit just right of center, body descends toward the lower-right edge.",
   "support_contact": "Likely kneeling or crouching on the interior floor; knees/feet and possible hand contact are mostly hidden by the sill, bottom frame, darkness, and glass reflections."
  }
 ]
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

4.2 실외 v2 — 인원/시점/마커 계약 3줄

S4_Shot1 loc=L03 · framing=wide · 인물=없음

인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.

생성 순서 ① control/plate/임시
뿌리 마킹 (카메라 콘+인물 서클) [CONTROL]
빈 배경 plate [ENV] gpt-image-2 · 126.9s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch of one real place,
with a green camera icon and view-cone marking ONE camera position and
its viewing direction. Circled letters mark site elements; red lettered
circles (if any) mark where people stand — but render NO people.

Draw the PHOTOREALISTIC outdoor view that THAT camera sees from its
marked position at eye level, looking along the view-cone: the
structures, ground surfaces, openings and approaches the sketch places
in front of that camera, at real-world human scale. This is an EMPTY
background plate: absolutely no people, no text, no letters, no
circles, no arrows, no sketch lines — pure photographic realism.

WHAT THIS PLACE LOOKS LIKE (production data):
- 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)

Site orientation notes:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
참조 이미지(역할 라벨 포함): root_marked.png
임시샷 nb2 · 18.2s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
윤곽 gpt-image-2 · 136.6s
prompt/refs (실제 호출 기록)
Convert the attached photograph into a clean LINE-ART CONTOUR drawing: thin dark ink lines on a plain white background. Preserve the EXACT composition, framing, perspective and proportions — trace the outline of every structure, surface edge and human figure as it appears. No shading, no colour fills, no photo texture, no text, no added or removed objects.
참조 이미지(역할 라벨 포함): temp.png
경로 A — 직행
A 최종샷 (plate+CONTROL+passport) nb2 · 17.4s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
경로 B — VLM 구도 텍스트
B1 재생성 배경 gpt-image-2 · 132.3s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "High oblique establishing view looking slightly downward across a dense rooftop neighborhood; camera faces roughly into the roofscape rather than straight down, with strong receding diagonals from parapets and alleys.", "height": "Elevated, likely from an upper-floor window or neighboring rooftop, several meters above the foreground courtyard and above the central roof deck; eye line is near the upper portions of midground rooftops.", "lens_feel": "Wide panoramic lens feel with broad horizontal field of view; mild wide-angle spatial expansion, deep focus, little subject isolation, extensive architectural detail from foreground to skyline."}, "empty_background_requirements": "The empty plate should be the same overcast rooftop panorama with no people added or removed. It must include the central flat-roof concrete hut with open metal door, stairs and rust-colored handrails in the lower center, surrounding parapet walls, the foreground concrete courtyard, blue car at lower left, brick building face at far left, right-side yard with clothesline, blue water tank, wooden platform/bench with ropes/netting, shrubs/trees, all rooftop objects, stains, puddle marks, vents, railings, windows, distant apartment towers, hazy hills, and gray cloudy sky. If people were to be inserted later, the plate must preserve unobstructed roof/floor contact areas, parapet edges, and cast/contact shadow zones on the concrete surfaces.", "horizon_and_depth": "Horizon is high in the frame, softened by haze and partly hidden by distant apartment blocks and low hills. Depth is layered: immediate foreground courtyard and low parapet at bottom; left foreground brick facade and parked car; central midground rooftop hut and stairs; multiple receding concrete roofs and parapets; distant high-rise skyline under cloudy sky. Atmospheric haze reduces contrast toward the background, creating clear depth separation.", "major_surfaces": ["Large gray concrete rooftop/courtyard floors with weather staining, cracks, damp patches, and scattered weeds.", "Low concrete parapet walls forming terraces, alleys, and roof edges throughout the frame.", "Central flat-roofed concrete utility/room structure with peeling exterior, open dark doorway, yellow-lit/amber window panels, and roof slab above.", "Brick apartment/building facades on far left and right, with dark-framed windows and drain pipes.", "Stair flight and landing in lower center with rusted metal railings leading up to the central structure.", "Right-side service yard surface with clothesline, blue cylindrical water tank, shrubs, and wooden platform/bench.", "Distant apartment towers and mid-rise buildings forming the skyline.", "Cloudy blue-gray sky occupying the upper band of the image."], "occlusion_order": "Nearest occluders are the bottom parapet edge, lower-right partial vertical structure, and foreground courtyard elements. The stair railings and central parapet overlap the central building base. The central rooftop hut occludes portions of the midground roofs behind it. Left brick building and right brick building frame and occlude side background structures. Midground parapets and rooftop volumes overlap one another in a stepped sequence before the distant high-rises, which sit behind all rooftop architecture. No human subjects are visible.", "subjects": []}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): plate.png
B2 최종샷 nb2 · 15.9s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png
경로 C — i2i 윤곽
C1 재생성 배경 gpt-image-2 · 143.8s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png plate.png
C2 최종샷 nb2 · 16.5s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C.png
m1 재생성 배경+마네킹 gpt-image-2 · 208.7s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

Where each person would stand or sit, place a featureless matte-grey
artist mannequin in that exact pose and scale (no face, no clothing
detail) — everything else stays an empty environment.
PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png plate.png
m2 최종샷 (마네킹 경유) nb2 · 19.4s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C_m.png
S4_Shot1_v2 VLM 구도 분석 JSON
{
 "camera": {
  "angle": "High oblique establishing view looking slightly downward across a dense rooftop neighborhood; camera faces roughly into the roofscape rather than straight down, with strong receding diagonals from parapets and alleys.",
  "height": "Elevated, likely from an upper-floor window or neighboring rooftop, several meters above the foreground courtyard and above the central roof deck; eye line is near the upper portions of midground rooftops.",
  "lens_feel": "Wide panoramic lens feel with broad horizontal field of view; mild wide-angle spatial expansion, deep focus, little subject isolation, extensive architectural detail from foreground to skyline."
 },
 "empty_background_requirements": "The empty plate should be the same overcast rooftop panorama with no people added or removed. It must include the central flat-roof concrete hut with open metal door, stairs and rust-colored handrails in the lower center, surrounding parapet walls, the foreground concrete courtyard, blue car at lower left, brick building face at far left, right-side yard with clothesline, blue water tank, wooden platform/bench with ropes/netting, shrubs/trees, all rooftop objects, stains, puddle marks, vents, railings, windows, distant apartment towers, hazy hills, and gray cloudy sky. If people were to be inserted later, the plate must preserve unobstructed roof/floor contact areas, parapet edges, and cast/contact shadow zones on the concrete surfaces.",
 "horizon_and_depth": "Horizon is high in the frame, softened by haze and partly hidden by distant apartment blocks and low hills. Depth is layered: immediate foreground courtyard and low parapet at bottom; left foreground brick facade and parked car; central midground rooftop hut and stairs; multiple receding concrete roofs and parapets; distant high-rise skyline under cloudy sky. Atmospheric haze reduces contrast toward the background, creating clear depth separation.",
 "major_surfaces": [
  "Large gray concrete rooftop/courtyard floors with weather staining, cracks, damp patches, and scattered weeds.",
  "Low concrete parapet walls forming terraces, alleys, and roof edges throughout the frame.",
  "Central flat-roofed concrete utility/room structure with peeling exterior, open dark doorway, yellow-lit/amber window panels, and roof slab above.",
  "Brick apartment/building facades on far left and right, with dark-framed windows and drain pipes.",
  "Stair flight and landing in lower center with rusted metal railings leading up to the central structure.",
  "Right-side service yard surface with clothesline, blue cylindrical water tank, shrubs, and wooden platform/bench.",
  "Distant apartment towers and mid-rise buildings forming the skyline.",
  "Cloudy blue-gray sky occupying the upper band of the image."
 ],
 "occlusion_order": "Nearest occluders are the bottom parapet edge, lower-right partial vertical structure, and foreground courtyard elements. The stair railings and central parapet overlap the central building base. The central rooftop hut occludes portions of the midground roofs behind it. Left brick building and right brick building frame and occlude side background structures. Midground parapets and rooftop volumes overlap one another in a stepped sequence before the distant high-rises, which sit behind all rooftop architecture. No human subjects are visible.",
 "subjects": []
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

S11_Shot3 loc=L10 · framing=close · 인물=수리영

계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.

생성 순서 ① control/plate/임시
뿌리 마킹 (카메라 콘+인물 서클) [CONTROL]
빈 배경 plate [ENV] gpt-image-2 · 149.7s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch of one real place,
with a green camera icon and view-cone marking ONE camera position and
its viewing direction. Circled letters mark site elements; red lettered
circles (if any) mark where people stand — but render NO people.

Draw the PHOTOREALISTIC outdoor view that THAT camera sees from its
marked position at eye level, looking along the view-cone: the
structures, ground surfaces, openings and approaches the sketch places
in front of that camera, at real-world human scale. This is an EMPTY
background plate: absolutely no people, no text, no letters, no
circles, no arrows, no sketch lines — pure photographic realism.

WHAT THIS PLACE LOOKS LIKE (production data):
- 옥탑방 외곽 골목·시멘트 계단: 다세대 빌라 마당의 후미진 구석과 옥탑방으로 올라가는 가파르고 낡은 시멘트 계단. (특징: 다세대 빌라 입구 마당; 후미진 구석 공간; 낡고 가파른 시멘트 계단)

Site orientation notes:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
참조 이미지(역할 라벨 포함): root_marked.png
임시샷 nb2 · 17.1s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

PEOPLE COUNT CONTRACT: exactly 1 person(s) in frame — 수리영. Absolutely no other people, bystanders or figures anywhere in the frame, foreground or background.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
윤곽 gpt-image-2 · 154.5s
prompt/refs (실제 호출 기록)
Convert the attached photograph into a clean LINE-ART CONTOUR drawing: thin dark ink lines on a plain white background. Preserve the EXACT composition, framing, perspective and proportions — trace the outline of every structure, surface edge and human figure as it appears. No shading, no colour fills, no photo texture, no text, no added or removed objects.
참조 이미지(역할 라벨 포함): temp.png
경로 A — 직행
A 최종샷 (plate+CONTROL+passport) nb2 · 16.8s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

PEOPLE COUNT CONTRACT: exactly 1 person(s) in frame — 수리영. Absolutely no other people, bystanders or figures anywhere in the frame, foreground or background.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png
경로 B — VLM 구도 텍스트
B1 재생성 배경 gpt-image-2 · 136.0s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "High-angle close-up looking down a concrete stairwell axis, with the subject looking upward toward camera left; frame has a slight off-level/diagonal feel from the stair rails and risers.", "height": "Camera is above the seated/kneeling subject’s head height, roughly one to two steps higher, aimed downward at her face and the steps behind her.", "lens_feel": "Moderately wide cinematic close-up in a very wide aspect ratio; close subject with visible environmental context. Shallow-to-moderate depth of field: face and hair are sharp, background steps and side walls are softer but legible."}, "empty_background_requirements": "The empty plate must be the same concrete staircase from the same high downward angle: grey worn steps running horizontally across the frame with riser bands, dark central stair trough receding upward, vertical concrete side walls/curbs on both far left and far right edges, cool bluish grading, mottled stains, small debris/pebbles/leaves on the lower and mid steps, and the same soft focus falloff. It must include the full areas currently hidden by the woman: lower-right steps, central lower risers, right-side stair edge/wall, and the stair surfaces behind her head and shoulders, so her hair, face, and blue shoulder can be reinserted without gaps.", "horizon_and_depth": "No true horizon is visible; depth is established by stacked horizontal stair treads and risers receding upward/back into the frame. The stair lines create layered depth planes from the lower foreground step at the bottom to darker, higher steps near the top. Side walls/curbs converge subtly upward, forming a narrow stairwell corridor. The subject occupies the nearest foreground/mid-foreground plane, while the stair background sits behind her and falls slightly out of focus.", "major_surfaces": ["Foreground/midground grey concrete stair treads with worn, stained texture.", "Horizontal riser faces forming dark bands behind the subject.", "Left vertical concrete side wall/curb, blurred and close to the lens along the left edge.", "Right slanted/vertical concrete side wall or stair curb along the right edge, also receding upward.", "Small scattered debris on steps, including pale chips near lower left/center and a small brown leaf/debris at lower right.", "Subject’s dark hair mass and blue knit/denim-like shoulder forming the dominant foreground surface in the lower-right half."], "occlusion_order": "Closest layer: the woman’s hair, face, neck, and blue shoulder dominate the lower-right and center-right foreground, occluding the lower and middle stair treads and the right-side stair edge. Fine hair strands sit in front of her forehead and cheek. Behind her are the concrete steps, then the side walls/curbs. Debris on visible steps lies behind the subject except where visible in unobstructed left/lower-right areas.", "subjects": [{"depth_plane": "Nearest foreground/mid-foreground, very close to camera; head and shoulders in front of the stair background.", "label": "young woman", "pose": "Tight close-up from slightly above. Head tilted back and turned slightly toward screen left, eyes looking upward off-frame left. Brows deeply furrowed, nose wrinkled, lips pursed/downturned, conveying suspicion, discomfort, or defiance. Long black hair falls around her face and shoulders with loose strands over forehead.", "screen_zone": "Face fills the lower-right quadrant and extends into the center; forehead and hair reach upper center-right; blue shoulder occupies the lower-right corner. Top of head is near the upper-right third, chin near lower center-right. Large empty negative space of stairs remains on the left half.", "support_contact": "No direct hand/foot contact visible. Body appears seated or crouched on the stairs just below frame; shoulder and torso imply support from a lower step outside the visible area."}]}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
PEOPLE COUNT CONTRACT: exactly 1 person(s) in frame — 수리영. Absolutely no other people, bystanders or figures anywhere in the frame, foreground or background.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): plate.png
B2 최종샷 nb2 · 16.9s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

