{
  "status": "completed",
  "applicable_count": 26,
  "completed_count": 26,
  "failed_count": 0,
  "schema_version": 3,
  "config_hash": "b7aceec6a4318cf9",
  "data": {
    "contis": {
      "S1sh3": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S1sh3.png",
        "plate_path": null,
        "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: A dense patch of undergrowth within a forest at dusk, where the fleeing victim is overtaken among the shrubs.\n\nSHOT TEXT (authoritative, Korean): 허공에 뜬 검은 형상의 존재가 금월산 남성 피해자의 등 위를 짓누르며 닿고, 그 충격으로 피해자의 몸이 앞으로 크게 휘청이는 역동적 충돌 찰나의 측면\n\nCARRIED STATE (persist exactly): The male victim is still missing one shoe, with a large bite wound on his thigh bleeding as the black figure strikes him.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At waist height and several meters to the side, the camera tracks parallel in a broad profile, widening only enough to preserve the changed distance and reveal the entire collision. 금월산 남성 피해자 pitches across the right half of frame while 검은 형상의 존재 descends through the upper-left space onto his back, leaving visible lateral room for the full forward stagger.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 우거진 수풀 (Dense along the forest route); used as The surrounding growth establishes the escape path behind the profile collision without obstructing either figure.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "no_plate": true,
        "ref_paths": [
          [
            "char:낯선 한국인 남성",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/f2ffa081-c9bc-47d2-8354-d671ca856080.png"
          ]
        ],
        "asset_id": "10afec5f-f0f7-4691-b81d-3c94a3505e02"
      },
      "S2sh2": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S2sh2.png",
        "plate_path": null,
        "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: A dimly lit urban back alley at night, directly beside a utility pole under a faint streetlamp.\n\nSHOT TEXT (authoritative, Korean): 효장동 여성 피해자의 목덜미에 이빨을 박아 넣은 낯선 한국인 남성의 붉은 눈동자 클로즈업\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At the man's eye height and slightly beside his face, the continuing dolly-in resolves into an extreme close-up in which his red eye occupies most of the central field while his teeth and the woman's neck remain legible along the lower edge. The oblique angle keeps the image predatory rather than portrait-like, with the utility pole and alley reduced to narrow peripheral fragments.\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: red eye and biting mouth in the middle-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: 전봇대 (The two figures are pressed together in front of it) — Its near side appears as a narrow strip behind the two figures; used as A thin peripheral vertical anchors the entwined bodies in the alley without competing with the eye; 가로등 불빛 (On and faint); used as Provides the explicitly faint illumination falling across the close observation.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "no_plate": true,
        "ref_paths": [
          [
            "char:낯선 한국인 남성 (육혈귀 활성 상태)",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/1629ff51-e264-4a3f-9d0e-1ca19087dc8c.png"
          ]
        ],
        "asset_id": "3e42da30-1925-4ac0-b3dd-0c6882eaf1c5"
      },
      "S3sh2": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S3sh2.png",
        "plate_path": null,
        "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The police perimeter in a forest clearing around the first body-discovery site, bordered by dense vegetation.\n\nSHOT TEXT (authoritative, Korean): 폴리스 라인 근처에 선 채 날카로운 시선으로 주변 한 곳을 응시하는 혜수의 상체\n\nCARRIED STATE (persist exactly): The police line remains erected around the crime scene while the bodies are being recovered.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Presented as local-news footage, the camera settles at 혜수's chest height near the police line after its dolly-in, holding her upper body in the right-center at a slight three-quarter angle. Her fixed eyeline cuts toward an unseen area beyond the left edge while the police line remains as a shallow diagonal boundary behind her.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 폴리스 라인 (Set around the scene); used as Runs diagonally behind 혜수 to separate her command position from the active collection area; 시신 수거 현장 (Police are processing the scene and collecting the bodies); used as Supplies restrained background activity while remaining subordinate to 혜수's gaze.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "no_plate": true,
        "ref_paths": [
          [
            "char:혜수",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/4af6ff57-5a8a-4168-98cd-a821386dd2d9.png"
          ]
        ],
        "asset_id": "d1af6951-6a6b-4d85-b7bb-b9176dd0e522"
      },
      "S4sh1": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S5sh5": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S5sh5.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B02.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the rooftop dwelling at its compact entrance area, adjacent to the living room. Daylight filters in through the small living-room window.\n\nSHOT TEXT (authoritative, Korean): 현관에 선 채 상체를 기울여 강민숙(민숙)의 어깨 부근에 코를 대는 수리영\n\nCARRIED STATE (persist exactly): Min-sook is still wearing her apron, and the small circular mark already exists on her wrist before Su-ri-yeong notices it in the following shot.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At upper-torso height about one meter away, the camera completes its short arc toward 강민숙's shoulder side and holds the two women in a close medium composition. 수리영 leans in from the left with her nose near her mother's shoulder, while 강민숙 remains on the right near the entrance and her arm is left unobstructed for the impending downward move.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 수리영 leaning toward her mother in the middle-left of the frame, foreground; 강민숙 beside the entrance in the middle-right of the frame, midground.\n- KEY BACKGROUND ELEMENTS: 현관 (Occupied by mother and daughter) — The entrance-side boundary faces the camera obliquely behind 강민숙; used as Frames the pair's departure-side interaction and provides the spatial edge behind 강민숙; 거실의 작은 창 (Admitting sunlight) — Daylight passes through the small window into the interior; the exterior beyond is not emphasized; used as Provides the established daylight reaching into the room behind the entrance composition.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B02.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ],
          [
            "char:강민숙",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/668dbbe1-b767-4949-8ecd-040ab34d61bb.png"
          ]
        ],
        "asset_id": "15bbafc4-b47f-4534-88bd-d578c8f2b63c"
      },
      "S5sh6": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S6sh1": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S6sh1.png",
        "plate_path": null,
        "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: An open coastal road running alongside the sea in daylight, with the cyclist riding along the roadway.\n\nSHOT TEXT (authoritative, Korean): 해안가 도로 위, 귀에 이어폰을 꽂은 채 자전거 안장에 앉아 한쪽 무릎을 굽혀 페달을 밟아 내리는 중간 순간, 옷깃과 머리카락이 뒤로 흩날리는 수리영의 활기찬 측면\n\nCARRIED STATE (persist exactly): Su-ri-yeong continues riding her bicycle with earphones in her ears.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At torso height beside the bicycle, the camera tracks parallel at a stable medium lateral distance, preserving 수리영's energetic profile and the circular rhythm of her pedaling. She occupies the middle-left with one bent knee driving the pedal downward, while her bicycle, trailing hair, road, and coastal context extend toward the right without changing the established side axis.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 수리영 riding the bicycle in the middle-left of the frame, midground, moves toward road ahead.\n- KEY BACKGROUND ELEMENTS: 해안가 도로 (Used as 수리영's cycling route); used as Runs horizontally behind and beneath the rider to make the parallel tracking direction readable; 해안가 (Adjacent to the road); used as Maintains the explicitly coastal setting as secondary lateral context; 자전거 (In motion) — Its full side profile faces the lateral camera, with the wheels and pedal motion readable; used as Provides the moving base and scale reference beneath 수리영.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "no_plate": true,
        "ref_paths": [
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "d173edac-d7e1-40c4-a817-0d304837caf2"
      },
