[RenderPromptCard v1]
{"asset_requirements":{"constraints":["do not imply or describe a reference image that is not listed in required_refs (no phantom references)","if a required character_outlook ref is missing, scene image generation must block before the image stage"],"forbidden_refs":[],"readiness_policy":"block_if_missing","required_refs":[{"id":"C01O01","kind":"character_outlook","policy":"required"},{"id":"C02O02","kind":"character_outlook","policy":"required"},{"id":"C03O03","kind":"character_outlook","policy":"required"},{"id":"L01B04","kind":"background","policy":"required"}]},"background_binding":{"bg_id":"L01B04","camera_reference":null,"close_framing_skips_background_ref":false,"constraints":["owned_objects lists all environment objects already drawn in the background reference — do not create new ones","if focusing on an owned object, declare its reference-kind via the reference_phrase_kinds sidecar (producer contract)"],"mode":"background_ref_attached","owned_objects":["blanket","door","fluorescent light","workbench"],"reference_usage":"exact_background"},"continuity_elements_used":{"constraints":["fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented","when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt","previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments","previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room","previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone","one t2i_prompt = one camera position — third-person full body and close-up of the same character must not be combined in a single shot. any framing-intent wording designates the area shown by the single camera position, not a view switch (id_policy.subject_reference_policy applies per-subject)","props held by characters face one direction only — toward camera OR toward character, never both"],"cross_shot_id_substitution_rule":{"applies_when":"fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs","double_description_forbidden":"do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures","no_repeat_after_pose":"이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라","preserve_pose_unchanged":"fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체","rationale_summary":"fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다","substitution":"replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##"},"fixed_elements":[{"applies_to_shots":[1,5],"character_name":"Old Man","confidence":"high","creative_decisions":["Positioned low in the frame to emphasize his vulnerability and immobile state."],"description":"An elderly Korean man lies completely motionless on the floor in an unconscious state. His eyes remain firmly closed, and his limbs are kept entirely still. He is positioned near the center of the cleared floor space.","element_id":"old_man_unconscious_posture","element_scope":"full","element_type":"character_state","source_facts":["노인이 눈을 감은 채 누워 있다","lying beneath the blanket, gaze=closed_eyes, state=unconscious","limbs still"],"visual_inferences":["His facial expression is slack and resting, showing no response to the surrounding environment."]},{"applies_to_shots":[1,5],"character_name":"Minsu","confidence":"high","creative_decisions":["His folded, grounded posture visually connects him to the old man, indicating his protective watchfulness."],"description":"A young Korean man maintains a low, balanced squatting posture on the floor right next to the old man. His heels are firmly grounded, his torso is slightly bowed forward, and his gaze is steadily directed downward at the unconscious man.","element_id":"minsu_squatting_posture","element_scope":"full","element_type":"character_state","source_facts":["민수가 노인 곁에 쪼그려 앉아 있다","balanced in a low squat","heels grounded, torso bowed","gaze=looks_at_character"],"visual_inferences":["His arms are likely resting near his knees to support his crouched balance."]},{"applies_to_shots":[1,5],"character_name":"","confidence":"high","creative_decisions":["The blanket acts as a visual anchor on the floor, contrasting with the mechanical clutter of the workshop."],"description":"A thick blanket is draped over the old man lying on the floor. It covers his torso and legs, concealing his body shape while leaving his head and face clearly visible.","element_id":"blanket_covering","element_scope":"full","element_type":"persistent_prop","source_facts":["담요를 덮고","blanket-covered old man extending across the lower center"],"visual_inferences":["The blanket looks slightly wrinkled and heavy, providing warmth in the cold environment."]},{"applies_to_shots":[1,5],"character_name":"","confidence":"high","creative_decisions":["Used as a framing device on the edge of the shot to emphasize the cramped nature of the workshop while justifying the open floor space."],"description":"A repair workbench is permanently pushed aside against the edge of the narrow workshop. This arrangement deliberately clears the central floor area, creating a spatial boundary for the characters resting on the ground.","element_id":"displaced_workbench","element_scope":"full","element_type":"environment_state","source_facts":["작업대를 한쪽으로 밀어 자리를 냈다","The displaced workbench stays along one frame edge as a spatial boundary"],"visual_inferences":["The surface of the workbench holds scattered tools or bicycle parts."]