PEOPLE COUNT CONTRACT: exactly 1 person(s) in frame — 수리영. Absolutely no other people, bystanders or figures anywhere in the frame, foreground or background.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png
경로 C — i2i 윤곽
C1 재생성 배경 gpt-image-2 · 137.5s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
PEOPLE COUNT CONTRACT: exactly 1 person(s) in frame — 수리영. Absolutely no other people, bystanders or figures anywhere in the frame, foreground or background.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png plate.png
C2 최종샷 nb2 · 15.6s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

PEOPLE COUNT CONTRACT: exactly 1 person(s) in frame — 수리영. Absolutely no other people, bystanders or figures anywhere in the frame, foreground or background.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png
m1 재생성 배경+마네킹 gpt-image-2 · 123.3s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

Where each person would stand or sit, place a featureless matte-grey
artist mannequin in that exact pose and scale (no face, no clothing
detail) — everything else stays an empty environment.
PEOPLE COUNT CONTRACT: exactly 1 person(s) in frame — 수리영. Absolutely no other people, bystanders or figures anywhere in the frame, foreground or background.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png plate.png
m2 최종샷 (마네킹 경유) nb2 · 15.6s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
PEOPLE IN SHOT: 수리영
CAMERA: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
FRAMING: close
LIGHTING: A cold blue-gray stairwell wash sculpts her face while a faint amber rooftop spill catches the bridge of her nose, making the smell reaction feel physical and ominous.
PERSON: {"angle": "three_quarter_left", "body_pose": "halted mid-stair climb", "character": "수리영", "gaze_direction_kind": "up", "gaze_target_id": null, "subject_state": "alive"}

PEOPLE COUNT CONTRACT: exactly 1 person(s) in frame — 수리영. Absolutely no other people, bystanders or figures anywhere in the frame, foreground or background.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C_m.png [IDENTITY REFERENCE photo of the person referred to as: 수리영] → 0b01920a-4b59-4e19-ba35-e6e033cbd6b4.png
S11_Shot3_v2 VLM 구도 분석 JSON
{
 "camera": {
  "angle": "High-angle close-up looking down a concrete stairwell axis, with the subject looking upward toward camera left; frame has a slight off-level/diagonal feel from the stair rails and risers.",
  "height": "Camera is above the seated/kneeling subject’s head height, roughly one to two steps higher, aimed downward at her face and the steps behind her.",
  "lens_feel": "Moderately wide cinematic close-up in a very wide aspect ratio; close subject with visible environmental context. Shallow-to-moderate depth of field: face and hair are sharp, background steps and side walls are softer but legible."
 },
 "empty_background_requirements": "The empty plate must be the same concrete staircase from the same high downward angle: grey worn steps running horizontally across the frame with riser bands, dark central stair trough receding upward, vertical concrete side walls/curbs on both far left and far right edges, cool bluish grading, mottled stains, small debris/pebbles/leaves on the lower and mid steps, and the same soft focus falloff. It must include the full areas currently hidden by the woman: lower-right steps, central lower risers, right-side stair edge/wall, and the stair surfaces behind her head and shoulders, so her hair, face, and blue shoulder can be reinserted without gaps.",
 "horizon_and_depth": "No true horizon is visible; depth is established by stacked horizontal stair treads and risers receding upward/back into the frame. The stair lines create layered depth planes from the lower foreground step at the bottom to darker, higher steps near the top. Side walls/curbs converge subtly upward, forming a narrow stairwell corridor. The subject occupies the nearest foreground/mid-foreground plane, while the stair background sits behind her and falls slightly out of focus.",
 "major_surfaces": [
  "Foreground/midground grey concrete stair treads with worn, stained texture.",
  "Horizontal riser faces forming dark bands behind the subject.",
  "Left vertical concrete side wall/curb, blurred and close to the lens along the left edge.",
  "Right slanted/vertical concrete side wall or stair curb along the right edge, also receding upward.",
  "Small scattered debris on steps, including pale chips near lower left/center and a small brown leaf/debris at lower right.",
  "Subject’s dark hair mass and blue knit/denim-like shoulder forming the dominant foreground surface in the lower-right half."
 ],
 "occlusion_order": "Closest layer: the woman’s hair, face, neck, and blue shoulder dominate the lower-right and center-right foreground, occluding the lower and middle stair treads and the right-side stair edge. Fine hair strands sit in front of her forehead and cheek. Behind her are the concrete steps, then the side walls/curbs. Debris on visible steps lies behind the subject except where visible in unobstructed left/lower-right areas.",
 "subjects": [
  {
   "depth_plane": "Nearest foreground/mid-foreground, very close to camera; head and shoulders in front of the stair background.",
   "label": "young woman",
   "pose": "Tight close-up from slightly above. Head tilted back and turned slightly toward screen left, eyes looking upward off-frame left. Brows deeply furrowed, nose wrinkled, lips pursed/downturned, conveying suspicion, discomfort, or defiance. Long black hair falls around her face and shoulders with loose strands over forehead.",
   "screen_zone": "Face fills the lower-right quadrant and extends into the center; forehead and hair reach upper center-right; blue shoulder occupies the lower-right corner. Top of head is near the upper-right third, chin near lower center-right. Large empty negative space of stairs remains on the left half.",
   "support_contact": "No direct hand/foot contact visible. Body appears seated or crouched on the stairs just below frame; shoulder and torso imply support from a lower step outside the visible area."
  }
 ]
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

S10_Shot6 loc=L03 · framing=medium · 인물=없음

방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.

생성 순서 ① control/plate/임시
뿌리 마킹 (카메라 콘+인물 서클) [CONTROL]
빈 배경 plate [ENV] gpt-image-2 · 138.0s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch of one real place,
with a green camera icon and view-cone marking ONE camera position and
its viewing direction. Circled letters mark site elements; red lettered
circles (if any) mark where people stand — but render NO people.

Draw the PHOTOREALISTIC outdoor view that THAT camera sees from its
marked position at eye level, looking along the view-cone: the
structures, ground surfaces, openings and approaches the sketch places
in front of that camera, at real-world human scale. This is an EMPTY
background plate: absolutely no people, no text, no letters, no
circles, no arrows, no sketch lines — pure photographic realism.

WHAT THIS PLACE LOOKS LIKE (production data):
- 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)

Site orientation notes:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
참조 이미지(역할 라벨 포함): root_marked.png
임시샷 nb2 · 20.0s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
윤곽 gpt-image-2 · 109.2s
prompt/refs (실제 호출 기록)
Convert the attached photograph into a clean LINE-ART CONTOUR drawing: thin dark ink lines on a plain white background. Preserve the EXACT composition, framing, perspective and proportions — trace the outline of every structure, surface edge and human figure as it appears. No shading, no colour fills, no photo texture, no text, no added or removed objects.
참조 이미지(역할 라벨 포함): temp.png
경로 A — 직행
A 최종샷 (plate+CONTROL+passport) nb2 · 18.8s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
경로 B — VLM 구도 텍스트
B1 재생성 배경 gpt-image-2 · 141.0s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "Nearly straight-on to the exterior wall/window, with a very slight downward and left-oblique view; verticals remain mostly upright and the window is treated as a flat compositional plane.", "height": "Approximately standing eye/chest height relative to the window; the camera is centered slightly below the upper window frame and above the lower sill, looking level to very slightly downward.", "lens_feel": "Moderate-wide anamorphic/cinematic feel; broad horizontal field, minimal perspective exaggeration, shallow-to-moderate depth with the window/frame and silhouettes dominant and the distant rooftop/city softened by glass/reflection."}, "empty_background_requirements": "The empty plate must preserve the full concrete exterior wall and the entire metal-framed sliding window in exactly the same position: thick grey stucco/concrete border around all sides, top and bottom metal rails, the central vertical sliding mullion slightly right of center, left and right glass panes with grime/reflection. The left pane must still contain the reflected/seen rooftop stairwell: wet concrete floor, stairs rising upward from lower-left toward mid-frame, copper/brown handrails, rooftop parapet walls, distant grey buildings, utility poles/wires, and dim blue dusk sky. The right pane must show the dim interior room/background without people: grey interior wall, dark side window/door rectangle at far right, warm amber light glow near the lower-right/mid-right area, faint glass reflections, and the same darker vertical interior edge/reflection near the right side. It must also retain the glass tint, smudges, low-contrast reflections, and the dark lower sill band so the two silhouetted figures can be reinserted behind the right pane with their lower bodies partially hidden/cropped by the bottom frame.", "horizon_and_depth": "Depth is layered through a foreground architectural frame, reflective glass, interior figures, and background reflections/interior surfaces. The implied exterior skyline/horizon sits in the upper half of the glass, roughly around the upper-middle of the left pane, softened by dusk haze. Strong depth cues come from the rooftop stairs and handrails in the left pane receding diagonally from lower-left toward center, while the right pane is flatter and darker, dominated by the near silhouettes against a dim interior wall and warm backlight.", "major_surfaces": ["Rough grey concrete/stucco wall surrounding the window, filling the outer frame of the image.", "Large horizontal metal sliding-window frame with top rail, bottom rail, side jambs, and a central vertical mullion dividing the two panes.", "Dirty reflective glass panes, blue-grey and slightly desaturated, carrying rooftop/city reflections and interior silhouettes.", "Wet rooftop concrete floor reflected/visible through the left pane, with sheen and dark patches.", "Concrete rooftop stair structure in the left pane, including steps, parapet/side walls, and landing.", "Copper/brown metal stair railings and posts in the left pane, forming diagonal perspective lines.", "Distant urban buildings, utility poles, wires, and dusk sky reflected/seen across the upper glass.", "Dim grey interior wall behind the subjects in the right pane with a warm amber light spill near lower right.", "Dark rectangular opening/window/door shape at the far right inside the right pane."], "occlusion_order": "Front to back: rough exterior concrete wall and metal window frame are foremost and occlude the panes at all edges; the central vertical mullion cuts between the panes and occludes the interior/reflections; the glass surface layer overlays reflections, grime, and tint over everything behind it; the two people are behind the right pane, appearing as dark silhouettes; the leaning standing figure overlaps and partially occludes the seated/slumped figure at the shoulder/upper back area; behind them are the interior wall and warm light; left-pane rooftop stairs/railings/city appear as reflected or viewed background elements behind/on the glass layer.", "subjects": [{"depth_plane": "Behind the right glass pane in the near interior plane, closer than the interior wall and warm light; partially masked by the lower window rail at the bottom.", "label": "Standing/leaning figure in dark blue", "pose": "Torso bent forward from left to right, head bowed over the other person; left/near arm angled down, one hand/forearm placed on or near the other figure's shoulder/upper back; legs vertical and close together, body forming a protective or burdened hunch.", "screen_zone": "Right half of the image, mainly the left side of the right window pane; head around upper-right-center, torso crossing the central-right area, legs descending toward the bottom edge just right of the central mullion.", "support_contact": "Standing on the unseen interior floor; feet/lower legs are obscured by darkness and the bottom window frame, but weight reads as supported by both legs. Hand/arm makes contact with the seated/slumped figure's shoulder/back."}, {"depth_plane": "Behind the right glass pane in the same near interior plane, slightly to the right and partly in front of/overlapped by the leaning figure; silhouetted against warm interior light.", "label": "Seated or slumped figure with reddish upper garment", "pose": "Bent forward with head dropped toward the right, neck and shoulders rounded; torso angled diagonally down to the right; one arm hangs limp downward along the right side; lower body dark and cropped by the bottom frame.", "screen_zone": "Lower-right quadrant of the right pane; head near mid-right, shoulders just right of center, torso and legs occupying the bottom-right area.", "support_contact": "Supported by an unseen seat, bed, ledge, or low surface inside the room, mostly hidden below the window sill and silhouette; no visible hand contact with the floor, with the right arm hanging freely."}]}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): plate.png
B2 최종샷 nb2 · 18.6s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png
경로 C — i2i 윤곽
C1 재생성 배경 gpt-image-2 · 141.3s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

Follow the attached line contour's composition EXACTLY —
same framing, perspective and structure placement.