      "S7sh1": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S7sh5": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S8sh1": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S8sh1.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B01.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: A neon-lit commercial street beside the harbor at dusk, threading between taxis, vendors, and street-food stalls.\n\nSHOT TEXT (authoritative, Korean): 네온사인이 켜진 포구 번화가 골목을 향해 자전거 핸들을 꺾어 쥔 채 한쪽 페달에 체중을 싣고 있는 수리영\n\nCARRIED STATE (persist exactly): Su-ri-yeong continues traveling on the same bicycle through the port district.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At waist height about 2.5 meters ahead and offset toward 수리영's front side, the camera tracks backward and briefly steadies on the instant she turns the handlebar and loads one pedal. She and the bicycle occupy the lower-center in a front three-quarter view, while the neon signs, taxis, street stalls, and alley activity remain distributed behind her as readable but secondary layers.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: 수리영 steering her bicycle in the lower-center of the frame, midground, moves toward neon-lined alley route.\n- KEY BACKGROUND ELEMENTS: 네온사인 (On) — The illuminated sign faces carrying their displayed storefront content are visible to the camera behind the rider; used as Creates illuminated content planes behind 수리영 and establishes the commercial alley; 택시 (Present in the commercial district) — Their front and side faces appear at varied oblique angles along the street; used as Adds directional street scale and layered urban activity behind the bicycle route; 길거리 포장마차 (Operating among the street activity) — Their customer-facing sides open toward the alley and are seen obliquely behind 수리영; used as Forms irregular background edges along 수리영's route without blocking her bicycle; 번화가 골목 (Active with taxis, solicitation, and street stalls); used as Defines the navigable path into the port-side commercial district.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B01.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "ca508cfe-4012-459e-b6d2-ba951bbadb0f"
      },
      "S8sh2": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S8sh2.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B02.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the large supermarket on the main retail floor, beside the merchandise aisles where store employees are working.\n\nSHOT TEXT (authoritative, Korean): 마트 안, 한국인 여성 직원을 향해 고개를 갸웃한 채 정지해 있는 수리영\n\nCARRIED STATE (persist exactly): Su-ri-yeong’s bicycle remains parked outside the mart while she searches inside.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At 수리영’s eye level, the dolly-in settles into a medium two-shot angled across the shared eyeline, with 수리영 in the left foreground and the 한국인 여성 직원 offset in the right midground. 수리영’s halted head tilt becomes the only changed axis, while shelf lines behind them preserve the inward trajectory and leave lateral room for the subsequent pan.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 마트 진열대 (진열 중) — The aisle-facing sides recede diagonally behind the two women; used as Shelf lines create depth behind the conversation and preserve space for the impending pan; 마트 통로 (영업 중); used as The aisle provides the open screen side from which the male employee can subsequently approach.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B02.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "16dfe778-bf52-48e5-8d47-480a98ba8051"
      },
      "S9sh1": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S9sh1.png",
        "plate_path": null,
        "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: A dark coastal roadway at night, with the sea running alongside the route home.\n\nSHOT TEXT (authoritative, Korean): 어두워진 해안도로 위, 상체를 잔뜩 굽힌 채 한쪽 페달을 아래로 딛은 찰나의 수리영의 측면 실루엣, 옷자락이 뒤로 강하게 휘날리는\n\nCARRIED STATE (persist exactly): Su-ri-yeong continues riding the bicycle home along the coastal road.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: From rider-torso height, the camera tracks parallel in a tightened strict side profile, keeping 수리영 and the bicycle moving horizontally through the middle of the frame. Her bent torso and the pedal at its lowest point form a compressed diagonal, while enough road remains visible around the silhouette to retain speed and scale.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 수리영 in the middle-center of the frame, midground, moves toward road ahead.\n- KEY BACKGROUND ELEMENTS: 해안도로 (어두워진 상태); used as The road forms a lateral movement line beneath the bicycle and supplies environmental scale; 자전거 (주행 중) — Its side faces the camera in strict profile, with one pedal at the bottom of its rotation; used as The bicycle anchors the pedaling action and remains legible beneath the rider.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "no_plate": true,
        "ref_paths": [
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "1cf1be76-7bdc-4ea7-8fed-61fa23865b3f"
      },
      "S10sh3": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S10sh4": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S11sh3": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S12sh3": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S12sh3.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B03.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Behind the window curtain inside the daughter's bedroom, in the blood-soaked corner where the mother's body is found seated.\n\nSHOT TEXT (authoritative, Korean): 커튼 뒤, 목과 어깨에 살점이 뜯긴 거친 상처를 입고 피를 흘린 채 앉아 고개를 떨군 강민숙(민숙)의 끔찍한 모습\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): She is seated behind the curtain with her torso slumped forward and her head dropped toward her chest. Her limbs hang limp, with one hand loosely holding a crumpled photograph.\n\nCARRIED STATE (persist exactly): Min-sook’s dead body remains seated behind the curtain with her torso slumped forward and her head dropped toward her chest, her torn neck and shoulder bleeding amid the room’s bloodstains and bloody footprints. Her limbs hang limp, with one hand loosely holding a crumpled photograph, and her wrist still bears the circular mark.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: From just behind and beside 수리영’s prior position at shoulder height, the push-in stops on a tight view of 강민숙 seated behind the displaced curtain, keeping her lowered head and the torn neck, shoulder, and collarbone wounds together. Her body occupies most of the center and lower frame, while the curtain edge remains as a narrow foreground border rather than obscuring the injuries.\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: 강민숙 in the middle-center of the frame, midground.\n- KEY BACKGROUND ELEMENTS: 커튼 (젖혀짐) — One displaced edge faces the camera as a narrow foreground border beside 강민숙; used as Its drawn-aside edge frames the reveal and marks the concealed location; 방바닥 (혈흔이 흥건함); used as Visible beneath and around the seated body, grounding her collapsed posture; 수리영 방 (핏자국이 있음); used as Provides limited room context beyond the corpse without distracting from the wounds.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B03.png"
          ],
          [
            "char:강민숙",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/668dbbe1-b767-4949-8ecd-040ab34d61bb.png"
          ]
        ],
        "asset_id": "417e2ef9-c6a1-429c-9c18-65d88d1df6f2"
      },
      "S12sh8": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S12sh9": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S14sh3": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S14sh4": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S14sh8": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S15sh1": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S15sh1.png",
        "plate_path": null,
        "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: An outdoor bus-stop bench on the coast at night, positioned directly in front of the dark sea.\n\nSHOT TEXT (authoritative, Korean): 어두운 밤바다 앞 버스정류장 벤치에 멍한 표정으로 가만히 앉아 있는 수리영\n\nCARRIED STATE (persist exactly): Su-ri-yeong continues to have the photograph taken from Min-sook’s hand while repeatedly trying to contact her missing mother.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Hold a static wide view from seated eye level in front of the bench, placing 수리영 off-center while the night sea remains visible behind and to the side of her. Angle the bench and her body so her distant eyeline can travel naturally toward the sea without crossing into the lens, leaving broad negative space around her stillness.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: 수리영 in the middle-left of the frame, midground, looks toward sea; sea in the middle-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: bus stop bench (Occupied only by 수리영 in this shot) — The seat runs obliquely across the frame, exposing its front and one receding side; used as Supports 수리영 and establishes her isolated stillness; sea (Seen at night); used as Distant visual destination of 수리영's stare and primary negative space; bus stop structure (Present beside the coastal stop) — One side faces camera while its length recedes toward the sea; used as Environmental frame around the isolated bench.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "no_plate": true,
        "ref_paths": [
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "12e24f6e-e930-4d62-8edb-d19e6b893642"
      },