}],"forward_zoom_targets":[],"previous_shot_refs":[{"kind":"location","ref_usage":"","scene_index":3,"shot_index":1}],"ref_usage_constraints":{"atmosphere_reference":{"forbidden_imports":["furniture layout from the prior shot","wall positions from the prior shot","specific architectural features from the prior shot"],"rationale_summary":"atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성","required_handling":"describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')","scope_summary":"different room/floor/angle entirely — only mood/tone is shared with the prior shot"},"exact_background":{"background_consistency_rule":"background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)","ignore_keep_handled_elsewhere":"ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt","permitted_additions":["new persons, poses, expressions, actions for this shot's moment","different camera angle within the same room"],"rationale_summary":"같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관","scope_summary":"same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot"},"zoom_in_detail":{"forbidden_additions":["new persons not in the prior shot","new props not in the prior shot","new background elements not in the prior shot","new poses, gestures, or expressions not in the prior shot","different moments of action"],"rationale_summary":"zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사","required_phrasings":["describe only the focused sub-region in concrete terms","explicitly state the same environment (lighting, background) is preserved","use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"],"scope_summary":"same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only","subject_reference_policy_cross_ref":"id_policy.subject_reference_policy applies per-subject; policy enum (id_and_outlook_required / base_id_required / generic_descriptor_allowed) determines C##/C##O## use"}},"view_consistency":{"close_up_handling":"an isolated framed area of a single subject must not coexist with that subject's full-body description in the same prompt","focus_on_is_focus_area_not_view_switch":"any framing-intent wording designates the area shown by the single camera position; it does not switch the view","framing_scope_options":["third_person","close_up"],"mixing_forbidden":true,"prop_orientation_rule":"props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)","rationale_summary":"single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리","single_camera_rule":"one t2i_prompt = one camera position. third-person full body and close-up of the same character must not be combined in a single prompt.","subject_reference_policy_cross_ref":"id_policy.subject_reference_policy — subjects with policy = 'base_id_required' or 'generic_descriptor_allowed' must not use outlook reference (C##O## form); additionally, subjects with policy = 'generic_descriptor_allowed' must not use bare C## either — render with a common/demographic descriptor only","third_person_handling":"describe persons with full or partial body in frame; single-camera consistency forbids combining a partial close-up and the same character's full body in one prompt"}},"id_policy":{"allowed_base_entity_ids":["C01","C02","C03","L01","P03","P06"],"allowed_outlook_pairs":[{"character_id":"C01","outlook_id":"O01"},{"character_id":"C02","outlook_id":"O02"},{"character_id":"C03","outlook_id":"O03"}],"common_noun_required_when":["a reproduced face inside any declared reproduction surface","unregistered extra"],"constraints":["ID format for visible subjects (C## bare, C##O## composite IDs, or common-noun descriptor) is determined per-subject by the id_policy per-subject policy array — see constraints[2] below","do not use C##O## for a reproduced face inside any element flagged by id_policy.reproduction_surface_rule.applies (declared reproduction surface) — use a generic descriptor with demographic instead. NOTE: the physical photo/poster/document/picture-frame/map/key prop itself MUST use its P## ID — the generic-descriptor rule applies only to a face reproduction, not to the prop entity.","per-subject identity reference policy is provided in id_policy.subject_reference_policy[] — apply each subject's policy when emitting references: (a) id_and_outlook_required ⇒ subject must use C##O## composite ID; (b) base_id_required ⇒ subject must use bare C## only (no outlook); (c) generic_descriptor_allowed ⇒ subject must NOT use C## or C##O##, render with a common/demographic descriptor only. omitted subjects default to id_and_outlook_required","when an ID is required for a subject (policy = id_and_outlook_required or base_id_required) and a C##O## (or C##) is introduced for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns. does not apply to generic_descriptor_allowed subjects (no ID emitted)","when an ID is required (policy = id_and_outlook_required or base_id_required), use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence). does not apply to generic_descriptor_allowed subjects — those use a common/demographic descriptor with no C##/C##O##"],"demographic_descriptor_policy":{"applies_to_id_forms":["C##","C##O##"],"components":{"age_band":["in his/her 20s","in his/her 30s","in his/her 40s","young","middle-aged","elderly"],"ethnicity":["Asian","East Asian","South Asian","Southeast Asian","Black","Middle Eastern","Hispanic","Latina","Latino","Caucasian"],"gender":["man","woman","figure"],"role_hint_from_outfit":["in worker uniform","in fisher workwear","in detective coat","in business suit"]},"format_template_a":"C##O## in <옷 1-3 단어>, <demographic descriptor>","format_template_b":"C##O##, <demographic descriptor>, <자세 표현>","regional_consistency":"한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정","required_on_first_appearance":true,"scenario_dependency_ban":"no work-specific proper nouns (character names, place names) — common nouns only","source_priority":["visual_world_rules.region","visual_world_rules.era","shot context outfit hint"],"token_count_range":[1,2]},"demographic_fallback_required":true,"face_identifiability_rule":{"common_noun_required_when":["back to camera with no visible face","silhouette or blurred outline only","OTS with only back of head/shoulder, face entirely hidden"],"id_use_summary":"C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part","rationale_summary":"C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌","use_entity_id_when":["face identifiable: front, profile, three-quarter, or eyes closed","OTS framing with any visible face"]},"id_use_required_when":["a physical photo/poster/document/picture-frame/map/key prop appearing in the scene — use its P## ID and preserve canonical content from entity_canon"],"must_use_composite_character_ids":true,"reproduction_surface_rule":{"applies":false,"id_use":"forbidden — generic descriptor with demographic only","rationale_summary":"C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면/반사 표면 안 얼굴이 표면 밖 실물 크기로 합성됨. 이 rule 은 표면 안 얼굴 (face) 에만 적용 — 물리적 사진/액자/문서 prop 자체는 P## ID 보존 (Patch A)."