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): contour.png plate.png
C2 최종샷 nb2 · 19.0s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_C.png
S10_Shot6_v2 VLM 구도 분석 JSON
{
 "camera": {
  "angle": "Nearly straight-on to the exterior wall/window, with a very slight downward and left-oblique view; verticals remain mostly upright and the window is treated as a flat compositional plane.",
  "height": "Approximately standing eye/chest height relative to the window; the camera is centered slightly below the upper window frame and above the lower sill, looking level to very slightly downward.",
  "lens_feel": "Moderate-wide anamorphic/cinematic feel; broad horizontal field, minimal perspective exaggeration, shallow-to-moderate depth with the window/frame and silhouettes dominant and the distant rooftop/city softened by glass/reflection."
 },
 "empty_background_requirements": "The empty plate must preserve the full concrete exterior wall and the entire metal-framed sliding window in exactly the same position: thick grey stucco/concrete border around all sides, top and bottom metal rails, the central vertical sliding mullion slightly right of center, left and right glass panes with grime/reflection. The left pane must still contain the reflected/seen rooftop stairwell: wet concrete floor, stairs rising upward from lower-left toward mid-frame, copper/brown handrails, rooftop parapet walls, distant grey buildings, utility poles/wires, and dim blue dusk sky. The right pane must show the dim interior room/background without people: grey interior wall, dark side window/door rectangle at far right, warm amber light glow near the lower-right/mid-right area, faint glass reflections, and the same darker vertical interior edge/reflection near the right side. It must also retain the glass tint, smudges, low-contrast reflections, and the dark lower sill band so the two silhouetted figures can be reinserted behind the right pane with their lower bodies partially hidden/cropped by the bottom frame.",
 "horizon_and_depth": "Depth is layered through a foreground architectural frame, reflective glass, interior figures, and background reflections/interior surfaces. The implied exterior skyline/horizon sits in the upper half of the glass, roughly around the upper-middle of the left pane, softened by dusk haze. Strong depth cues come from the rooftop stairs and handrails in the left pane receding diagonally from lower-left toward center, while the right pane is flatter and darker, dominated by the near silhouettes against a dim interior wall and warm backlight.",
 "major_surfaces": [
  "Rough grey concrete/stucco wall surrounding the window, filling the outer frame of the image.",
  "Large horizontal metal sliding-window frame with top rail, bottom rail, side jambs, and a central vertical mullion dividing the two panes.",
  "Dirty reflective glass panes, blue-grey and slightly desaturated, carrying rooftop/city reflections and interior silhouettes.",
  "Wet rooftop concrete floor reflected/visible through the left pane, with sheen and dark patches.",
  "Concrete rooftop stair structure in the left pane, including steps, parapet/side walls, and landing.",
  "Copper/brown metal stair railings and posts in the left pane, forming diagonal perspective lines.",
  "Distant urban buildings, utility poles, wires, and dusk sky reflected/seen across the upper glass.",
  "Dim grey interior wall behind the subjects in the right pane with a warm amber light spill near lower right.",
  "Dark rectangular opening/window/door shape at the far right inside the right pane."
 ],
 "occlusion_order": "Front to back: rough exterior concrete wall and metal window frame are foremost and occlude the panes at all edges; the central vertical mullion cuts between the panes and occludes the interior/reflections; the glass surface layer overlays reflections, grime, and tint over everything behind it; the two people are behind the right pane, appearing as dark silhouettes; the leaning standing figure overlaps and partially occludes the seated/slumped figure at the shoulder/upper back area; behind them are the interior wall and warm light; left-pane rooftop stairs/railings/city appear as reflected or viewed background elements behind/on the glass layer.",
 "subjects": [
  {
   "depth_plane": "Behind the right glass pane in the near interior plane, closer than the interior wall and warm light; partially masked by the lower window rail at the bottom.",
   "label": "Standing/leaning figure in dark blue",
   "pose": "Torso bent forward from left to right, head bowed over the other person; left/near arm angled down, one hand/forearm placed on or near the other figure's shoulder/upper back; legs vertical and close together, body forming a protective or burdened hunch.",
   "screen_zone": "Right half of the image, mainly the left side of the right window pane; head around upper-right-center, torso crossing the central-right area, legs descending toward the bottom edge just right of the central mullion.",
   "support_contact": "Standing on the unseen interior floor; feet/lower legs are obscured by darkness and the bottom window frame, but weight reads as supported by both legs. Hand/arm makes contact with the seated/slumped figure's shoulder/back."
  },
  {
   "depth_plane": "Behind the right glass pane in the same near interior plane, slightly to the right and partly in front of/overlapped by the leaning figure; silhouetted against warm interior light.",
   "label": "Seated or slumped figure with reddish upper garment",
   "pose": "Bent forward with head dropped toward the right, neck and shoulders rounded; torso angled diagonally down to the right; one arm hangs limp downward along the right side; lower body dark and cropped by the bottom frame.",
   "screen_zone": "Lower-right quadrant of the right pane; head near mid-right, shoulders just right of center, torso and legs occupying the bottom-right area.",
   "support_contact": "Supported by an unseen seat, bed, ledge, or low surface inside the room, mostly hidden below the window sill and silhouette; no visible hand contact with the floor, with the right arm hanging freely."
  }
 ]
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

4.3 실외 v3 — sketch-hop-before-plate (+v3.1 CONTROL=sketch)

S4_Shot1 loc=L03 · framing=wide · 인물=없음

인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.

생성 순서 ① control/plate/임시
뿌리 마킹 (카메라 콘+인물 서클) [CONTROL]
①' camview 라인아트 (sketch-hop) gpt-image-2 · 154.4s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch of one real place, with
a green camera icon and view-cone marking ONE camera position and its
viewing direction (circled letters are site markers, never people).

Draw the clean LINE-ART sketch of the EYE-LEVEL view that THAT camera sees
from its marked position: thin dark ink lines on a plain white background,
no colour, no shading, no photo texture. The camera stands ON the ground of
its marked spot at human eye height (about 1.6 m) INSIDE the scene — NOT
above it. Show the structures, ground surfaces, openings and approaches the
site sketch places in front of that camera, in correct perspective at
real-world human scale, with the horizon at a natural eye-level height.
Do NOT draw any overhead or bird's-eye view. No people, no text, no
letters, no circles, no arrows — pure line drawing of the environment.
참조 이미지(역할 라벨 포함): root_marked.png
빈 배경 plate [ENV] gpt-image-2 · 119.3s
prompt/refs (실제 호출 기록)
The FIRST attached image is a LINE-ART sketch of one camera's eye-level
view of a real outdoor place — it is the COMPOSITION AND PERSPECTIVE
ground truth. The SECOND attached image is the top-down site sketch of
the same place — use it ONLY to understand materials, fixtures and
spatial relations; never copy its top-down viewpoint or its markers.

Render the PHOTOREALISTIC empty background plate of exactly the view the
line-art sketch shows: same framing, same perspective, same structures,
at real-world human scale. This is an EMPTY plate: no people, no text,
no letters, no circles, no sketch lines — pure photographic realism.

WHAT THIS PLACE LOOKS LIKE (production data):
- 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)

Site orientation notes:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
참조 이미지(역할 라벨 포함): sketch.png root_marked.png
임시샷 nb2 · 17.4s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → root_marked.png
③' 임시샷 v3.1 (CONTROL=sketch) nb2 · 19.1s
prompt/refs (실제 호출 기록)
Create a photorealistic cinematic still that stages this shot inside the
given environment. This is a COMPOSITION DRAFT: the people are ordinary
real humans whose identity does not matter — focus on a strong, natural
composition that matches the camera and placement exactly.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Keep the environment's architecture, materials and lighting from the
environment reference. Place the camera and every person exactly as the
control diagram indicates. Absolutely no text, letters, circles, arrows
or diagram marks in the output.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people.] → plate.png [CAMERA AND PLACEMENT DIAGRAM (top-down control image) — use it ONLY to understand where the camera stands, what it looks at, and where each person is. NEVER copy its drawing style, lines, circles, letters or any marks into the output.] → sketch.png
경로 B — VLM 구도 텍스트
B1 재생성 배경 gpt-image-2 · 131.5s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "Very high oblique overhead / bird’s-eye establishing angle, looking down into a dense cluster of flat-roofed urban buildings. The camera is pitched steeply downward, with only vertical wall faces and roof planes visible; no sky.", "height": "Rooftop-to-crane height, well above the main courtyard and surrounding roofs, roughly several stories up. It looks down into multiple roof levels and narrow alleys.", "lens_feel": "Wide panoramic lens feel with deep focus. Strong architectural perspective and many receding diagonals, but not heavily distorted; everything from foreground parapets to distant roofs remains sharp."}, "empty_background_requirements": "The empty plate must be the same high, wide overhead view of the residential rooftop complex with no people added or removed. It must preserve all architecture and props: the central walled courtyard, concrete parapets, staircases with metal railings at lower left/center, the small rooftop room with open grey door and warm-lit interior, the adjacent flat roof, laundry area with blue water tank and hanging sheets at right, stacked wooden boards and coiled material at lower right, surrounding brick-and-concrete buildings, alleys, rooftop tanks, pipes, windows, weather stains, weeds, rocks, drains, and the parked car at lower left. Since there are no visible human subjects in the still, the empty background is effectively identical to the shown image.", "horizon_and_depth": "No visible horizon line; depth is constructed through stacked roof planes, parapet heights, alleys, and diagonal wall edges. The image has layered depth from the foreground lower parapets and street/courtyard edge, through the central courtyard and rooftop room, to midground and background apartment roofs. Recession runs mainly from lower frame toward upper frame, with strong diagonals leading upper left and upper right through alleys and roof walls.", "major_surfaces": ["Large weathered concrete rooftop/courtyard floor occupying the central lower-middle area, mottled with stains, dirt, weeds, and scattered stones.", "Low concrete parapet walls forming rectangular roof enclosures across the frame.", "Small central rooftop structure/room with flat concrete roof, off-white stained walls, vertical windows, and an open metal door revealing a warm beige interior floor and walls.", "Concrete stairs and landings with silver metal railings in the lower-left to lower-center foreground.", "Right-side rooftop service area with pale concrete floor, blue cylindrical water tank, metal clothesline posts, hanging laundry, pipes, and vegetation along wall bases.", "Lower-right storage surface: stacked wooden pallets/boards with coiled rope/wire and a bicycle-like metal frame/object nearby.", "Surrounding red-brick and grey-concrete building façades with windows, doors, rooftop slabs, vents, pipes, and parapets.", "Narrow asphalt/concrete alleys between buildings, including a darker vertical lane near upper center-left and a lower street/drive area with a parked blue-grey car at bottom left.", "Multiple background rooftops with blue water tanks, patched concrete, tar stains, vents, corrugated metal covers, and small utility structures."], "occlusion_order": "No people are present. Architectural occlusion proceeds from foreground parapet and stair railings at the bottom edge, then the central courtyard walls and stairs, then the central rooftop room whose walls and open door block the roof floor behind it, then the right service-yard parapet/laundry/water tank, with surrounding midground buildings and background roofs layered behind. Parapet walls repeatedly hide lower alleys and roof floors; the open door partially occludes the doorway/interior.", "subjects": []}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): plate.png
B2 최종샷 nb2 · 20.5s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B.png
B1' 재생성 배경 v3.1 gpt-image-2 · 115.9s
prompt/refs (실제 호출 기록)
Create the photorealistic EMPTY background plate for one film shot:
the environment exactly as the environment reference shows it (same
architecture, materials, lighting), seen from the shot's camera.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