      "S15sh6": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S16sh1": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S16sh1.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L12B03.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The doorway and entry aisle inside a police office at night, opening onto the duty desks.\n\nSHOT TEXT (authoritative, Korean): 경찰서 사무실 안을 향해 한 발을 막 내디딘 mid-stride 자세로, 귀에 휴대전화를 바짝 댄 혜수의 굳은 얼굴\n\nCARRIED STATE (persist exactly): Hye-su continues carrying and using her phone to call Min-sook as she enters the office.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Just inside the office entrance at chest height, track backward as 혜수 plants her leading foot inside, holding briefly on her rigid three-quarter face and the phone pressed to her ear. Frame her in the middle foreground with the entrance behind her and leave open office space ahead for the later curve toward the duty desk.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 혜수 in the middle-center of the frame, midground, moves toward police office interior.\n- KEY BACKGROUND ELEMENTS: office entrance (Open for her entry) — The opening faces the camera behind 혜수 as she crosses inward; used as Rear spatial frame marking 혜수's entry into the office; police office interior (Occupied on duty by 김형사); used as Held as open depth in front of 혜수 for the continuing backward track; mobile phone (Calling 강민숙 without a response) — Its earpiece side is pressed to her ear while the screen faces away from camera; used as Held against 혜수's ear as evidence of the unanswered call.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L12B03.png"
          ],
          [
            "char:혜수",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/4af6ff57-5a8a-4168-98cd-a821386dd2d9.png"
          ]
        ],
        "asset_id": "e0ebab69-b969-4b40-acc5-5c8b7a95231e"
      },
      "S16sh4": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S17sh1": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S18sh2": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S18sh2.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B01.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the main bedroom of the rooftop dwelling, at the bed where the daughter has dozed while waiting through the night. Early daylight is beginning outside.\n\nSHOT TEXT (authoritative, Korean): 감았던 눈을 번쩍 뜬 채 굳은 표정으로 한 곳을 응시하는 수리영\n\nCARRIED STATE (persist exactly): Su-ri-yeong still possesses the photograph taken from Min-sook and remains in the lit rooftop room after waiting there all night.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At seated eye level beside the bed, finish the dolly-in on a tight three-quarter view of 수리영 as her eyes snap open and lock toward the unseen concern. Let her face occupy most of the frame while a small portion of the bed remains at the lower edge, holding the rigid stare before the camera eases back for her rise.\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: 수리영 isolated in awakening close view in the middle-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: bed (수리영 has been resting against it) — Only the near upper edge and the area beside her head remain visible; used as Lower-frame support showing where 수리영 had fallen asleep while waiting.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B01.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "7de5e7f0-004a-42e2-ba2e-7fd890dab160"
      },
      "S18sh8": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S18sh8.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B01.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the small bathroom, on the tiled wall reflected behind the daughter in the mirror.\n\nSHOT TEXT (authoritative, Korean): 거울 속 반사된 수리영의 등 뒤 욕실 타일 벽면 위로 선명하게 나타난 붉은색 원 형태\n\nCARRIED STATE (persist exactly): Su-ri-yeong now carries her doll-adorned backpack and still has the photograph taken from Min-sook. The red circle is visible only in the mirror on the bathroom wall at this moment.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Dolly in from directly behind 수리영 at shoulder height toward the bathroom mirror, keeping her physical back low and left while her reflected figure occupies the middle-left portion of the mirror. Give the reflected wall more space on the right so the vivid red circle remains cleanly separated from her reflection, and retain at least one mirror edge to establish the left-right-reversed reflected view.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 수리영 in the lower-left of the frame, foreground; reflected bathroom wall with red circle in the middle-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: bathroom mirror (The red circle is visible only within the reflected view at this moment) — The mirror reflects 수리영's front and the bathroom wall behind her, with the wall given more reflected area on the right; used as Primary reflective field containing 수리영 and the supernatural wall mark; bathroom tile wall (A vivid red circle has suddenly appeared on it in the mirror view) — Its reflected camera-visible face bears a clear red circular form positioned away from 수리영's reflected body; used as Separated reflected background plane carrying the sudden mark.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B01.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "a63613fb-df0d-4d9d-a8e7-c164fbe5bfe0"
      },
      "S18sh12": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S19sh1": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S19sh1.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B04.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the quiet supermarket in the early morning, among the merchandise aisles on the main sales floor.\n\nSHOT TEXT (authoritative, Korean): 이른 아침 한산한 마트 안, 진열대 사이에서 주위를 유심히 살피는 수리영의 전신\n\nCARRIED STATE (persist exactly): Su-ri-yeong’s bicycle remains parked outside the mart while she searches inside; she continues to have her backpack and Min-sook’s old photograph.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: From chest height five meters ahead in the aisle, track backward at 수리영's pace while maintaining a full-body view between the displays. Keep her slightly off-center with the aisle extending behind her, catching her mid-stride as her head and eyes search from one side to the other.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: 수리영 in the middle-center of the frame, midground, moves toward far end of the store aisle; far end of the store aisle in the upper-center of the frame, background.\n- KEY BACKGROUND ELEMENTS: 마트 진열대 (진열대 사이 통로를 이루고 있음) — Their aisle-facing sides flank the frame and recede toward the rear of the store; used as The displays form parallel side boundaries around 수리영 and guide the backward tracking path; 마트 통로 (이른 아침이라 한산함); used as Provides the long search axis and visible spatial context around the moving figure.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B04.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "4c573b7b-dbf9-4a95-bd2d-ec876bf4438c"
      },
      "S19sh4": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S19sh4.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B03.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Outside the supermarket, directly beneath the section of the building facade fitted with a surveillance camera.\n\nSHOT TEXT (authoritative, Korean): 마트 건물 밖, 고개를 뒤로 젖혀 건물 외벽의 CCTV 카메라를 올려다보는 수리영의 얼굴\n\nCARRIED STATE (persist exactly): Su-ri-yeong remains outside the mart with her bicycle parked there, still carrying her backpack and the photograph.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Continue the reveal tilt from slightly below 수리영's eye level, tightening within one meter so her upturned face occupies most of the lower and middle frame while the CCTV camera remains above along the same sightline. Use a restrained low angle and shallow focus that preserves the CCTV silhouette clearly enough to establish what she has found.\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: 수리영 in the middle-left of the frame, foreground, looks toward exterior CCTV camera; exterior CCTV camera in the upper-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: 마트 외벽 CCTV 카메라 (마트 외벽에 설치되어 있음) — Its lens-bearing front is angled toward the area outside the store and remains visible above 수리영; used as The upper-frame visual target completing 수리영's upward eyeline; 마트 건물 외벽 (CCTV가 설치되어 있음) — The exterior face carrying the CCTV is visible behind and above her; used as Anchors the CCTV physically above 수리영 without widening away from her face.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B03.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "adc7810b-b519-403e-b1a6-9a52897267d0"
      },
      "S20sh1": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S20sh1.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L13B01.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the supermarket's administrative CCTV monitoring room, gathered closely around the surveillance monitors.\n\nSHOT TEXT (authoritative, Korean): 마트 총무과 안, 어두운 CCTV 모니터 화면을 향해 상체를 바짝 기울인 혜수와 그 뒤에 선 수리영\n\nCARRIED STATE (persist exactly): Su-ri-yeong continues to carry her backpack and the photograph taken from Min-sook while watching the CCTV review.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Begin at chest height behind and slightly beside 혜수, then push forward along the shared monitor axis while retaining 수리영 farther back in the same frame. 혜수 leans into the left foreground and partially frames the dark CCTV display, while 수리영 remains fully separated in the rear, tense and fixed on the screen.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 혜수 in the middle-left of the frame, foreground, looks toward CCTV monitor; 수리영 in the middle-right of the frame, background, looks toward CCTV monitor; CCTV monitor in the upper-center of the frame, midground.\n- KEY BACKGROUND ELEMENTS: CCTV 모니터 화면 (CCTV 영상을 재생 중이며 해당 구간만 유독 어두움) — The active front display faces away from the characters and obliquely toward the camera, showing the unusually dark surveillance section; used as Central visual destination of the dolly-in and the common target of both characters; 총무과 작업 책상 (CCTV 확인 작업에 사용 중) — Its monitor-facing side recedes toward the center of frame; used as Supports the monitor and creates foreground layering beneath 혜수's leaning torso.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L13B01.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ],