},"subject_reference_policy":[]},"render_contracts":[],"render_strategy":{"camera_direction":"Complete the crane withdrawal high near an interior corner and hold a steep oblique wide view across the entire narrow workshop: the old man lies low near center, Minsu remains folded beside him, and Yeonhee is separated at the doorway. At the instant the fluorescent light goes out, the changed lighting is the single emphasized axis; the three figures retain their established positions, with Minsu attending to the old man and Yeonhee looking out toward the alley.","constraints":["one prompt captures one still moment","do not combine full-body framing and body-part close-up in one frame","camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule","two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule","framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"],"frame_spatial_contract":{"constraints":[{"constraint_id":"fsc_001","depth_plane":"midground","gesture_action":"looks_toward","gesture_target_label":"노인","label":"민수","screen_zone":"middle_right","target_id":"C01","target_kind":"character"},{"constraint_id":"fsc_002","depth_plane":"background","gesture_action":"looks_toward","gesture_target_label":"골목","label":"연희","screen_zone":"upper_left","target_id":"C02","target_kind":"character"},{"constraint_id":"fsc_003","depth_plane":"midground","gesture_action":"none","gesture_target_label":"","label":"노인","screen_zone":"lower_center","target_id":"C03","target_kind":"character"}],"reason":"shared_space_relation"},"framing_scale":"wide","lighting_mood":"As the fluorescent light goes out, the workshop falls abruptly into restrained low-key darkness with all three figures only faintly legible.","mode":"direct","moment_lock":"single still moment from the selected shot only","perception_mode":"direct","primary_subject":"","spatial_consistency":{"camera_frame_rule":{"applies_when":"camera_direction expresses a vertical camera height or viewpoint position and the scene description includes frame-edge surfaces","consistency_check_summary":"elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges","core_principles":["low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden","overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden","hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together","full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"],"forbidden_combinations":["low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject","overhead high angle + feet visible at the lower frame edge with floor visible below them","hip-height side camera + full silhouette including head and feet visible in same frame","low angle looking up + ceiling and floor both fully visible in same frame"],"rationale_summary":"T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과","recommended_phrasings":["low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge","overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them","at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges","low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"],"self_check_steps":["identify the camera position phrasing (height + angle)","list elements described inside the frame (foreground prop, body parts, background surfaces)","verify each element's vertical/depth placement is geometrically consistent with that camera position","if mismatch found, adjust frame-edge description to match camera position"]},"fg_bg_shared_anchor_rule":{"applies_when":"two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)","forbidden_phrasings":["fg/bg separation without naming the shared surface/space","isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)","one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"],"rationale_summary":"fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제","recommended_keywords":["shared bench / shared table / shared surface","the same X they both occupy (X = bench, sofa, table, doorway, room)","across the X from each other","<prop> crosses the air between them (interaction prop visually links the two)","the <surface> sharing a single line of sight from the camera"],"self_check_steps":["do the two characters share a single interaction (dialogue, handing, facing, co-watching)?","is one foreground and the other background-separated?","is the shared surface/space anchor explicitly named?","if not, add one of the recommended keywords"],"shared_anchor_required":"describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space"},"primary_framing_rule":{"applies_when":"framing_scale ∈ {close, medium, wide, insert} from `shot_staging.framing_scale` enum (render_strategy.framing_scale, production SOT). LLM consumes the enum only; keyword classification is forbidden.","close_framing_rules":{"forbidden_combinations":["same character's full body and body-part close-up in the same frame (view mixing)","two characters both rendered as sharp close-up faces in the same frame"],"other_entities_appearance_options":["partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge","soft background — out-of-focus silhouette via shallow depth of field","absent — not rendered at all even if listed in visible_entities"],"primary_subject_only_fully_visible":"the named primary subject (hand / face / object) is the only fully visible entity in the frame","subject_reference_policy_cross_ref":"see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"},"rationale_summary":"한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성","self_check_steps":["read framing_scale enum from render_strategy.framing_scale (do NOT infer from camera_direction)","if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent","verify same character's full body + body-part close-up are not combined","if close: verify two faces are not both rendered sharp"],"wide_medium_rules":{"body_part_close_up_forbidden":"body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot","fg_bg_separation_requires_shared_anchor":"if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule","primary_and_secondary_both_visible":"primary subject + secondary entities all renderable","subject_reference_policy_cross_ref":"see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"}},"rationale_summary":"Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."}},"schema_version":1,"shot_key":{"scene_index":3,"shot_index":5}}