The required composition, extracted from a draft of this shot:
{"camera": {"angle": "High oblique establishing view looking downward into a dense residential rooftop block; camera faces roughly along a central alley/roof corridor that recedes from lower center toward upper center. The frame is not level with the ground plane: rooftops are seen from above, with strong vertical drop visibility into alleys.", "height": "Elevated well above street/alley level, approximately 2–4 stories up or drone/crane height, slightly higher than most visible flat roofs and looking across/over adjacent rooftops.", "lens_feel": "Wide panoramic lens feel with a very broad horizontal field of view; rectilinear or mildly wide-angle perspective. Depth compression is moderate: parallel rooftop walls and alley edges converge gently toward the upper center, while foreground roof edges appear large and close."}, "empty_background_requirements": "The plate must contain the entire empty urban rooftop environment exactly as shown: no people or moving figures anywhere. It must preserve the foreground red tiled roof strip along the bottom, the central foreground flat-roof building with parapet, weathered rooftop room, open grey door, rust-stained metal door, yellow-lit window, rooftop stains and cracks, surrounding concrete parapets, the narrow alleys on both sides, overhead power/utility wires crossing the lower and middle frame, utility poles, corrugated metal awnings, water tanks, tiled roofs, flat concrete roofs, rooftop sheds, small doors/windows, and the dense repeating residential buildings extending to the top of frame. Since no human subjects are visible, this image effectively already functions as an empty background plate; any future inserted people would need to be matched to the high downward perspective and occluded by parapets, wires, roof lips, awnings, and building edges where appropriate.", "horizon_and_depth": "No true sky horizon is visible; the frame is filled by rooftops and buildings to the top edge. Depth is constructed by repeated rectangular rooftops, parapet walls, alleys, and roof ridges receding toward the upper center. The central alley/void creates the main vanishing direction, with walls and roof edges converging subtly upward. Foreground depth plane occupies the bottom red tile roof and lower parapet/wire layer; midground is dominated by the central flat-roof building with rooftop room and adjacent alleys; background consists of tightly packed roofs and higher apartment blocks fading toward the top. The overall depth is layered and architectural rather than atmospheric, with cool blue-grey grading unifying the scene.", "major_surfaces": ["Foreground red clay tiled roof band along the bottom edge, with curved ridge tiles and dark weathering.", "Large central foreground flat concrete rooftop enclosed by a stained parapet, including mottled black/white roof surface, cracks, and roof-wall edges.", "Small rooftop room on the central building: white/grey stained walls, rusted metal double door, open grey hinged door, rectangular yellow-lit window, flat blackened roof slab, and attached drainpipes.", "Left foreground/midground flat concrete roofs with pale blue-grey waterproofing, raised parapets, rooftop access rooms, dark doors, windows, stains, and puddle-like discoloration.", "Right foreground/midground red tiled roof mass and adjacent pale flat roof with parapets, rooftop box structures, dark window openings, and corrugated awnings.", "Narrow alleys and roof-level service passages running vertically through the composition, especially the central lane receding from lower middle toward top center.", "Concrete boundary walls, parapets, and rooftop edges forming repeated horizontal and diagonal bands across the frame.", "Corrugated metal awnings and lean-to roofs in grey/white/rust tones attached to alley-facing walls.", "Overhead utility wires crossing diagonally and horizontally in the lower half and midframe, plus utility poles and small electrical boxes.", "Background dense residential block: repeating flat roofs, tiled gables, rooftop sheds, water tanks/cylinders, apartment facades, windows, balconies, and parapet tops."], "occlusion_order": "Nearest visual layer: lower-edge foreground roofs and parapet tops, including the bottom red tile roof and lower wall edges. Next: foreground utility wires crossing over building faces and alleys, visually overlaying parts of the central and lower buildings. Main midground layer: central flat-roof building and rooftop room, which occlude the alley floor behind them and parts of adjacent roofs. Left and right neighboring parapets and roof slabs overlap the side alleys and partially hide lower walls. Corrugated awnings protrude over alleys and occlude portions of doorways/walkways beneath. Farther rooftops and tiled ridges stack behind one another toward the upper frame, with nearer parapets cutting across and hiding the bases of buildings behind them. No people are present, so there are no subject-to-background occlusions to preserve beyond architectural/wire occlusions.", "subjects": []}

The plate must contain NO people, no figures, and no silhouettes —
just the environment, composed so the described people could be
inserted later.
PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
Absolutely no text, letters, circles, arrows or diagram marks.
참조 이미지(역할 라벨 포함): plate.png
B2' 최종샷 v3.1 nb2 · 19.8s
prompt/refs (실제 호출 기록)
Create the FINAL photorealistic cinematic film still of this shot.

SHOT CONTENT: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

PEOPLE COUNT CONTRACT: this shot contains NO people at all — the frame must be completely unpopulated, with no figures anywhere.
Any circled letters, numbers or legend text on the control diagram are SITE MARKERS only — they are never people and must not become people or objects in the output.
CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.

Stage the shot inside the attached environment background — keep its
architecture, materials and lighting exactly. Every person is a REAL
human being, photorealistic, matching their identity reference photo
(face, hair, build). Natural film lighting and grain consistent with
the environment.
Absolutely no text, letters, circles, arrows, diagram marks, and no
mannequin-like or statue-like appearance on any person.
참조 이미지(역할 라벨 포함): [ENVIRONMENT BACKGROUND reference — the empty environment: its space, architecture, materials and lighting are the ground truth. It contains NO people. Use it as the shot's background, matching its space and lighting exactly.] → bg_B_v31.png
S4_Shot1_v3 VLM 구도 분석 JSON
{
 "camera": {
  "angle": "Very high oblique overhead / bird’s-eye establishing angle, looking down into a dense cluster of flat-roofed urban buildings. The camera is pitched steeply downward, with only vertical wall faces and roof planes visible; no sky.",
  "height": "Rooftop-to-crane height, well above the main courtyard and surrounding roofs, roughly several stories up. It looks down into multiple roof levels and narrow alleys.",
  "lens_feel": "Wide panoramic lens feel with deep focus. Strong architectural perspective and many receding diagonals, but not heavily distorted; everything from foreground parapets to distant roofs remains sharp."
 },
 "empty_background_requirements": "The empty plate must be the same high, wide overhead view of the residential rooftop complex with no people added or removed. It must preserve all architecture and props: the central walled courtyard, concrete parapets, staircases with metal railings at lower left/center, the small rooftop room with open grey door and warm-lit interior, the adjacent flat roof, laundry area with blue water tank and hanging sheets at right, stacked wooden boards and coiled material at lower right, surrounding brick-and-concrete buildings, alleys, rooftop tanks, pipes, windows, weather stains, weeds, rocks, drains, and the parked car at lower left. Since there are no visible human subjects in the still, the empty background is effectively identical to the shown image.",
 "horizon_and_depth": "No visible horizon line; depth is constructed through stacked roof planes, parapet heights, alleys, and diagonal wall edges. The image has layered depth from the foreground lower parapets and street/courtyard edge, through the central courtyard and rooftop room, to midground and background apartment roofs. Recession runs mainly from lower frame toward upper frame, with strong diagonals leading upper left and upper right through alleys and roof walls.",
 "major_surfaces": [
  "Large weathered concrete rooftop/courtyard floor occupying the central lower-middle area, mottled with stains, dirt, weeds, and scattered stones.",
  "Low concrete parapet walls forming rectangular roof enclosures across the frame.",
  "Small central rooftop structure/room with flat concrete roof, off-white stained walls, vertical windows, and an open metal door revealing a warm beige interior floor and walls.",
  "Concrete stairs and landings with silver metal railings in the lower-left to lower-center foreground.",
  "Right-side rooftop service area with pale concrete floor, blue cylindrical water tank, metal clothesline posts, hanging laundry, pipes, and vegetation along wall bases.",
  "Lower-right storage surface: stacked wooden pallets/boards with coiled rope/wire and a bicycle-like metal frame/object nearby.",
  "Surrounding red-brick and grey-concrete building façades with windows, doors, rooftop slabs, vents, pipes, and parapets.",
  "Narrow asphalt/concrete alleys between buildings, including a darker vertical lane near upper center-left and a lower street/drive area with a parked blue-grey car at bottom left.",
  "Multiple background rooftops with blue water tanks, patched concrete, tar stains, vents, corrugated metal covers, and small utility structures."
 ],
 "occlusion_order": "No people are present. Architectural occlusion proceeds from foreground parapet and stair railings at the bottom edge, then the central courtyard walls and stairs, then the central rooftop room whose walls and open door block the roof floor behind it, then the right service-yard parapet/laundry/water tank, with surrounding midground buildings and background roofs layered behind. Parapet walls repeatedly hide lower alleys and roof floors; the open door partially occludes the doorway/interior.",
 "subjects": []
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

S10_Shot6 loc=L03 · framing=medium · 인물=없음

방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.

생성 순서 ① control/plate/임시
뿌리 마킹 (카메라 콘+인물 서클) [CONTROL]
①' camview 라인아트 (sketch-hop) gpt-image-2 · 113.3s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch of one real place, with
a green camera icon and view-cone marking ONE camera position and its
viewing direction (circled letters are site markers, never people).

Draw the clean LINE-ART sketch of the EYE-LEVEL view that THAT camera sees
from its marked position: thin dark ink lines on a plain white background,
no colour, no shading, no photo texture. The camera stands ON the ground of
its marked spot at human eye height (about 1.6 m) INSIDE the scene — NOT
above it. Show the structures, ground surfaces, openings and approaches the
site sketch places in front of that camera, in correct perspective at
real-world human scale, with the horizon at a natural eye-level height.
Do NOT draw any overhead or bird's-eye view. No people, no text, no
letters, no circles, no arrows — pure line drawing of the environment.
참조 이미지(역할 라벨 포함): root_marked.png
빈 배경 plate [ENV] gpt-image-2 · 108.1s
prompt/refs (실제 호출 기록)
The FIRST attached image is a LINE-ART sketch of one camera's eye-level
view of a real outdoor place — it is the COMPOSITION AND PERSPECTIVE
ground truth. The SECOND attached image is the top-down site sketch of
the same place — use it ONLY to understand materials, fixtures and
spatial relations; never copy its top-down viewpoint or its markers.

Render the PHOTOREALISTIC empty background plate of exactly the view the
line-art sketch shows: same framing, same perspective, same structures,
at real-world human scale. This is an EMPTY plate: no people, no text,
no letters, no circles, no sketch lines — pure photographic realism.

WHAT THIS PLACE LOOKS LIKE (production data):
- 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)

Site orientation notes:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

CAMERA: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
FRAMING: medium
LIGHTING: The reflected action is almost monochrome blue-black, broken by a weak amber practical smear and restrained crimson-brown shadow at the shoulder line.
PERSON: {"angle": "three_quarter_left", "body_pose": "hunched over shoulder", "character": "인영", "gaze_direction_kind": "looks_at_character", "gaze_target_id": "C20", "subject_state": "alive"}
PERSON: {"angle": "profile_left", "body_pose": "buckling under lunge", "character": "사람", "gaze_direction_kind": "off_screen", "gaze_target_id": null, "subject_state": "severely_injured"}
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
참조 이미지(역할 라벨 포함): sketch.png root_marked.png
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

4.4 실외 root_C 체인 재검증 (fp 앵커 뿌리 → 마킹 → sketch-hop → plate)

S4_Shot1 loc=L03 · framing=wide · 인물=없음

인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.

생성 순서 ① control/plate/임시
뿌리 마킹 (카메라 콘+인물 서클) [CONTROL] gpt-image-2 · 133.0s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch with circled capital letters marking site elements (and possibly a legend panel on the right). Keep the sketch EXACTLY as it is — same geometry, same circled letters, same legend, do not redraw or restyle anything.
ADD exactly these annotations for ONE camera setup:
- ONE green camera icon with a green triangular view-CONE showing where the camera stands and what it looks at, following this staging description:
An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
- This shot has NO people — add no lettered person circles.
Add NOTHING else — no new structures, no new text other than the new capital letters in their small circles.
참조 이미지(역할 라벨 포함): root_C.png
①' camview 라인아트 (sketch-hop) gpt-image-2 · 106.0s
prompt/refs (실제 호출 기록)
The attached image is a TOP-DOWN aerial site sketch of one real place, with
a green camera icon and view-cone marking ONE camera position and its
viewing direction (circled letters are site markers, never people).

Draw the clean LINE-ART sketch of the EYE-LEVEL view that THAT camera sees
from its marked position: thin dark ink lines on a plain white background,
no colour, no shading, no photo texture. The camera stands ON the ground of
its marked spot at human eye height (about 1.6 m) INSIDE the scene — NOT
above it. Show the structures, ground surfaces, openings and approaches the
site sketch places in front of that camera, in correct perspective at
real-world human scale, with the horizon at a natural eye-level height.
Do NOT draw any overhead or bird's-eye view. No people, no text, no
letters, no circles, no arrows — pure line drawing of the environment.
참조 이미지(역할 라벨 포함): root_marked.png
빈 배경 plate [ENV] gpt-image-2 · 123.0s
prompt/refs (실제 호출 기록)
The FIRST attached image is a LINE-ART sketch of one camera's eye-level
view of a real outdoor place — it is the COMPOSITION AND PERSPECTIVE
ground truth. The SECOND attached image is the top-down site sketch of
the same place — use it ONLY to understand materials, fixtures and
spatial relations; never copy its top-down viewpoint or its markers.

Render the PHOTOREALISTIC empty background plate of exactly the view the
line-art sketch shows: same framing, same perspective, same structures,
at real-world human scale. This is an EMPTY plate: no people, no text,
no letters, no circles, no sketch lines — pure photographic realism.

WHAT THIS PLACE LOOKS LIKE (production data):
- 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)

Site orientation notes:
Use a direct overhead plan. Keep the rooftop room as the central roof mass, with the iron-door side facing the terrace landing, exterior stair, and alley approach. Show only the roof outline and openings for the interior: no interior floor plan, furniture, blood, wall marks, bed, table, TV, sink, mirror, or bathroom layout. Interior shots are anchored only by the front door, exterior windows, and the abstract inner doorway markers.