          [
            "char:혜수",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/4af6ff57-5a8a-4168-98cd-a821386dd2d9.png"
          ]
        ],
        "asset_id": "379a2abb-c2f8-4965-b23d-8e0ba4c32f7f"
      },
      "S20sh4": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S21sh3": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S21sh3.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L12B03.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the police office at the detective's vacant desk, covered with enlarged crime-scene photographs.\n\nSHOT TEXT (authoritative, Korean): 혜수의 빈 책상 앞에 앉아 어지럽게 널린 사건 현장 사진들을 내려다보는 수리영\n\nCARRIED STATE (persist exactly): The enlarged murder-scene photographs remain scattered across Hye-su’s desk. Su-ri-yeong continues carrying her backpack and Min-sook’s old photograph.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: From the high three-quarter position beside 혜수's desk, continue the dolly-in until the camera hovers just above 수리영's seated shoulder. Arrange her bent upper body in the lower side of frame and spread the crime-scene photographs across the central desk area, letting her downward gaze lead directly into their disturbing details.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 수리영 in the lower-right of the frame, foreground, looks toward scattered crime-scene photographs; scattered crime-scene photographs in the middle-center of the frame, midground.\n- KEY BACKGROUND ELEMENTS: 사건 현장 확대 사진들 (혜수의 책상 위에 어지럽게 널려 있음) — Their image-bearing fronts face upward toward the camera, showing the photographed neck, shoulder, and facial injuries; used as Primary downward focal field beneath 수리영's gaze; 혜수의 책상 (주인이 자리를 비운 상태이며 사건 사진들이 놓여 있음) — Its top surface faces the high three-quarter camera position; used as Creates the high-angle plane across which the photographs and 수리영's hands are organized; 경찰서 사무실 (형사들이 회의로 빠져나가 수리영만 남아 있음); used as Provides negative space beyond the desk to emphasize that 수리영 has been left alone.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L12B03.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "d3afc3c4-c7ac-41c2-877f-014c41f0bf2c"
      },
      "S21sh5": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S21sh8": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S22sh1": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S22sh1.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L12B01.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Outside the police station at the bicycle parking area immediately in front of the building.\n\nSHOT TEXT (authoritative, Korean): 경찰서 건물 앞, 자전거 안장에 앉은 채 한쪽 무릎을 굽혀 페달을 힘껏 밟아 내리는 중간 찰나, 다급한 표정의 수리영의 측면\n\nCARRIED STATE (persist exactly): Su-ri-yeong rides away with the coordinate note folded in her pocket, while carrying her backpack and Min-sook’s old photograph.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At waist height and perpendicular to the bicycle, hold the inherited side axis on the exact launch instant before the lateral track begins. Frame 수리영 and the bicycle in a full-body side view as one bent knee rises and the opposite foot drives its pedal down, her urgent face angled toward the direction of travel.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: 수리영 in the middle-center of the frame, midground, moves toward right edge of frame; police station building in the upper-center of the frame, background.\n- KEY BACKGROUND ELEMENTS: 자전거 (정지 상태에서 막 앞으로 움직이기 시작함) — The bicycle's full side faces the camera, with the crank and descending pedal visible; used as Carries 수리영's urgent launch and supplies a clear side-on motion profile; 경찰서 건물 (수리영의 출발 배경으로 보임) — The building's front exterior faces the camera behind 수리영; used as Establishes the departure point without competing with the cycling action.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L12B01.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "5185526d-6e22-429a-8f61-6b231379b23a"
      },
      "S23sh2": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S24sh2": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S24sh2.png",
        "plate_path": null,
        "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: An exposed coastal road under storm clouds, lashed by a heavy downpour as it follows the shoreline.\n\nSHOT TEXT (authoritative, Korean): 세차게 쏟아지는 소나기 속에서 흠뻑 젖은 채, 한쪽 발로 자전거 페달을 강하게 내리누르는 중간 동작으로 몸이 앞으로 쏠린 수리영의 전신\n\nCARRIED STATE (persist exactly): Su-ri-yeong rides through the rain with several printed maps inside her backpack, along with Min-sook’s old photograph and the coordinate note.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Track laterally alongside 수리영 at a low chest-to-waist height, holding her full body and bicycle in a wide lateral three-quarter composition as she drives toward frame right. Her forward-pitched torso occupies the center-left while the forcefully lowered pedal and weighted foot remain clear in the lower center, with the coastal surroundings receding behind her.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: 수리영 in the middle-center of the frame, midground, moves toward frame-right coastal route.\n- KEY BACKGROUND ELEMENTS: 자전거 (전진 중) — Its side and frontward direction are visible as it travels toward frame right; used as Carries 수리영 through the frame and provides the lateral tracking axis; 해안가 (소나기 속); used as Provides environmental depth behind the moving rider; 먹구름 (잔뜩 낀 상태); used as Forms the upper background and establishes the storm; 세찬 비 (세차게 내리는 중); used as Cuts across 수리영 and the bicycle as visible weather texture.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "no_plate": true,
        "ref_paths": [
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "73592123-00b3-4422-93e8-a8e0c620becf"
      },
      "S25sh2": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S25sh2.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B02.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The ransacked living room inside the rooftop dwelling, littered with disturbed household goods and overturned dining chairs. Dusk enters through the open window.\n\nSHOT TEXT (authoritative, Korean): 온갖 가재도구가 쏟아져 엉망이 된 거실 한가운데 선 수리영의 충격받은 상체\n\nCARRIED STATE (persist exactly): The rooftop-room interior remains ransacked, with footprints, scattered household goods, an open window, and overturned dining chairs. Su-ri-yeong still carries the backpack containing her printed maps.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Begin the reaction stage at chest height directly across the disrupted living room, framing 수리영 from the waist up in a slightly off-center medium composition. Keep the fallen chairs and scattered household items around her while her compressed breathing and tense glance toward the open bedroom doorway initiate the coming pan.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 흩어진 가재도구 (거실에 엉망으로 널브러진 상태); used as Surrounds 수리영 with evidence that the room has been searched; 식탁 의자들 (쓰러진 상태) — Their fallen sides face the camera at differing angles; used as Creates diagonal interruptions around 수리영's lower body; 거실 창 (열린 상태) — The open aperture is visible; the exterior beyond is not emphasized; used as Holds an open void behind and beside 수리영; 방문 (열린 상태) — The open doorway faces the camera obliquely from the living room; used as Receives 수리영's glance and establishes the axis for the next shot.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B02.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "15506f4d-27a1-4f75-ba15-7dbdaedda28f"
      },
      "S25sh3": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S25sh5": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S26sh2": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S26sh2.png",
        "plate_path": null,
        "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: On a rock at the edge of an empty harbor, surrounded by dense fog rolling in from the sea.\n\nSHOT TEXT (authoritative, Korean): 수리영의 손안에서 혜수의 이름과 부재중 전화 알림이 떠오른 휴대전화 액정 화면 클로즈업\n\nCARRIED STATE (persist exactly): Su-ri-yeong continues carrying the bloodstained photograph and her backpack containing the printed maps; her phone shows multiple missed calls from Hye-su.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Hold at 수리영's hand height beside her, angled squarely enough for the phone display to remain legible while the device occupies less than two-fifths of the close frame. Her gripping fingers and part of her seated body provide scale around the screen showing 혜수's name and repeated missed-call notifications.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 휴대전화 화면 (부재중 전화 알림이 표시된 상태) — The active front display faces the camera and shows 혜수's name with multiple missed-call notifications; used as Primary information surface in the lower-middle frame; 갯바위 (수리영이 앉아 있는 상태); used as Provides a grounded edge of environmental context behind the hand; 포구의 안개 (자욱한 상태); used as Soft background context retained beyond the phone.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "no_plate": true,