[Entity stable_traits for this shot]
- C01 (민수): 한국인 남성, 40대 중년 얼굴, 자연스러운 검은 머리
- C02 (연희): 한국인 여성, 20대 젊은 얼굴, 자연스러운 검은 머리
- C03 (노인): 한국인 남성, 70대 노년 얼굴, 자연스러운 얼굴 주름, 희끗한 머리

[chain_bg에 이미 그려진 객체 — 새로 그리지 말 것 (Rule C contract)]
- blanket
- door
- fluorescent light
- workbench

씬 3 요약: 밤이 된 정비소 안, 형광등 불빛 아래 작업대가 치워진 공간에 노인이 담요를 덮고 누워 있습니다. 남색 작업복의 민수는 노인 곁에 쪼그려 앉아 보살피고 있으며, 노란 우비를 입은 연희는 문가에서 손전등을 껐다 켜며 골목 밖 구급차를 기다립니다.

[분석 대상 Shot]
  Shot 5: 천장의 형광등 불빛이 꺼져 일순간 어두워진 좁은 정비소 실내 전경. 바닥의 노인, 쪼그려 앉은 민수, 문가의 연희가 희미하게 보인다.
  Beat #2 [reaction]: 골목을 살피며 구급차가 오지 않아 초조하고 긴장된 상태 → 구급차가 곧 올 것이라는 연희의 말에 민수가 동의하며 서로 안심을 나누는 상태
  [앞쪽 연관 Shot — 연속성 유지]
    배경 참조: S3_Shot1
[중요 — 순간 고정]
t2i_prompt는 위 Shot description이 묘사하는 정확한 순간만 캡처하세요.
씬의 다른 시점이나 다른 장면은 포함하지 마세요.
이 shot에서 카메라에 찍히는 것만 영어로 묘사하세요.