CAMERA: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
FRAMING: wide
LIGHTING: Daylight is overcast and desaturated, with blue-gray concrete shadows and faint sickly amber window stains breaking the neighborhood’s cold isolation.
SPATIAL CONSTRAINTS: [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}]

CAMERA HEIGHT CONTRACT: the camera stands ON the ground INSIDE the scene at human eye height (about 1.6 m). Sky or horizon must be visible where the view allows it. Do NOT render an overhead, elevated, aerial or drone view — this is a ground-level cinematic shot.
참조 이미지(역할 라벨 포함): sketch.png root_marked.png
S4_Shot1 VLM 구도 분석 JSON
{
 "camera": {
  "angle": "Very high oblique aerial/rooftop view looking steeply downward, not perfectly vertical; the camera is above and slightly in front of the main roof court, producing strong plan-view geometry with visible wall faces.",
  "height": "Several stories above the subjects, approximately 2–4 building levels above the main rooftop; subjects appear small and compressed into an architectural grid.",
  "lens_feel": "Wide panoramic/stitched feel with mild perspective convergence and large horizontal field of view; moderate-wide lens impression, deep focus across foreground roof, central courtyard, and distant neighboring rooftops."
 },
 "empty_background_requirements": "An empty plate must preserve the entire rooftop complex and surrounding city fabric with no people: the central sunken/boxed concrete rooftop court with stained walls, two open metal doors on the upper wall, the warm-lit left-side window/door opening, the front parapet with horizontal window, the open gate/door near the lower-left corner of the main court, staircases and railings at lower left, the left upper rooftop platform, the right rooftop annex with clotheslines, hanging laundry, blue cylindrical water tank, stacked wooden debris/cart, parapet walls, cracked concrete, leaf piles, drainage grates, neighboring flat roofs, red-tile roof, green roofs, utility cables, windows, alley/drive surfaces, parked vehicles at far left, tree foliage at lower right, and the blue corrugated roof in the lower foreground. The plate must include all contact surfaces where people stand: central court floor, door thresholds, parapet-edge walkway, stair treads/landings, right annex roof, far-right rooftop ledge, and bottom exterior walkway. Door positions, laundry, water tank, debris piles, stains, cracks, leaf scatter, and warm interior glows should remain unchanged so subjects can be composited back into the same occlusion layers.",
 "horizon_and_depth": "No visible sky or true horizon; the frame is dominated by receding horizontal roof planes. Depth is established by stacked parapet walls and rooftops: foreground lower roofs and exterior walkway at bottom, main rooftop court in the center, side annexes left and right, then background apartment roofs and facades at the top. The high angle flattens vertical depth but wall faces, stair runs, open doors, and roof edges create clear stepped depth planes. The central court is the primary mid-depth plane, enclosed by higher parapets and adjacent roof decks.",
 "major_surfaces": [
  "Large central concrete rooftop court/floor, cracked and stained, occupying the middle of frame.",
  "Tall rectangular concrete rooftop room/parapet structure around the central court, with stained vertical walls and two open metal doors on the upper wall.",
  "Front/lower parapet wall of the central court with a narrow horizontal warm-lit window.",
  "Left upper rooftop terrace/platform separated by low concrete walls, with leaf debris and weathered concrete.",
  "Lower-left staircase system with concrete steps, landings, rust-colored metal railings, and surrounding parapet walls.",
  "Right-side rooftop annex/deck with cracked dark concrete, clothesline poles, hanging laundry, blue cylindrical water tank, and pile/cart of wood debris.",
  "Far-right higher/outer rooftop walkway and parapet edge where a lone figure stands.",
  "Surrounding neighboring buildings: flat gray roofs, green roof panels, red tiled roof, brick and concrete facades, windows, balconies, overhead utility wires.",
  "Bottom foreground exterior walkway/roof lane and blue corrugated roof, plus tree foliage at lower right.",
  "Left edge alley/drive area with parked vehicles and building walls."
 ],
 "occlusion_order": "Nearest/lowest foreground elements are the bottom exterior roof lane, blue corrugated roof, lower parapets, tree branches, and stair railings, which would occlude lower bodies if overlapping. The main central court subjects sit behind the front parapet lip but in front of the rear wall and open doors. Doorway subjects are partially framed/occluded by door jambs and metal door panels. The man at the left window is adjacent to/partly occluded by the central building side wall and window frame. The right-annex subjects are behind the central court’s right parapet wall but in front of the laundry, tank, and debris unless overlapping. The upper-left pair are behind the nearer left parapet edge and in front of background apartment roofs. The far-right rooftop figure is on a background/right roof plane, visually behind the right annex parapets and utility cables. Background buildings, roofs, cables, and distant facades are the rearmost layers.",
 "subjects": [
  {
   "depth_plane": "Upper-left adjacent rooftop terrace, behind the central court and above/left of it.",
   "label": "Upper-left pair, man A",
   "pose": "Standing upright in dark jacket and jeans, body angled slightly toward the other man as if conversing; arms close to body.",
   "screen_zone": "Upper left-of-center, on narrow roof strip just above the left side of the central structure.",
   "support_contact": "Both feet planted on the weathered concrete roof surface near the parapet edge."
  },
  {
   "depth_plane": "Upper-left adjacent rooftop terrace, same plane as man A.",
   "label": "Upper-left pair, man B",
   "pose": "Standing upright in dark jacket, turned toward man A, slight contrapposto/conversation stance.",
   "screen_zone": "Upper left-of-center, just to the right of man A near the same parapet line.",
   "support_contact": "Feet on the concrete rooftop strip, close to the central roof wall edge."
  },
  {
   "depth_plane": "Central rooftop room threshold, rear/upper wall of central court.",
   "label": "Left rear doorway figure",
   "pose": "Standing partly inside/open doorway, body facing outward into the courtyard, dark clothing with light shirt visible; relaxed vertical posture.",
   "screen_zone": "Upper middle-left of the central court, framed by the left open metal door.",
   "support_contact": "Feet at the doorway threshold/interior floor level, contacting the sill/door landing."
  },
  {
   "depth_plane": "Central rooftop room threshold, rear/upper wall of central court.",
   "label": "Right rear doorway figure",
   "pose": "Standing in the right doorway, facing outward; dark coat and trousers, arms low, framed by the open door panel.",
   "screen_zone": "Upper middle-right of central court, inside the right open doorway.",
   "support_contact": "Feet planted on the doorway threshold/interior floor, just behind the court floor plane."
  },
  {
   "depth_plane": "Central court left side, beside the building wall/window; mid-ground.",
   "label": "Left wall/window man",
   "pose": "Standing side-on to the courtyard, facing the warm-lit window/opening, hands raised near chest as if holding phone or manipulating the frame.",
   "screen_zone": "Left-middle edge of the central court, adjacent to the vertical wall.",
   "support_contact": "Feet on central concrete court floor immediately beside the wall/window base."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 1, left of cluster",
   "pose": "Standing facing inward toward the group, dark puffer jacket, head slightly down toward the others/phone.",
   "screen_zone": "Lower middle-right of the central court cluster.",
   "support_contact": "Both feet on central cracked concrete floor."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 2, phone-holder/inner left",
   "pose": "Standing close to the group, looking down with hands together as if holding or showing an object/phone.",
   "screen_zone": "Center-right of the central court, slightly above the left member of the group.",
   "support_contact": "Feet planted on central court concrete."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 3, tall upper-right of cluster",
   "pose": "Standing upright in dark jacket, facing inward/down toward group; slightly separated behind the others.",
   "screen_zone": "Right-center of the central court cluster.",
   "support_contact": "Feet on central concrete floor."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 4, back-to-camera foreground of cluster",
   "pose": "Standing with back to camera in dark padded jacket, facing the rest of the group; legs apart slightly.",
   "screen_zone": "Lower center-right of central court cluster.",
   "support_contact": "Feet on central concrete floor, closest member of the central group to the lower edge."
  },
  {
   "depth_plane": "Central court floor, primary mid-ground group.",
   "label": "Central group man 5, patterned-coat/right member",
   "pose": "Standing facing the back-to-camera man and the group, slightly turned left; patterned/dark coat visible.",
   "screen_zone": "Lower right side of the central group.",
   "support_contact": "Feet on central concrete floor."
  },
  {
   "depth_plane": "Right side of central court near parapet/wall, slightly separated from main group.",
   "label": "Right wall phone man",
   "pose": "Standing alone, side-on, head down toward hands as if using a phone; light gray/brown coat.",
   "screen_zone": "Right-middle of central court, near the right parapet and warm wall light.",
   "support_contact": "Feet on central court floor close to the right wall/parapet edge."
  },
  {
   "depth_plane": "Right rooftop annex/deck beyond the central court wall.",
   "label": "Right annex lower figure",
   "pose": "Standing near laundry/debris area, dark jacket and jeans, head down; body angled diagonally toward lower right.",
   "screen_zone": "Right side of frame, lower half of the right annex, next to hanging laundry and debris pile.",
   "support_contact": "Feet on cracked dark concrete roof surface of the right annex."
  },
  {
   "depth_plane": "Far-right outer rooftop/walkway, background-right plane.",
   "label": "Far-right rooftop figure",
   "pose": "Standing/walking slowly along roof edge in dark coat, body facing left/downward, one leg advanced.",
   "screen_zone": "Extreme upper-right quadrant near the right border.",
   "support_contact": "Feet on the far-right flat roof/walkway surface near a parapet edge."
  },
  {
   "depth_plane": "Lower-left staircase, foreground-midground transition.",
   "label": "Staircase descending man",
   "pose": "Standing or descending on the stair run, dark coat, body facing down the steps toward camera/lower frame.",
   "screen_zone": "Lower left-of-center on the stairwell between railings.",
   "support_contact": "Feet on separate stair treads, partially enclosed by metal railings."
  },
  {
   "depth_plane": "Bottom exterior walkway/roof lane, foreground.",
   "label": "Bottom-left standing man",
   "pose": "Standing still in long coat, mostly back/side to camera, looking upward/right toward the rooftop complex.",
   "screen_zone": "Lower left quadrant, just below the staircase base and inside the foreground roof lane.",
   "support_contact": "Feet planted on the lower concrete walkway/roof surface."
  }
 ]
}
production 비교
비교 production 최종 스틸 #0
비교 production 최종 스틸 #1

부록 — LLM 단계 프롬프트 (실제 사용 원문)

이미지 셀의 prompt/refs 는 전부 호출 시점 runlog 기록. LLM(텍스트) 단계의 system 프롬프트는 아래 코드 상수가 그대로 사용되었고, user 프롬프트는 §0-§1 의 데이터(멤버/샷 원문 전체+계획 JSON)를 자르지 않고 조립한 것(조립 규칙 포함). 이후 호출부터는 runlog 에 원문도 기록.
R1 요소 선정 system prompt (s1_root.R1_SYSTEM)
You are the master planner for a group of connected filming locations
(one real-world place made of indoor and outdoor parts). You are given the place's
member descriptions and the FULL content of every shot that happens there.

Your job: design ONE comprehensive TOP-DOWN aerial site sketch that lets every later
image of any of these shots stay spatially consistent. Select the elements that must
appear on that single sketch.

Hard rules:
- The sketch shows the place from directly above: structures (roof outline), outdoor
  areas, approach paths, and every OPENING (door, gate, window, stair/level access).
- NEVER expose interior floor plans or interior furniture. Indoor action may only be
  represented by its openings (the window/door through which it is visible or
  reached) and by elements visible from outside.
- Every shot must be covered: for each shot, the elements a viewer would need to
  locate that shot's action on the sketch (its opening, area, or approach).
- Keep it compact: at most 10 elements, each with a single capital letter ID
  (A, B, C, ...) and a SHORT English name (1-3 words) for the legend.
- Placement phrases must be relative and physical (e.g. "on the north edge of the
  roof", "at the bottom of the exterior stair"), grounded in the given data only.
- Do not invent features that contradict the member descriptions. Do not use any
  proper names in element names; use generic physical terms.
I0 실내 계획 system prompt (s2_indoor.I0_SYSTEM)
You are the background production planner for the INDOOR shots of one
real-world place. You are given: the place's aerial-sketch element plan (the spatial
root contract), the indoor floor plan identifiers available, and the FULL content of
every indoor shot.