        "ref_paths": [
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "84b01b23-e35b-4af4-a262-072330ad2908"
      },
      "S26sh5": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S26sh5.png",
        "plate_path": null,
        "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: At the fogbound harbor's mooring edge beside the newly arrived fishing boat, where its line is being secured.\n\nSHOT TEXT (authoritative, Korean): 밧줄을 쥐고 선 인우를 바짝 올려다보는 수리영의 결연한 얼굴\n\nCARRIED STATE (persist exactly): Su-ri-yeong still has the bloodstained photograph and the map-filled backpack as she asks In-woo for passage.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: From chest height close to 인우's side, finish the dolly on 수리영's upturned face in a tight, slightly high-angle composition. Her face occupies most of the center-left while only 인우's rope-gripping hand and forearm remain at the right edge as immediate spatial context.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 닷줄 (인우가 쥔 상태); used as Appears only at the frame edge to establish 인우's task and proximity; 포구의 안개 (자욱한 상태); used as Provides restrained harbor context behind the confrontation; 배 (포구에 도착한 상태) — Only the side nearest the two characters is visible behind them; used as Remains a partial background form beside 인우.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "no_plate": true,
        "ref_paths": [
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ]
        ],
        "asset_id": "b8e108c7-f639-48f2-87ea-6903a18c35c2"
      },
      "S27sh1": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S28sh1": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S28sh5": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S28sh5.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L19B02.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: On the open deck of the small fishing boat at sunset, where the old photograph is held out between the two passengers.\n\nSHOT TEXT (authoritative, Korean): 눈앞의 사진을 보고 동공이 크게 확장된 채 굳어있는 인우의 당황한 얼굴 클로즈업\n\nCARRIED STATE (persist exactly): The bloodstained old photograph remains in Su-ri-yeong’s possession and is held out for In-woo to inspect; her printed maps remain with her in the backpack.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: End the push at 인우's eye level in a tight face close-up, favoring a slight three-quarter angle rather than a flat frontal portrait. His widened pupils hold near the center while a narrow, softly focused edge of the presented photograph remains low in frame to preserve the cause of his alarm.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 사진 (수리영이 내민 상태) — A small portion of its image-bearing front angles upward toward 인우; the pictured restaurant is only partially readable; used as Remains at the lower edge as the visible trigger for 인우's reaction; 갑판 (항해 중인 어선의 갑판) — The deck recedes behind 인우 on the vessel's axis; used as Keeps the setting legible without competing with the face.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L19B02.png"
          ],
          [
            "char:인우",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/4dc39f0d-3845-479f-a87a-46b9aeb0ba87.png"
          ]
        ],
        "asset_id": "a0cde503-49af-4303-8e94-84cb1ceafaa6"
      },
      "S28sh10": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S28sh10.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L19B01.png",
        "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the fishing boat's compact wheelhouse at the helm, where the man reaches for the controls and the woman restrains his arm.\n\nSHOT TEXT (authoritative, Korean): 조타기에 손을 뻗은 인우의 팔뚝을 수리영의 양손이 강하게 꽉 움켜쥐어 피부가 눌려 있는 상태의 클로즈업\n\nCARRIED STATE (persist exactly): Su-ri-yeong’s backpack, printed maps, and bloodstained photograph remain aboard as she grips In-woo’s arm to stop him from turning the boat around.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Lower to forearm height beside the helm and finish the dolly on the point of contact, isolating 인우's reaching forearm and 수리영's two compressing hands as an insert. The helm remains in the upper-right background as the physical destination of his reach, while the locked grip crosses the lower center without enlarging any nearby object unnaturally.\n- FRAMING SCALE: insert close-up on a detail\n- FRAME LAYOUT: 인우 in the middle-right of the frame, foreground, reaches for helm; 수리영 in the middle-left of the frame, foreground, reaches for 인우's forearm; helm in the upper-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: 조타기 (인우가 손을 뻗는 상태) — Its operating side faces 인우 and is visible in the upper-right background; used as Provides the destination of 인우's interrupted reach in the background; 조타실 내부 (두 인물이 들어온 상태) — The interior surfaces recede behind the interlocked arms and helm; used as Confines the physical struggle within the vessel interior.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.",
        "skipped_reason": null,
        "error": null,
        "ref_paths": [
          [
            "plate",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L19B01.png"
          ],
          [
            "char:수리영",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/5228291d-fa9a-4943-87c3-4b9efa0406db.png"
          ],
          [
            "char:인우",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/reference/4dc39f0d-3845-479f-a87a-46b9aeb0ba87.png"
          ]
        ],
        "asset_id": "b91a544e-27a8-4b90-ae16-98906ae78f35"
      },
      "S29sh3": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S29sh6": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S29sh9": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S30sh2": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      }
    },
    "map_conti": {},
    "conti_pack": "5.202607222353",
    "lane_conti": {
      "S4sh1": {
        "lane": "structure_plate",
        "group_id": "bg_rooftop_residence",
        "segment_id": "SEG_01",
        "status": "ab_select_bypass",
        "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/background_chain/seed_bg_rooftop_residence_sel.png",
        "seed_asset_id": "f32917dc-6b3c-4dfb-b8de-0a07e04327ac",
        "seed_status": "ok",
        "bg_source": "plate",
        "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L03B02.png",
        "bg_reason": "",
        "bypass_reason": "bg_only"
      },
      "S10sh3": {
        "lane": "structure_plate",
        "group_id": "bg_rooftop_residence",
        "segment_id": "SEG_02",
        "status": "ab_select_bypass",
        "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/background_chain/seed_bg_rooftop_residence_sel.png",
        "seed_asset_id": "f32917dc-6b3c-4dfb-b8de-0a07e04327ac",
        "seed_status": "ok",
        "bg_source": "plate",
        "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L03B01.png",
        "bg_reason": "",
        "bypass_reason": "bg_only"
      },
      "S10sh4": {
        "lane": "structure_plate",
        "group_id": "bg_rooftop_residence",
        "segment_id": "SEG_02",
        "status": "ab_select_bypass",
        "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/background_chain/seed_bg_rooftop_residence_sel.png",
        "seed_asset_id": "f32917dc-6b3c-4dfb-b8de-0a07e04327ac",
        "seed_status": "ok",
        "bg_source": "plate",
        "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L03B01.png",
        "bg_reason": "",
        "bypass_reason": "bg_only"
      },
      "S13sh2": {
        "lane": "map_marker",
        "group_id": "bg_rooftop_residence",
        "segment_id": "SEG_03",
        "sketch_attempts": 1,
        "status": "ok",
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/lane_sketch_S13sh2.png",
        "base_map_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/background_chain/canon_bg_rooftop_residence_map.png",
        "base_map_asset_id": "8425b16e-3519-4d9e-acd9-ceab87c5d9d4",
        "geometry": {
          "camera": {
            "look_target": {
              "x": 0.53,
              "y": 0.72
            },
            "origin": {
              "x": 0.73,
              "y": 0.86
            }
          },
          "entity_placements": [
            {
              "slot": "E1",
              "subject_en": "dazed standing person",
              "x": 0.5,
              "y": 0.68
            },
            {
              "slot": "E2",
              "subject_en": "running middle-aged policewoman",
              "x": 0.59,
              "y": 0.76
            },
            {
              "slot": "E3",
              "subject_en": "parked police car with flashing lights",
              "x": 0.64,
              "y": 0.71
            }
          ],
          "rationale_ko": "C2 후면 지상 안뜰의 S1 계단 하단 가까이에 멍하니 선 인물을 두고, 경찰차는 그 뒤쪽에 배치했다. 여경은 경찰차에서 계단 방향으로 달려가는 접근선상 중경에 놓아 한 발이 들린 전신 동작을 담는다. 카메라는 같은 접근선 뒤쪽에서 후진 추적하며 여경을 중경, 멈춰 선 인물과 경찰차를 배경에 함께 유지한다."