[교차 샷 고정 요소]

  [인물 상태] old_man_unconscious_posture (Old Man):
    An elderly Korean man lies completely motionless on the floor in an unconscious state. His eyes remain firmly closed, and his limbs are kept entirely still. He is positioned near the center of the cleared floor space.

  [인물 상태] minsu_squatting_posture (Minsu):
    A young Korean man maintains a low, balanced squatting posture on the floor right next to the old man. His heels are firmly grounded, his torso is slightly bowed forward, and his gaze is steadily directed downward at the unconscious man.

  [고정 소품] blanket_covering:
    A thick blanket is draped over the old man lying on the floor. It covers his torso and legs, concealing his body shape while leaving his head and face clearly visible.

  [환경 상태] displaced_workbench:
    A repair workbench is permanently pushed aside against the edge of the narrow workshop. This arrangement deliberately clears the central floor area, creating a spatial boundary for the characters resting on the ground.

[사용 가능한 엔티티]
  C01 (민수)
  C02 (연희)
  C03 (노인)
  L01 (좁은 자전거 정비소 내부)
  P03 (휴대용 손전등)
  P06 (담요)

인물별 아웃룩 선택지 (각 variation의 outfit_assignments에 인물별 1개씩 선택):
  C01 아웃룩: O01(남색작업복) [확정]
  C02 아웃룩: O02(노란우비) [확정]
  C03 아웃룩: O03(회색외투) [확정]

[촬영 감독(DP) 연출 지시 — 반드시 t2i_prompt에 반영하세요]
카메라 관점(POV): omniscient
카메라/프레이밍: Complete the crane withdrawal high near an interior corner and hold a steep oblique wide view across the entire narrow workshop: the old man lies low near center, Minsu remains folded beside him, and Yeonhee is separated at the doorway. At the instant the fluorescent light goes out, the changed lighting is the single emphasized axis; the three figures retain their established positions, with Minsu attending to the old man and Yeonhee looking out toward the alley.
조명/색감: As the fluorescent light goes out, the workshop falls abruptly into restrained low-key darkness with all three figures only faintly legible.
배경 핵심 요소:
  - 한쪽으로 밀린 작업대: 한쪽에 옮겨져 있음 (Clarifies the cleared floor layout in the high wide composition.) [방향: Its top and long side are visible from above along the room's edge.]
  - 정비소 문: 연희가 문가에서 골목 쪽을 내다봄 (Anchors Yeonhee at the far edge of the room and establishes her outward attention.) [방향: The doorway is viewed diagonally from the opposite interior corner, with its opening beyond Yeonhee.]
  - 손전등: 연희가 껐다 켰다 하는 중 (Remains a small readable prop associated with Yeonhee without becoming the dominant light cue.) [방향: Its body is faintly visible in Yeonhee's hand, angled toward the doorway area.]
  - 담요: 바닥의 노인을 덮고 있음 (Keeps the old man's prone position distinguishable in the dim wide view.)
[인물-카메라 각도 + 시선 + 상태 — 절대 무시 금지, t2i_prompt에 반드시 반영]
아래 각 인물의 카메라 대비 방향, 자세, 시선 방향, 신체 상태를 t2i_prompt에 영어로 구체적으로 명시하세요:
- facing_camera → 'facing the camera' / back_to_camera → 'with back to camera'
- profile_left → 'in left profile' / three_quarter_right → 'at three-quarter angle from the right'
- gaze=camera → 'looking at the camera' / gaze=down → 'looking down' / gaze=up → 'looking up'
- gaze=distant → 'gazing into the distance' / gaze=closed_eyes → 'with eyes closed'
- gaze=off_screen → 'looking off-screen' / gaze=looks_at_character→C## → 'eyes fixed on [that character]'
- gaze=looks_at_object→P##/B## → 'eyes fixed on [that prop/background element]'
- state=alive → 평소 자세/표정 / state=unconscious → 'unconscious, slack and limp'
- state=dead → 'lying motionless, lifeless' / state=severely_injured → 'visibly wounded, pained expression'
인물이 2명 이상이면 각각의 방향, 시선, 상태를 따로 명시하세요.
- 엔티티 미등록 인물은 C## ID 대신 보통명사 + demographic descriptor (인종/연령대/성별)로 묘사하세요. 인종은 visual_world_rules.region 이 명시한 ethnicity 그대로 carry — production code / prompt 어디에도 hardcoded ethnicity 어휘 list 를 강요하지 마세요 (시나리오/region 마다 다름, A-prime binding).
  노인: back_to_camera, blanket-covered, limbs still, gaze=closed_eyes, state=unconscious
  민수: three_quarter_left, heels grounded, torso bowed, gaze=looks_at_character→C03, state=alive
  연희: back_to_camera, leaning toward the doorway, gaze=off_screen, state=alive