Plan the background generation like a set photographer:
1. For each shot, state what background it needs (which part of the indoor space,
   from roughly what direction).
2. Merge those needs into AT MOST TWO "top-layer" master backgrounds — wide, clean,
   empty-room views that together cover all the shots. Prefer ONE if the space is
   small enough to read in a single wide view.
3. Give the generation order. If there are two, the second must chain on the first
   (same dwelling, same materials).
4. For each top-layer, judge whether attaching the floor plan image as a reference
   would help (geometry anchoring) or hurt (style leakage), and say why.
Ground every statement in the given data only; do not invent rooms or furniture.
Use generic physical terms, no proper names.
VLM 구도 분석 지시문 (forest_chain.vlm_composition)
Analyse this film still's composition precisely. Describe the camera, horizon/depth, major visible surfaces, each subject's screen position / depth / pose / support contact, occlusion order, and what an EMPTY background plate (no people) must contain so the people could be re-inserted with the same composition.
root readback 지시문 (s1_root.readback)
This is a top-down site sketch with circled capital letters and a legend panel. List every circled capital letter you can find, list the legend entries as written, and say whether any interior room layout is exposed.
llm 호출 기록 — forest_root_plan_v2 (gpt)
SYSTEM:
You are the master planner for a group of connected filming locations
(one real-world place: a building and its grounds, with indoor and outdoor parts).
You are given the place's member descriptions and the FULL content of every shot.

Design ONE comprehensive TOP-DOWN site plan of the WHOLE property — not just its
top level. The plan must show, together in one drawing:
- the full BUILDING footprint (the multi-storey building the upper dwelling sits on),
- the GROUND level around it: the yard/alley, the building's street-side entrance
  and the approach path where characters arrive,
- the exterior STAIR route connecting ground to the top level,
- the TOP level: the upper dwelling's roof outline, its terrace and fixtures,
- a modest margin of the immediate surroundings.

Select the elements to mark on this one plan. Hard rules:
- NEVER expose interior floor plans or interior furniture; enclosed spaces show
  only their outline and boundary openings (doors, windows, gates).
- Cover every shot: for each shot, the elements needed to locate its action.
- At most 12 elements, each with a single capital letter ID and a SHORT English
  name (1-3 words). Placement phrases must be relative and physical, grounded in
  the given data only. Generic physical terms, no proper names.

USER:
PLACE MEMBERS:
- (outdoor, L03) 인천 변두리 낡은 빌라 옥탑방 옥상·현관 앞 외부: 낡은 다세대 빌라 꼭대기에 위치한 야외 공간. 물탱크, 흔들리는 빨랫줄, 평상 위 약초 건조 흔적, 낡은 철문 현관이 있다. (특징: 낡은 시멘트 바닥; 물탱크; 바람에 날리는 빨랫줄; 평상과 널려 있는 말린 약초(석창포); 전단지가 끼워진 철문 현관)
- (indoor, L04) 옥탑방 내부: 작은 창문으로 빛이 들어오는 낡은 주거 공간. 싱크대, 식탁, TV가 있는 거실과 침대, 커튼, 거울 등이 있는 방/욕실로 구성된다. 약초 끓이는 냄비 등 생활 소품이 있으며, 간헐적으로 벽면에 붉은 원 형태의 환영과 핏자국이 생겨난다. (특징: 작은 창문의 햇살; 싱크대와 약초(석창포); 가스레인지 위 끓는 냄비와 수증기; 거실 TV와 스탠드; 침대, 커튼, 거울; 벽과 거울 표면에 나타나는 붉은 원 환영; 바닥과 벽의 핏자국 (특정 시점); 어지럽혀진 가재도구 (특정 시점))
- (outdoor, L10) 옥탑방 외곽 골목·시멘트 계단: 다세대 빌라 마당의 후미진 구석과 옥탑방으로 올라가는 가파르고 낡은 시멘트 계단. (특징: 다세대 빌라 입구 마당; 후미진 구석 공간; 낡고 가파른 시멘트 계단)

ALL SHOTS AT THIS PLACE:

[S10_Shot5] (outdoor; loc=L03; scene_heading=S#10. 옥탑방 / N)
description: 철문이 미세하게 열린 틈 사이로 어두운 내부가 보이는 구도.
framing_scale: insert
camera_direction: At the end of the flow’s dolly-in, the lens freezes just outside the iron door at handle height, only inches from the seam, staring directly into the thin opening. The dark crack sits in the center like a vertical wound, with rough iron surfaces on both sides occupying the foreground while the interior beyond remains unreadable and almost lightless.
key_bg_elements: [{"camera_use": "Primary focal aperture; turns the entry into a threatening slit rather than a normal doorway.", "directionality_class": "directional_3d", "element": "iron front door", "orientation": "The two heavy door edges face camera at close range, separated by a narrow central crack leading into darkness.", "state": "slightly open, scratched, cold metal"}, {"camera_use": "Hides what is inside and makes the gap feel predatory.", "directionality_class": "non_directional", "element": "dark interior beyond the crack", "orientation": "", "state": "unlit, opaque, silent"}, {"camera_use": "Adds tactile evidence of forced entry near the seam.", "directionality_class": "content_surface", "element": "creased advertisement flyer edge", "orientation": "Only the printed edge of the paper face is visible near the door seam, with partial color blocks and unreadable text.", "state": "bent, partly displaced, dirty"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "foreground", "gesture_action": "none", "gesture_target_label": "", "label": "narrow iron door seam", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}], "reason": "required_background_position"}

[S10_Shot6] (outdoor; loc=L03; scene_heading=S#10. 옥탑방 / N)
description: 방 안 창문에 비친 그림자, 굽은 형태의 인영이 다른 사람 형상 위에 포개져 멈춘 찰나의 실루엣.
framing_scale: medium
camera_direction: Inside the room, the camera holds static near the side wall at shoulder height, angled so only the window glass carries the action as a reflection and the direct attack is never seen. The reflected silhouettes sit within the window frame: a bent 인영 in the upper-middle area lowers its head toward the shoulder of 사람, whose body buckles beneath it in a distorted, wavering mid-action shape.
key_bg_elements: [{"camera_use": "Serves as the only visible surface for the attack, keeping violence indirect and distorted.", "directionality_class": "reflective_surface", "element": "room window glass", "orientation": "The glass reflects the bent 인영 and 사람 as warped dark silhouettes, with faint interior light streaks trembling across them.", "state": "closed, grimy, reflective in darkness"}, {"camera_use": "Frames the reflection and prevents the viewer from seeing the real bodies directly.", "directionality_class": "directional_3d", "element": "window frame", "orientation": "The frame’s inner edges face camera and box the reflected action into a rigid rectangle.", "state": "old, chipped, motionless"}, {"camera_use": "Adds low, diseased color to the reflected silhouettes.", "directionality_class": "directional_3d", "element": "dim interior practical light", "orientation": "The lamp’s shaded side is off-frame but its amber spill grazes the wall and window reflection.", "state": "on, weak, sickly amber"}, {"camera_use": "Keeps the room claustrophobic around the window surface.", "directionality_class": "non_directional", "element": "dark side wall", "orientation": "", "state": "rough, stained, blue-gray shadowed"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "window reflection containing silhouettes", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}], "reason": "required_background_position"}

[S11_Shot3] (outdoor; loc=L10; scene_heading=S#11. 옥탑 방 밖 / N)
description: 계단 중간에 서서 심하게 코를 찡그린 수리영의 얼굴 클로즈업.
characters: 수리영
framing_scale: close
camera_direction: Midway up the narrow concrete staircase, the camera holds static very close to 수리영 from the front-left at face height, tightening into an intense close-up that leaves only a sliver of stair texture behind her. Her nose wrinkles hard at the sudden smell, eyes lifting toward the unseen rooftop landing while her halted climb compresses her shoulders into the frame.
key_bg_elements: [{"camera_use": "Minimal background texture that preserves the stair location without diluting the reaction.", "directionality_class": "directional_3d", "element": "narrow concrete staircase", "orientation": "Only the side edge and riser texture angle behind her cheek, indicating the upward path to the rooftop.", "state": "dark, damp, rough"}, {"camera_use": "Creates a suffocating side boundary close to her face.", "directionality_class": "non_directional", "element": "stairwell wall", "orientation": "", "state": "stained, cold, blue-gray"}, {"camera_use": "Suggests the unseen source direction through faint light above.", "directionality_class": "non_directional", "element": "rooftop darkness above the stairs", "orientation": "", "state": "unseen, heavy, foul implied"}]

[S11_Shot4] (outdoor; loc=L10; scene_heading=S#11. 옥탑 방 밖 / N)
description: 옥상 위, 어둠 속에 반쯤 열려 멈춰 있는 옥탑방 현관 철문의 정적 구도.
framing_scale: wide
camera_direction: After the hard eyeline cut, the camera adopts 수리영’s direct viewpoint from the rooftop landing, several meters from the entrance and at human eye level, facing the iron front door squarely. The half-open door is held in rigid symmetry at the center of the frame, surrounded by still rooftop darkness, with no figure entering to relieve the threat.
key_bg_elements: [{"camera_use": "Central reveal and source of unease, held motionless after her smell reaction.", "directionality_class": "directional_3d", "element": "rooftop room iron front door", "orientation": "The door faces camera squarely but hangs half-open, exposing a narrow black interior gap along one side.", "state": "half-open, frozen, scratched"}, {"camera_use": "Frames the doorway in isolated negative space.", "directionality_class": "non_directional", "element": "rooftop landing darkness", "orientation": "", "state": "still, damp, blue-black"}, {"camera_use": "Adds rough domestic rooftop texture without drawing attention from the door.", "directionality_class": "directional_3d", "element": "low rooftop wall", "orientation": "Its top edge runs horizontally across the lower background, barely lit against the night.", "state": "wet-stained, concrete, motionless"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "background", "gesture_action": "none", "gesture_target_label": "", "label": "half-open rooftop iron door", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}], "reason": "required_background_position"}

[S12_Shot15] (indoor; loc=L04; scene_heading=S#12. 옥탑방 안 / N)
description: 침대 위 어두운 벽면에 피가 번지듯 선명한 붉은색 원형 표식이 그려진 상태의 정지 구도.
framing_scale: medium
camera_direction: From low bedside height near the mattress edge, the camera completes its upward tilt and locks off on the dark wall above the bed, where a completed red circular mark sits in the upper middle of frame. The bed edge remains only as a thin lower strip for scale, while the wall becomes an oppressive flat plane; this is aligned with 수리영’s panicked perception, the image subtly treated as an occult hallucination rather than stable reality.
key_bg_elements: [{"camera_use": "Primary occult surface holding the completed mark.", "directionality_class": "content_surface", "element": "dark wall above the bed", "orientation": "The camera-facing wall face is visible, carrying a vivid red circular mark at its center.", "state": "dark, stained-looking, marked"}, {"camera_use": "Lower frame scale reference beneath the wall.", "directionality_class": "directional_3d", "element": "bed edge", "orientation": "The side edge of the mattress faces the camera from below, cropped into a narrow horizontal band.", "state": "dim, still, partly obscured"}, {"camera_use": "Symbolic focal mark on the wall.", "directionality_class": "content_surface", "element": "red circular mark", "orientation": "The painted-looking face of the circle is fully visible to the camera, as if freshly drawn into the wall surface.", "state": "bright red, wet-looking, completed"}]

[S12_Shot4] (indoor; loc=L04; scene_heading=S#12. 옥탑방 안 / N)
description: 열린 방문 틈으로 보이는 방바닥에 검붉은 핏자국이 흥건하게 고여 있는 정지 구도.
framing_scale: close
camera_direction: From the low waist-height position outside the bedroom doorway, the camera holds completely still about three feet back, peering through the opened door gap toward the dark red blood pooled on the floor just beyond the threshold. The door edges form a narrow vertical frame on both sides, with the blood occupying the lower middle of the image and the dim bedroom receding into blue-gray darkness behind it; this is a neutral observer’s direct view, not a character POV.
key_bg_elements: [{"camera_use": "Foreground framing device that restricts the view into the room.", "directionality_class": "directional_3d", "element": "opened bedroom door", "orientation": "The inner edge of the door faces the camera at an oblique angle, creating a narrow gap into the room.", "state": "open, still, shadowed"}, {"camera_use": "Primary visual focus on the floor just inside the doorway.", "directionality_class": "non_directional", "element": "dark red blood pool", "orientation": "", "state": "wet, thick, spread across the floor"}, {"camera_use": "Texture under the blood and scale reference for the room.", "directionality_class": "non_directional", "element": "bedroom floor", "orientation": "", "state": "dirty, damp-looking, partially covered by blood"}]

[S12_Shot8] (indoor; loc=L04; scene_heading=S#12. 옥탑방 안 / N)
description: 두 눈을 크게 뜨고 입을 벌린 채 굳어버린 수리영의 창백한 얼굴 클로즈업.
characters: 수리영
framing_scale: close
camera_direction: At eye level directly in front of 수리영, the handheld camera compresses tighter than the stage distance until her pale face nearly fills the frame, backing away only a fraction as her shock freezes mid-recoil. The background is almost lost in darkness, with only a faint suggestion of the room’s black edges behind her; the view remains a direct observer angle, but the proximity feels invasive and breathless.
key_bg_elements: [{"camera_use": "Nearly swallowed background plane behind her face.", "directionality_class": "non_directional", "element": "dark bedroom recess", "orientation": "", "state": "unlit, indistinct"}, {"camera_use": "Soft edge shadow that isolates her head from the room.", "directionality_class": "directional_3d", "element": "bedroom doorway edge", "orientation": "A narrow side edge catches minimal spill light behind her shoulder.", "state": "partially visible, shadowed"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "foreground", "gesture_action": "none", "gesture_target_label": "", "label": "수리영 terrified face", "screen_zone": "middle_center", "target_id": "C01", "target_kind": "character"}], "reason": "primary_subject_isolation"}