        },
        "geometry_attempts": 1,
        "leakage": {
          "has_marker_leakage": false,
          "details_ko": "도면 기호나 텍스트 누출이 발견되지 않았습니다. 지시된 카메라 뷰를 따른 스케치입니다."
        },
        "prompt": "Draw a single CAMERA-VIEW storyboard frame (16:9) of the scene staged\non the attached TOP-DOWN SITE PLAN, seen from the camera position\ngiven in the STAGING GEOMETRY data below.\n\nJurisdiction of sources — follow all three, they do not conflict:\n- The attached SITE PLAN is the SOT for what exists on the site and\n  how its zones and landmarks are arranged relative to each other.\n- The STAGING GEOMETRY data below is the SOT for XY POSITIONS and\n  horizontal heading ONLY: where each subject stands on that plan,\n  where the camera stands, and which way it looks. Distances,\n  directions and relative depths between subjects come from these\n  coordinates. Subjects outside the camera's horizontal field of\n  view are out of frame.\n- The CAMERA DIRECTION text below (when present) is the SOT for the\n  VERTICAL angle, elevation, tilt and framing (eye-level, high angle,\n  overhead crane, low angle, ...). If it asks for a high or overhead\n  angle, draw that angle — the site plan being top-down does NOT mean\n  the frame must be eye-level.\n\nSTYLE — LIGHT STORYBOARD FRAME: thin uniform dark outlines on plain\npaper. No shading, no hatching, no texture, no facial features beyond\na minimal head shape, no costume detail. Human figures are correctly\nproportioned full-body outlines in their canonical poses. Environment\nis reduced to a few placement lines (ground line, key landmark\nsilhouettes) — just enough to read positions and depth.\n\nSTAGING GEOMETRY — PLANNING DATA ONLY, NEVER RENDER IT: the lines\nbelow are normalized map coordinates on the attached site plan\n(x runs left→right 0..1, y runs top→bottom 0..1). Use them solely to\nplace the camera and subjects. Do NOT draw any of this data in the\nimage — no numbers, no coordinates, no labels, no arrows, no cones,\nno dots, no diagram symbols of any kind.\n- the camera stands at (x=0.73, y=0.86) and looks toward (x=0.53, y=0.72); subjects outside the camera's horizontal field of view are out of frame\n- dazed standing person stands at (x=0.50, y=0.68)\n- running middle-aged policewoman stands at (x=0.59, y=0.76)\n- parked police car with flashing lights stands at (x=0.64, y=0.71)\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): At eye height below the stairs, the camera tracks backward along 혜수’s approach line in a wide full-body composition, holding 수리영 near the police car in the background and 혜수 in the advancing midground. The frame is timed to 혜수’s lifted foot, while 수리영 remains fixed and unfocused so only their relative positions change.\n\nTHE LOCATION: 다세대 빌라 마당 및 옥탑방 외부 계단\n\nSHOT TEXT (authoritative, Korean): 경광등이 번쩍이는 경찰차 앞 초점을 잃고 멍하니 선 수리영과, 그를 향해 달려오다 한 발이 땅에서 떨어진 mid-action 순간의 혜수의 전신\n\nCRITICAL — THE SITE PLAN IS A STAGING REFERENCE, NOT CONTENT: do NOT\ndraw the plan itself, and do NOT draw any diagram elements in the\nframe — no circles, dots, wedges, cones, arrows, callouts, codes or\nany other overlay symbols. The output is a clean storyboard drawing\nof the scene as seen by the camera only.\n\nNo text, no letters, no numbers, no captions anywhere in the image.",
        "asset_id": "4ac1a815-3633-4919-b8d7-570f3a8a3859"
      },
      "S15sh5": {
        "lane": "map_marker",
        "group_id": "bg_coastal_bus_stop",
        "segment_id": "SEG_02",
        "sketch_attempts": 1,
        "status": "ok",
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/lane_sketch_S15sh5.png",
        "base_map_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/background_chain/canon_bg_coastal_bus_stop_map.png",
        "base_map_asset_id": "f9fa1155-95b6-45c6-b9aa-e2cbdb5cdb54",
        "geometry": {
          "camera": {
            "look_target": {
              "x": 0.46,
              "y": 0.71
            },
            "origin": {
              "x": 0.57,
              "y": 0.58
            }
          },
          "entity_placements": [
            {
              "slot": "E1",
              "subject_en": "receding young woman",
              "x": 0.45,
              "y": 0.73
            },
            {
              "slot": "E2",
              "subject_en": "calling woman with cupped hands",
              "x": 0.52,
              "y": 0.62
            }
          ],
          "rationale_ko": "혜수는 B1 해안 버스정류장 남서쪽에 두고, 수리영은 A1 해안 접근 구역의 열린 출발 경로를 따라 더 남서쪽으로 멀어지게 배치했다. 카메라는 혜수 옆의 가까운 위치에서 같은 대각선 방향을 바라보아 혜수를 좌측 전경의 상체 중심으로 잡으면서, 어깨 너머로 작아지는 수리영의 퇴장 방향이 이어지도록 했다."
        },
        "geometry_attempts": 1,
        "leakage": {
          "has_marker_leakage": false,
          "details_ko": "다이어그램 기호나 텍스트가 노출되지 않은 자연스러운 스케치입니다."