[카메라 포커싱]
t2i_prompt에 카메라가 무엇에 초점을 맞추는지 반드시 명시하세요:
- 인물의 특정 신체 부위/표정 (영어 명사구로 구체적 묘사 — gender / emotional label 은 본 beat 의 staging.subject_state 와 character_angles 에서 가져오기)
- 본 shot 의 핵심 narrative 객체 (해당 beat 에서 등장하는 prop 또는 background element)
- 두 인물 간 공간/시선 관계 (subject 간 frame 안 spatial tension)
- 단순히 앵글만 쓰지 말고, 그 앵글로 무엇을 강조하는지 반드시 포함할 것

[조명/색감 판단]
beat의 상태 변화와 씬 분위기를 고려하여 t2i_prompt에 조명과 색감을 반영하세요:
- 시간대(낮/밤/새벽/석양), 자연광/인공광, 색온도(따뜻한/차가운)
- 색감은 beat의 정서와 씬 분위기에서 직접 derive하고, 특정 정서에 고정 색조를 대응시키도록 강요하지 마세요
- 핵심 인물/물체에 대한 조명 방향(역광/사광/정면광)

[규칙]
- 인물+아웃룩은 복합 ID(C01O02)를 사용 — 합성 단계가 'the character from Image N'으로 자동 치환.
- 신체 부위 클로즈업/사진·거울 속 인물 등 system prompt가 명시한 예외 구도에서는 보통명사로 대체 (system 룰 참조).
- outfit_assignments에 각 인물이 이 variation에서 입는 아웃룩 ID를 지정 — t2i_prompt의 복합 ID와 같은 정보를 명시.
- t2i_variations 정확히 1개.
- 각 variation의 t2i_prompt는 해당 촬영 기법의 카메라 구도를 반영할 것.

씬 텍스트:
#3. 정비소 안 – 밤

작업대를 한쪽으로 밀어 자리를 냈다. 형광등 불빛 아래 노인이 담요를 덮고 눈을 감은 채 누워 있다.

민수가 노인 곁에 쪼그려 앉아 있다. 연희는 문가에 서서 손전등을 껐다 켰다 하며 골목 쪽을 내다본다.

연희: 구급차 곧 올 거예요. 조금만 더 기다리면 돼요.

민수가 말없이 고개를 끄덕인다. 형광등이 한 번 깜빡인다.[부동 피사체 연속성 계약 — immobilized subject continuity]
아래 인물은 같은 씬의 여러 컷에 걸쳐 스스로 움직이지 못하는 상태입니다. 자세·신체 방향·위치, 그리고 쥐고 있거나 곁에 닿은 소품의 상태는 컷마다 동일해야 하는 고정 계약입니다. 카메라 앵글/프레이밍/크롭은 이 샷의 묘사대로 자유이나(가까이 잡아 일부만 보여도 됨), 이 물리적 상태/자세/소품 상태는 바꾸거나 새로 지어내지 마세요.
  C03 [unconscious]: The immobilized subject lies motionless on the garage floor beside the workbench, eyes closed and covered by a blanket. No specific head or limb direction is established, so all shots must preserve the same unspecified resting orientation. | 이 샷 프레임에 보이는 부분: Wide but briefly darkened view in which the blanket-covered body remains faintly visible on the floor.