[S13_Shot3] (outdoor; loc=L03; scene_heading=S#13. 옥탑방 외곽 / N)
description: 차에서 내린 혜수가 초점 없는 눈으로 멍하게 서 있는 수리영을 향해 시선을 고정한 찰나의 상체.
characters: 혜수, 수리영
framing_scale: medium
camera_direction: Beside the police car at chest height, the tracking move slows into a held upper-body frame on 혜수 as she has just stepped out, her body paused between the car and the alley. 수리영 appears farther down the alley in soft background focus, small and blank beneath flashing siren wash, while 혜수 occupies the left foreground in a tense three-quarter view; this is a direct observer view moving parallel with her discovery.
key_bg_elements: [{"camera_use": "Foreground context and flashing light source beside 혜수.", "directionality_class": "directional_3d", "element": "police car", "orientation": "The side of the car and open door angle toward the camera, framing 혜수’s exit.", "state": "parked, door open, siren lights active"}, {"camera_use": "Depth corridor between 혜수 and 수리영.", "directionality_class": "directional_3d", "element": "narrow alley", "orientation": "The alley recedes diagonally from the police car toward 수리영 in the background.", "state": "wet, dark, foggy"}, {"camera_use": "Intermittent color wash across faces and walls.", "directionality_class": "non_directional", "element": "siren light spill", "orientation": "", "state": "flashing red-blue across damp surfaces"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "foreground", "gesture_action": "looks_toward", "gesture_target_label": "수리영 down the alley", "label": "혜수 by police car", "screen_zone": "middle_left", "target_id": "C02", "target_kind": "character"}, {"depth_plane": "background", "gesture_action": "none", "gesture_target_label": "", "label": "수리영 in alley", "screen_zone": "middle_right", "target_id": "C01", "target_kind": "character"}], "reason": "shared_space_relation"}

[S13_Shot5] (outdoor; loc=L03; scene_heading=S#13. 옥탑방 외곽 / N)
description: 수리영이 고개를 들어 혜수의 얼굴을 올려다보는 정적 구도.
characters: 수리영, 혜수
framing_scale: close
camera_direction: The camera sits low near 수리영’s eye level, about one meter away, tightened into a still close composition as she lifts her face toward 혜수 just above the frame. 수리영 holds the lower center of the image, her upward eyeline creating the unseen presence of 혜수, while the wet alley background blurs into dark blue-gray; this is a direct observer angle from the space between them.
key_bg_elements: [{"camera_use": "Soft, dark background texture behind 수리영’s head.", "directionality_class": "non_directional", "element": "wet alley wall", "orientation": "", "state": "damp, shadowed, out of focus"}, {"camera_use": "Atmospheric layer around her face.", "directionality_class": "non_directional", "element": "night fog", "orientation": "", "state": "thin, drifting, blue-gray"}, {"camera_use": "Off-screen motivated color pulse on her skin.", "directionality_class": "non_directional", "element": "police siren spill", "orientation": "", "state": "intermittent, faint"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "foreground", "gesture_action": "looks_toward", "gesture_target_label": "혜수 just above frame", "label": "수리영 close low frame", "screen_zone": "middle_center", "target_id": "C01", "target_kind": "character"}], "reason": "primary_subject_isolation"}

[S14_Shot4] (indoor; loc=L04; scene_heading=S#14. 옥탑방 안 / N)
description: 핏자국 하나 없이 깨끗하게 정돈된 수리영의 방 내부 정지 구도.
framing_scale: wide
camera_direction: Just inside 수리영’s bedroom doorway at eye level, the camera holds a wide, unmoving view inward toward the bed, bare wall, curtain, and spotless floor. The room is framed as evidence: the clean floor stretches across the lower half, the curtain line sits to one side where the body should have been, and the wall above the bed remains blank; this is a direct neutral observation of absence.
key_bg_elements: [{"camera_use": "Primary proof of erased violence across the lower frame.", "directionality_class": "non_directional", "element": "spotless bedroom floor", "orientation": "", "state": "clean, dry, no blood marks"}, {"camera_use": "Central room anchor and comparison point for the missing wall mark.", "directionality_class": "directional_3d", "element": "bed", "orientation": "The side and top plane of the bed face the camera from mid-frame.", "state": "neatly made, undisturbed"}, {"camera_use": "Surface where the red circle should have been absent.", "directionality_class": "content_surface", "element": "wall above the bed", "orientation": "The camera-facing wall face is visible and completely bare, carrying no red circular mark.", "state": "clean, dark, unmarked"}, {"camera_use": "Empty area where the hidden body had been discovered earlier.", "directionality_class": "directional_3d", "element": "curtain line", "orientation": "The front folds face the camera from the side of the room, concealing only darkness and empty space behind.", "state": "hanging still, clean, no body visible"}]

[S14_Shot6] (indoor; loc=L04; scene_heading=S#14. 옥탑방 안 / N)
description: 수리영이 핏기가 가신 창백한 얼굴로 멍하니 빈 커튼 쪽을 응시하는 정면.
characters: 수리영
framing_scale: close
camera_direction: Inside the bedroom near the bed and curtain side, the dolly-in ends in a frontal upper-body emphasis on 수리영, close enough that her pale face and rigid shoulders take most of the frame. She looks past the camera toward the empty curtain area, which is kept implied rather than shown, turning the direct observer view into a psychological confrontation with the missing evidence.
key_bg_elements: [{"camera_use": "Blurred side texture suggesting where the corpse should have been.", "directionality_class": "directional_3d", "element": "curtain edge", "orientation": "Only a soft side fold is visible near the frame edge, with the empty area kept off-camera.", "state": "still, clean, partially out of focus"}, {"camera_use": "Low background shape behind her shoulder.", "directionality_class": "directional_3d", "element": "bed corner", "orientation": "The near corner angles away behind 수리영, cropped and subdued.", "state": "neat, undisturbed"}, {"camera_use": "Absence marker behind her expression.", "directionality_class": "content_surface", "element": "blank wall", "orientation": "The visible wall face behind her is bare and carries no red mark.", "state": "unmarked, dim"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "foreground", "gesture_action": "looks_toward", "gesture_target_label": "empty curtain area behind camera", "label": "수리영 frontal close frame", "screen_zone": "middle_center", "target_id": "C01", "target_kind": "character"}], "reason": "primary_subject_isolation"}

[S14_Shot8] (indoor; loc=L04; scene_heading=S#14. 옥탑방 안 / N)
description: 식탁 앞에 선 수리영이 빈 식탁을 손가락으로 가리킨 채 멈춘 측면 상체.
characters: 수리영
framing_scale: medium
camera_direction: At chest height beside the dining table, the camera settles from the track into a brief still side composition perpendicular to 수리영’s body line. Her profile holds the left half of frame while her pointing hand cuts toward the bare tabletop on the right, keeping both the gesture and the missing teacups in one direct observational image.
key_bg_elements: [{"camera_use": "Gesture target proving the vanished cups.", "directionality_class": "directional_3d", "element": "bare dining table", "orientation": "The clean top plane faces the camera at a shallow angle, with no cups where her finger indicates.", "state": "clean, empty, dry"}, {"camera_use": "Dim living-room depth behind the table.", "directionality_class": "directional_3d", "element": "living room wall and doorway", "orientation": "The wall and doorway recede behind 수리영 in side view.", "state": "shadowed, quiet"}, {"camera_use": "Soft ambient source in the room.", "directionality_class": "directional_3d", "element": "living room stand lamp", "orientation": "The lamp shade is seen from the side, its warm face turned slightly away from camera.", "state": "on, weak amber"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "foreground", "gesture_action": "points_to", "gesture_target_label": "bare dining tabletop", "label": "수리영 pointing beside table", "screen_zone": "middle_left", "target_id": "C01", "target_kind": "character"}, {"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "bare dining tabletop", "screen_zone": "middle_right", "target_id": "", "target_kind": "background"}], "reason": "points_to_anchor"}

[S17_Shot1] (outdoor; loc=L03; scene_heading=S#17. 옥탑방 / 동틀무렵)
description: 짙고 푸른 안개가 깔린 새벽녘, 희미한 노란 불빛이 켜진 옥탑방 창문을 향해 검은 고양이 한 마리가 고개를 돌린 찰나의 측면.
framing_scale: medium
camera_direction: Low at the 검은 고양이’s shoulder height, roughly one meter away, the camera tracks parallel along the rooftop wall and then holds a brief side profile as the cat turns its head toward the lit rooftop-room window. The cat occupies the lower left-to-center band of the frame, while the faint yellow window hangs in the misty background line of sight above the wall.
key_bg_elements: [{"camera_use": "distant visual lure for the cat’s head turn", "directionality_class": "transparent_surface", "element": "rooftop-room window", "orientation": "fogged glass shows a weak yellow interior glow beyond it", "state": "closed, lit from inside"}, {"camera_use": "tracking guide and jump setup", "directionality_class": "directional_3d", "element": "low concrete rooftop wall", "orientation": "the long side face runs parallel to the camera movement, with its top edge rising toward the next action", "state": "damp, stained"}, {"camera_use": "atmospheric veil separating cat and room", "directionality_class": "non_directional", "element": "blue dawn fog", "orientation": "", "state": "thick, cold, slowly moving"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "foreground", "gesture_action": "looks_toward", "gesture_target_label": "lit rooftop window", "label": "black cat", "screen_zone": "lower_left", "target_id": "C11", "target_kind": "character"}, {"depth_plane": "background", "gesture_action": "none", "gesture_target_label": "", "label": "lit rooftop window", "screen_zone": "upper_right", "target_id": "", "target_kind": "background"}], "reason": "looks_to_anchor"}

[S18_Shot15] (indoor; loc=L04; scene_heading=S#18. 안방 안 / D)
description: 거울 속 욕실 벽면에 선명한 붉은색 원형 표식이 맺혀 있는 정지 구도.
framing_scale: insert
camera_direction: Inside the bathroom, the camera is fixed at eye level about three feet from the mirror, tightened so the mirror reflection becomes the frame and the reflected rear wall sits centered. The red circular mark is isolated near the middle of the reflected wall, with only a sliver of mirror edge and damp tile context allowed to remain, making the apparition feel graphic and unavoidable.
key_bg_elements: [{"camera_use": "the shot’s perceptual surface and compositional border", "directionality_class": "reflective_surface", "element": "bathroom mirror", "orientation": "the mirror reflects the rear bathroom wall and the impossible red circular mark; a narrow mirror edge confirms this is a reflected view", "state": "slightly misted, cold"}, {"camera_use": "surface on which the occult symbol appears within reflection", "directionality_class": "content_surface", "element": "reflected bathroom wall", "orientation": "the wall face visible in the mirror carries a sharp crimson circular mark at its center", "state": "pale tile surface, otherwise clean"}, {"camera_use": "claustrophobic bathroom texture", "directionality_class": "non_directional", "element": "damp tile grout", "orientation": "", "state": "wet-looking, gray, stained"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "red circular mark in mirror reflection", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}], "reason": "required_background_position"}

[S18_Shot20] (indoor; loc=L04; scene_heading=S#18. 안방 안 / D)
description: 식탁 위에 놓인 사진 속, 살점이 뭉개진 채 기괴하게 흘러내린 (변형된 민숙)의 모습 클로즈업.
characters: 민숙
framing_scale: insert
camera_direction: At tabletop height beside the dining table, the push-in finishes at an extreme close angle on the framed photograph, stripping away nearly all surrounding table context. The mother’s photographed face, now perceived as 민숙 (변형된), occupies the central close field in a grotesque melted distortion, while the photo frame edge remains barely visible to prove this horror is trapped inside the image surface.
key_bg_elements: [{"camera_use": "primary hallucinated image surface", "directionality_class": "content_surface", "element": "framed family photograph", "orientation": "the front image face is angled slightly upward to camera, showing the mother’s face grotesquely distorted within the printed photo", "state": "upright on table, visually corrupted by hallucination"}, {"camera_use": "thin physical proof that this is still a household object", "directionality_class": "reflective_surface", "element": "photo frame glass", "orientation": "the glass reflects a dim streak of room light across the distorted face without hiding it", "state": "clean but unnervingly glossy"}, {"camera_use": "minimal scale reference around the frame", "directionality_class": "directional_3d", "element": "dining table edge", "orientation": "only a narrow tabletop plane and edge remain at the lower frame margin", "state": "still, ordinary, dim"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "foreground", "gesture_action": "none", "gesture_target_label": "", "label": "distorted mother’s face inside framed photograph", "screen_zone": "middle_center", "target_id": "C12", "target_kind": "character"}], "reason": "primary_subject_isolation"}