        },
        "prompt": "Draw a single CAMERA-VIEW storyboard frame (16:9) of the scene staged\non the attached TOP-DOWN SITE PLAN, seen from the camera position\ngiven in the STAGING GEOMETRY data below.\n\nJurisdiction of sources — follow all three, they do not conflict:\n- The attached SITE PLAN is the SOT for what exists on the site and\n  how its zones and landmarks are arranged relative to each other.\n- The STAGING GEOMETRY data below is the SOT for XY POSITIONS and\n  horizontal heading ONLY: where each subject stands on that plan,\n  where the camera stands, and which way it looks. Distances,\n  directions and relative depths between subjects come from these\n  coordinates. Subjects outside the camera's horizontal field of\n  view are out of frame.\n- The CAMERA DIRECTION text below (when present) is the SOT for the\n  VERTICAL angle, elevation, tilt and framing (eye-level, high angle,\n  overhead crane, low angle, ...). If it asks for a high or overhead\n  angle, draw that angle — the site plan being top-down does NOT mean\n  the frame must be eye-level.\n\nSTYLE — LIGHT STORYBOARD FRAME: thin uniform dark outlines on plain\npaper. No shading, no hatching, no texture, no facial features beyond\na minimal head shape, no costume detail. Human figures are correctly\nproportioned full-body outlines in their canonical poses. Environment\nis reduced to a few placement lines (ground line, key landmark\nsilhouettes) — just enough to read positions and depth.\n\nSTAGING GEOMETRY — PLANNING DATA ONLY, NEVER RENDER IT: the lines\nbelow are normalized map coordinates on the attached site plan\n(x runs left→right 0..1, y runs top→bottom 0..1). Use them solely to\nplace the camera and subjects. Do NOT draw any of this data in the\nimage — no numbers, no coordinates, no labels, no arrows, no cones,\nno dots, no diagram symbols of any kind.\n- the camera stands at (x=0.57, y=0.58) and looks toward (x=0.46, y=0.71); subjects outside the camera's horizontal field of view are out of frame\n- receding young woman stands at (x=0.45, y=0.73)\n- calling woman with cupped hands stands at (x=0.52, y=0.62)\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): Track beside 혜수 at chest height and tighten to her upper body, holding her in the left foreground as her cupped hands reach her mouth. Keep 수리영 small and receding along the same diagonal beyond 혜수's shoulder, so the departing direction remains unmistakable without widening away from 혜수's call.\n\nTHE LOCATION: 해안가 버스정류장 일대\n\nSHOT TEXT (authoritative, Korean): 멀어지는 수리영의 등을 향해 양손을 입가에 모으고 소리치는 혜수의 상체\n\nCRITICAL — THE SITE PLAN IS A STAGING REFERENCE, NOT CONTENT: do NOT\ndraw the plan itself, and do NOT draw any diagram elements in the\nframe — no circles, dots, wedges, cones, arrows, callouts, codes or\nany other overlay symbols. The output is a clean storyboard drawing\nof the scene as seen by the camera only.\n\nNo text, no letters, no numbers, no captions anywhere in the image.",
        "asset_id": "60a36926-148b-407b-a275-b8f96c506cda"
      },
      "S15sh6": {
        "lane": "structure_plate",
        "group_id": "bg_coastal_bus_stop",
        "segment_id": "SEG_03",
        "status": "ab_select_bypass",
        "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/background_chain/seed_bg_coastal_bus_stop_sel.png",
        "seed_asset_id": "7e636055-57cd-42ff-a58c-3fe738ea7c06",
        "seed_status": "ok",
        "bg_source": "seed",
        "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/background_chain/seed_bg_coastal_bus_stop_sel.png",
        "bg_reason": "",
        "bypass_reason": "prev"
      },
      "S17sh1": {
        "lane": "structure_plate",
        "group_id": "bg_rooftop_residence",
        "segment_id": "SEG_02",
        "status": "ab_select_bypass",
        "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/background_chain/seed_bg_rooftop_residence_sel.png",
        "seed_asset_id": "f32917dc-6b3c-4dfb-b8de-0a07e04327ac",
        "seed_status": "ok",
        "bg_source": "plate",
        "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L03B01.png",
        "bg_reason": "",
        "bypass_reason": "bg_only"
      },
      "S28sh10": {
        "lane": "structure_plate",
        "group_id": "bg_small_fishing_boat",
        "segment_id": "SEG_03",
        "status": "ab_select_ready",
        "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/background_chain/seed_bg_small_fishing_boat_sel.png",
        "seed_asset_id": "f2a3ff57-072f-4a32-bc42-e7e3dcebd19f",
        "seed_status": "ok",
        "bg_source": "plate",
        "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L19B01.png",
        "bg_reason": "",
        "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/images/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/conti/conti_S28sh10.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L19B01.png"
      }
    },
    "plate_authority": {
      "S5sh5": {
        "assigned": "L05B02",
        "chosen": "L05B02",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B02.png",
        "record": {
          "candidates": {
            "A": "L05B01",
            "B": "L05B02",
            "C": "L05B03",
            "D": "L05B04",
            "E": "L05B05",
            "F": "L05B06"
          },
          "assigned": "L05B02",
          "choice": "Candidate B",
          "confident": true,
          "reason_ko": "\"현관에 선 채\"라는 지문이 있으므로, 출입문과 신발을 벗는 현관 공간이 명확히 보이는 현재 할당된 이미지가 적합합니다.",
          "kept": "L05B02"
        },
        "fingerprint": "d6e7ba366c755b4b"
      },
      "S8sh1": {
        "assigned": "L09B01",
        "chosen": "L09B01",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B01.png",
        "record": {
          "candidates": {
            "A": "L09B01",
            "B": "L09B02",
            "C": "L09B03",
            "D": "L09B04"
          },
          "assigned": "L09B01",
          "choice": "Candidate A",
          "confident": true,
          "reason_ko": "지문에서 '네온사인이 켜진 포구 번화가 골목'을 명시하고 있으므로, 식당과 네온 간판이 늘어선 야외 번화가 골목을 보여주는 후보 A가 적합합니다.",
          "kept": "L09B01"
        },
        "fingerprint": "6f441e790a416ff9"
      },
      "S8sh2": {
        "assigned": "L09B02",
        "chosen": "L09B02",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B02.png",
        "record": {
          "candidates": {
            "A": "L09B01",
            "B": "L09B02",
            "C": "L09B03",
            "D": "L09B04"
          },
          "assigned": "L09B02",
          "choice": "Candidate B",
          "confident": true,
          "reason_ko": "\"마트 안\"이라는 지문에 부합하는 실내 공간이며, 직원과 상호작용하기에 자연스러운 계산대 구역이 포함되어 있으므로 기존 할당을 유지합니다.",
          "kept": "L09B02"
        },
        "fingerprint": "00c0838b890b2cb0"
      },
      "S12sh3": {
        "assigned": "L05B05",
        "chosen": "L05B05",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B03.png",