[S18_Shot6] (indoor; loc=L04; scene_heading=S#18. 안방 안 / D)
description: 열린 방문 너머, 핏자국 하나 없이 말끔하게 정돈된 방안 정경.
framing_scale: wide
camera_direction: Just outside 수리영’s room, the camera stays eye-level and static about five feet from the threshold, looking straight through the opened door into a room that appears too clean. The doorway forms a dark rectangular frame around the orderly bed, smooth floor, and untouched curtains, with no body, no stain, and no trace where memory said there should be horror.
key_bg_elements: [{"camera_use": "primary frame-within-frame revealing the room", "directionality_class": "directional_3d", "element": "opened bedroom door", "orientation": "the door slab is swung aside so the camera sees through the threshold into the room", "state": "open, still"}, {"camera_use": "visual proof of unnatural order", "directionality_class": "directional_3d", "element": "neatly arranged bed", "orientation": "the bed’s side and top plane face camera beyond the doorway", "state": "made, undisturbed"}, {"camera_use": "absence marker where the earlier horror is expected", "directionality_class": "transparent_surface", "element": "bedroom window with curtains", "orientation": "the window is partly obscured by clean curtains, with pale daylight diffused beyond", "state": "closed, curtains hanging evenly"}, {"camera_use": "negative evidence emphasized by stillness", "directionality_class": "non_directional", "element": "spotless bedroom floor", "orientation": "", "state": "clean, dry, no blood visible"}]

[S25_Shot4] (indoor; loc=L04; scene_heading=S#25. 옥탑방 안 / 해질 무렵)
description: 붉은 원 한가운데에 피가 묻은 낡은 흑백 사진이 꽂혀 있는 클로즈업.
framing_scale: close
camera_direction: Inside the bedroom at eye level, the dolly-in ends locked nearly perpendicular to the torn wall, holding a close composition where the blood-stained black-and-white photograph sits pinned at the exact center of a crimson circle. The photo and red mark take up the central mass of the frame, while the rough wall texture remains visible around them like scraped skin.
key_bg_elements: [{"camera_use": "central occult symbol and compositional target", "directionality_class": "content_surface", "element": "red circular wall mark", "orientation": "the painted wall face is directly visible to camera, showing a rough crimson circle surrounding the pinned photograph", "state": "fresh-looking, uneven, ominous"}, {"camera_use": "primary revealed clue", "directionality_class": "content_surface", "element": "old black-and-white photograph", "orientation": "the front image face is visible, showing an aged rural restaurant scene partially obscured by blood stains", "state": "pinned to wall, creased, blood-stained"}, {"camera_use": "macabre texture around the clue", "directionality_class": "non_directional", "element": "torn bedroom wall texture", "orientation": "", "state": "scraped, dirty, disturbed"}]

[S25_Shot8] (indoor; loc=L04; scene_heading=S#25. 옥탑방 안 / 해질 무렵)
description: 수리영이 한 손에 구겨진 사진을 꽉 쥔 채 백팩을 메고 현관 밖으로 한 발을 내디딘 찰나의 뒷모습.
characters: 수리영
framing_scale: wide
camera_direction: From inside the rooftop room behind 수리영, slightly below eye level and several feet back, the tracking shot widens just enough to include the open front-door threshold as she steps out. Her back and backpack sit in the middle of frame, one foot crossing into the exterior light, while the crumpled photograph remains readable as a tight fist-level detail near her right side.
key_bg_elements: [{"camera_use": "destination frame and exit boundary", "directionality_class": "directional_3d", "element": "open front door", "orientation": "the inside face of the open door and its threshold angle toward the camera as 수리영 exits", "state": "open, letting in dim exterior dusk"}, {"camera_use": "evidence of intrusion in the room she leaves behind", "directionality_class": "non_directional", "element": "scattered household debris", "orientation": "", "state": "ransacked, strewn across the floor"}, {"camera_use": "broken domestic geometry in the side background", "directionality_class": "directional_3d", "element": "overturned dining chairs", "orientation": "chair legs jut sideways at uneven angles across the room", "state": "knocked over"}, {"camera_use": "damp air source and unsettling escape route implication", "directionality_class": "transparent_surface", "element": "open living-room window", "orientation": "the camera sees the dark opening and wet exterior air beyond the window frame", "state": "open, dirty, cold"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "midground", "gesture_action": "moves_toward", "gesture_target_label": "open front door", "label": "수리영", "screen_zone": "middle_center", "target_id": "C01", "target_kind": "character"}, {"depth_plane": "background", "gesture_action": "none", "gesture_target_label": "", "label": "open front door threshold", "screen_zone": "upper_center", "target_id": "", "target_kind": "background"}], "reason": "movement_direction"}

[S27_Shot1] (indoor; loc=L04; scene_heading=S#27. 옥탑방 안 / 해질 무렵)
description: 난장판이 된 옥탑방 거실, 혜수가 핸드폰을 귀에 댄 채 심각한 표정으로 굳어 있는 상체.
characters: 혜수
framing_scale: medium
camera_direction: Inside the rooftop living room at chest height, the camera continues the flow’s slow dolly-in from about 2.5 meters, tightening to a medium upper-body frame of 혜수 with the phone pressed to her ear. She sits slightly right of center amid overturned, damp-looking clutter, angled three-quarters as if her attention has just pulled toward 김형사 off-frame rather than toward us.
key_bg_elements: [{"camera_use": "visible disorder around 혜수, keeping the room’s violated condition readable behind her", "directionality_class": "non_directional", "element": "scattered rooftop-room clutter", "orientation": "", "state": "messy, overturned, neglected"}, {"camera_use": "background source of cold draft and later sound, held out of focus behind the anxiety", "directionality_class": "directional_3d", "element": "entrance door", "orientation": "its inner face angles slightly away from camera, showing the rattling edge and frame gap", "state": "not fully secure, wind-shaken"}, {"camera_use": "thin translucent layer over the small room window, adding a damp dusk haze", "directionality_class": "transparent_surface", "element": "grimy window glass", "orientation": "dirty glass catches the gray exterior light while showing only a blurred rooftop beyond", "state": "streaked, dim"}]

[S4_Shot1] (outdoor; loc=L03; scene_heading=S#4. 옥탑방 / D)
description: 인천 변두리의 낡고 오래된 빌라 옥탑방 외부 전경이 한눈에 내려다보이는 부감 구도.
framing_scale: wide
camera_direction: An omniscient overhead camera holds from about forty-five meters above the old villa, centered on the rooftop room while still keeping the surrounding neighborhood readable. The rooftop structure sits in the middle of the frame like a small exposed shrine, boxed in by worn roofs, narrow alleys, and faded concrete blocks.
key_bg_elements: [{"camera_use": "The rooftop room is the central visual anchor and destination of the aerial reveal.", "directionality_class": "directional_3d", "element": "old rooftop room exterior", "orientation": "its roof and front wall are visible from above, with the doorway side angled slightly toward camera", "state": "aged, patched, weather-stained"}, {"camera_use": "Surrounding villa roofs create a cramped grid that isolates the rooftop room.", "directionality_class": "directional_3d", "element": "neighboring old villa rooftops", "orientation": "flat roof planes face upward toward the overhead camera", "state": "worn, cluttered, pale gray"}, {"camera_use": "A thin haze softens the outskirts and carries the news voice’s unease into the space.", "directionality_class": "non_directional", "element": "damp urban haze", "orientation": "", "state": "thin, bluish, stagnant"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "midground", "gesture_action": "none", "gesture_target_label": "", "label": "old rooftop room", "screen_zone": "middle_center", "target_id": "", "target_kind": "background"}], "reason": "required_background_position"}

[S5_Shot10] (indoor; loc=L04; scene_heading=S#5. 옥탑방 안 / 실내)
description: 수리영이 민숙의 어깨에 코를 묻고 멈춘 찰나의 측면.
characters: 수리영, 민숙
framing_scale: close
camera_direction: The camera follows the flow into the narrow entrance area and holds side-on at shoulder height, about one meter away, lens parallel to the wall to compress mother and daughter together. The tighter profile frame favors the contact point: Suriyeong’s face and nose press into Minsuk’s shoulder at center-left, while Minsuk’s softened profile and apron edge sit center-right.
key_bg_elements: [{"camera_use": "The narrow wall flattens the space and makes their closeness feel private and fragile.", "directionality_class": "non_directional", "element": "entrance wall", "orientation": "", "state": "worn, slightly yellowed, close to camera plane"}, {"camera_use": "The shoe area at the bottom edge hints at Suriyeong leaving soon without pulling focus from the embrace.", "directionality_class": "directional_3d", "element": "entryway shoe area", "orientation": "shoe tops and low threshold edge face the camera from below the profiles", "state": "cluttered, dim"}, {"camera_use": "The door seam creates a vertical boundary beside them, suggesting a moment just before departure.", "directionality_class": "directional_3d", "element": "front door seam", "orientation": "the flat door face is seen in side compression, seam running vertically near the right edge", "state": "closed, dull, scuffed"}]

[S5_Shot12] (indoor; loc=L04; scene_heading=S#5. 옥탑방 안 / 실내)
description: 민숙의 손목 안쪽에 새겨진 작은 원 모양의 표식 클로즈업.
characters: 민숙
framing_scale: insert
camera_direction: The camera completes the flow’s downward push from Suriyeong’s side of the entrance to a very close waist-height insert, about twenty centimeters from Minsuk’s inner wrist. The wrist cuts diagonally across the center of frame, the small circular mark isolated in sharp focus while skin, sleeve edge, and the entryway behind fall into creamy blur.
key_bg_elements: [{"camera_use": "The marked skin surface is the focal plane and occult reveal.", "directionality_class": "content_surface", "element": "inner wrist with circular mark", "orientation": "the inner wrist surface faces the camera, showing a small dark circular mark clearly against the skin", "state": "exposed, sharply focused, mark unusually distinct"}, {"camera_use": "The sleeve cuff frames the wrist without becoming the subject.", "directionality_class": "directional_3d", "element": "apron or sleeve edge", "orientation": "fabric edge runs along the wrist from camera-left, seen as a soft side fold", "state": "soft, worn, out of focus"}, {"camera_use": "The entrance background becomes an indistinct shadow field so the symbol carries the tension.", "directionality_class": "non_directional", "element": "blurred entryway background", "orientation": "", "state": "dim, warm-gray, unfocused"}]
frame_spatial_contract: {"constraints": [{"depth_plane": "foreground", "gesture_action": "none", "gesture_target_label": "", "label": "Minsuk inner wrist mark", "screen_zone": "middle_center", "target_id": "C04", "target_kind": "character"}], "reason": "primary_subject_isolation"}

[S5_Shot3] (indoor; loc=L04; scene_heading=S#5. 옥탑방 안 / 실내)
description: 앞치마를 두른 민숙이 어두운 표정으로 거실 TV 화면을 응시하며 굳어 있는 상체.
characters: 민숙
framing_scale: medium
camera_direction: The observer camera settles at the end of its lateral track from near the sink and small window, chest height and about two and a half meters from Minsuk, looking across the counter line toward the living room TV. Minsuk is held in an upper-body frame at the right-middle of the image, shoulders locked in her apron as the kitchen foreground remains softly present and the TV glow pulls her stare off-frame.
key_bg_elements: [{"camera_use": "The TV is the off-frame source of her fixed attention and casts a cold news glow across the room.", "directionality_class": "content_surface", "element": "living room TV screen", "orientation": "the screen face is angled away from the camera, showing only a sliver of moving blue news light rather than readable content", "state": "on, low volume, flickering"}, {"camera_use": "The sink and herbs sit in the near foreground, domestic routine interrupted by dread.", "directionality_class": "directional_3d", "element": "sink with unfinished medicinal herbs", "orientation": "the basin rim and faucet side face the camera across the counter", "state": "water running, herbs wet and half-washed"}, {"camera_use": "Steam from the pot veils the compact room and gives the practical light a sick texture.", "directionality_class": "non_directional", "element": "boiling pot steam", "orientation": "", "state": "rising, thin, wavering"}, {"camera_use": "The small window gives a narrow daylight slit that contrasts with the TV’s colder glow.", "directionality_class": "transparent_surface", "element": "small living-room window", "orientation": "slightly dirty glass admits pale daylight; only a blurred exterior brightness is visible through it", "state": "closed, dusty"}]

Design the whole-property site plan element set now.
llm 호출 기록 — forest_root_readback (gpt)
SYSTEM:
You read technical plans precisely.

USER:
[{"type": "text", "text": "This is a top-down site plan with circled capital letters and a legend panel. List every circled capital letter, list the legend entries as written, and say whether any interior room layout is exposed."}]