        "record": {
          "candidates": {
            "A": "L05B01",
            "B": "L05B02",
            "C": "L05B03",
            "D": "L05B04",
            "E": "L05B05",
            "F": "L05B06"
          },
          "assigned": "L05B05",
          "choice": "Candidate E",
          "confident": true,
          "reason_ko": "지문에서 '커튼 뒤'라는 공간적 배경을 명시하고 있으므로, 커튼과 창문이 가장 잘 보이고 그 주변 공간을 비추는 현재 배정된 이미지가 적합합니다.",
          "kept": "L05B05"
        },
        "fingerprint": "129fbb1363926792"
      },
      "S16sh1": {
        "assigned": "L12B03",
        "chosen": "L12B03",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L12B03.png",
        "record": {
          "candidates": {
            "A": "L12B01",
            "B": "L12B02",
            "C": "L12B03"
          },
          "assigned": "L12B03",
          "choice": "Candidate C",
          "confident": true,
          "reason_ko": "지문에서 '경찰서 사무실 안을 향해'라고 명시되어 있으므로, 경찰서 외부가 아닌 내부 사무실 공간을 보여주는 후보가 적합합니다. 후보 B와 C는 동일한 내부 이미지이며, 현재 할당된 C를 유지합니다.",
          "kept": "L12B03"
        },
        "fingerprint": "6a6c2cd6415c5055"
      },
      "S18sh2": {
        "assigned": "L05B01",
        "chosen": "L05B01",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B01.png",
        "record": {
          "candidates": {
            "A": "L05B01",
            "B": "L05B02",
            "C": "L05B03",
            "D": "L05B04",
            "E": "L05B05",
            "F": "L05B06"
          },
          "assigned": "L05B01",
          "choice": "Candidate A",
          "confident": false,
          "reason_ko": "지문에서 인물이 눈을 뜨고 한 곳을 응시한다는 행동만 묘사되어 있을 뿐, 침대나 거울 등 특정 서브공간을 특정할 수 있는 단서가 전혀 없습니다. 따라서 공간을 변경할 명확한 근거가 없으므로 현재 배정된 후보를 유지합니다.",
          "kept": "L05B01"
        },
        "fingerprint": "f18f55cf85664a74"
      },
      "S18sh8": {
        "assigned": "L05B01",
        "chosen": "L05B01",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B01.png",
        "record": {
          "candidates": {
            "A": "L05B01",
            "B": "L05B02",
            "C": "L05B03",
            "D": "L05B04",
            "E": "L05B05",
            "F": "L05B06"
          },
          "assigned": "L05B01",
          "choice": "Candidate A",
          "confident": true,
          "reason_ko": "욕실 타일 벽면 위로 나타난 붉은색 원 형태와 거울이라는 명확한 언급이 있으므로 욕실 내부가 보이는 Candidate A가 적합합니다.",
          "kept": "L05B01"
        },
        "fingerprint": "fb1804b2f6865ed2"
      },
      "S19sh1": {
        "assigned": "L09B04",
        "chosen": "L09B04",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B04.png",
        "record": {
          "candidates": {
            "A": "L09B01",
            "B": "L09B02",
            "C": "L09B03",
            "D": "L09B04"
          },
          "assigned": "L09B04",
          "choice": "Candidate D",
          "confident": true,
          "reason_ko": "\"마트 안, 진열대 사이\"라는 묘사에 정확히 부합하는 실내 매대 통로 공간입니다.",
          "kept": "L09B04"
        },
        "fingerprint": "04e5a957e04c5959"
      },
      "S19sh4": {
        "assigned": "L09B03",
        "chosen": "L09B03",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L09B03.png",
        "record": {
          "candidates": {
            "A": "L09B01",
            "B": "L09B02",
            "C": "L09B03",
            "D": "L09B04"
          },
          "assigned": "L09B03",
          "choice": "Candidate C",
          "confident": true,
          "reason_ko": "\"건물 외벽의 CCTV 카메라\"라는 지문에 따라, 외벽에 설치된 CCTV가 명확하게 보이는 공간이 필요함.",
          "kept": "L09B03"
        },
        "fingerprint": "82feb515fe0dd41b"
      },
      "S21sh3": {
        "assigned": "L12B02",
        "chosen": "L12B02",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L12B03.png",
        "record": {
          "candidates": {
            "A": "L12B01",
            "B": "L12B02",
            "C": "L12B03"
          },
          "assigned": "L12B02",
          "choice": "Candidate B",
          "confident": true,
          "reason_ko": "\"혜수의 빈 책상 앞에 앉아\"라는 지문을 통해 경찰서 내부의 사무 공간(책상)이 필요함을 알 수 있으며, 현재 할당된 Candidate B가 이를 잘 보여줍니다.",
          "kept": "L12B02"
        },
        "fingerprint": "122d41eb32ccb184"
      },
      "S22sh1": {
        "assigned": "L12B01",
        "chosen": "L12B01",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L12B01.png",
        "record": {
          "candidates": {
            "A": "L12B01",
            "B": "L12B02",
            "C": "L12B03"
          },
          "assigned": "L12B01",
          "choice": "Candidate A",
          "confident": true,
          "reason_ko": "샷 텍스트에서 '경찰서 건물 앞', '자전거 안장'이 명시되어 있으므로 자전거가 세워져 있는 경찰서 건물 외부 공간을 보여주는 후보 A가 적합합니다.",
          "kept": "L12B01"
        },
        "fingerprint": "79d642f9e2102ad7"
      },
      "S25sh2": {
        "assigned": "L05B04",
        "chosen": "L05B04",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L05B02.png",
        "record": {
          "candidates": {
            "A": "L05B01",
            "B": "L05B02",
            "C": "L05B03",
            "D": "L05B04",
            "E": "L05B05",
            "F": "L05B06"
          },
          "assigned": "L05B04",
          "choice": "Candidate A",
          "confident": true,
          "reason_ko": "\"엉망이 된 거실\"이라는 지문에 따라 가재도구와 종이들이 어질러져 있는 거실 공간이 필요하므로, 테이블 위에 물건들이 흩어져 있는 Candidate A가 가장 적합합니다.",
          "kept": "L05B04"
        },
        "fingerprint": "2062c611dba1e8a7"
      },
      "S28sh5": {
        "assigned": "L19B02",
        "chosen": "L19B02",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L19B02.png",
        "record": {
          "candidates": {
            "A": "L19B01",
            "B": "L19B02",
            "C": "L19B03"
          },
          "assigned": "L19B02",
          "choice": "Candidate B",
          "confident": true,
          "reason_ko": "지문에서 인우가 '눈앞의 사진'을 보고 당황한다고 명시되어 있으며, Candidate B의 전경에 해당 사진이 놓여 있으므로 이 갑판 공간이 적합합니다.",
          "kept": "L19B02"
        },
        "fingerprint": "3f8ff2803a60bea2"
      },
      "S28sh10": {
        "assigned": "L19B01",
        "chosen": "L19B01",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/88362757-1436-49d1-91c3-4bcc56fad1b2/episodes/5ecb3f04-00aa-436b-9ae7-232c4aa9f150/images/background_chain/L19B01.png",
        "record": {
          "candidates": {
            "A": "L19B01",
            "B": "L19B02",
            "C": "L19B03"
          },
          "assigned": "L19B01",
          "choice": "Candidate A",
          "confident": true,
          "reason_ko": "\"조타기에 손을 뻗은\"이라는 지문으로 보아 배의 조타기가 있는 조타실 내부 공간이 필요하므로, 조타핸들이 있는 Candidate A가 적합합니다.",
          "kept": "L19B01"
        },
        "fingerprint": "fa416980fb0160e1"
      }
    }
  },
  "step_id": "shot_conti_light",
  "run_id": "92c179ec-749a-4951-bfb8-09af7097300b",
  "resolved_model": "gpt-image-2",
  "updated_at": "2026-07-23T08:43:12.833049+00:00",
  "project_config_snapshot": {}
}