{
  "status": "completed",
  "applicable_count": 4,
  "completed_count": 4,
  "failed_count": 0,
  "schema_version": 4,
  "config_hash": "123987836f4b9e64",
  "data": {
    "contis": {
      "S1sh7": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "bgonly",
        "error": null
      },
      "S1sh8": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S1sh9": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/conti/conti_S1sh9.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L01B01.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 front cabin of the aging intercity bus, crouched in the narrow space before the farebox and facing the open front entrance.\n\nSHOT TEXT (authoritative, Korean): 쪼그려 앉은 정임이 고개를 든 채 앞문 쪽의 최씨를 바라보는 측면 얼굴.\n\nCARRIED STATE (persist exactly): The bus still has old vinyl seatback covers and a rubber aisle mat. The chained fare box and its coins and two folded bills remain unchanged near the driver's seat. 정임: She remains crouched in front of the fare box, wearing her navy conductor's uniform and brimmed cap.\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: The camera settles beside 정임 at her crouched head height, perpendicular to her eyeline, placing her right-facing profile in the left foreground with open look space toward the doorway. 최씨 remains smaller at the right rear near the entrance, his weight held over the raised foot as the two characters maintain a physically continuous upward-and-downward exchange of looks.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 정임 in the middle-left of the frame, foreground, looks toward 최씨 at the front doorway; 최씨 in the middle-right of the frame, background, looks toward 정임 beside the fare box; front doorway in the upper-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: front doorway (open behind 최씨 at the entrance steps) — The doorway is seen obliquely in the right background on the same side of the sightline established in the previous shot; used as Anchors 최씨 and receives 정임's profile eyeline; fare box (secured to the column by its chain) — Its upper side appears low between 정임 and the bus-front background; used as Connects 정임's crouched position to the object she has just inspected; aisle and seat backs (aisle covered by a rubber mat; seat backs fitted with old vinyl covers) — The seat backs recede away from the front area on an oblique axis; used as Provide depth behind 정임 without interrupting her look space.\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/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L01B01.png"
          ],
          [
            "char:정임",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/reference/dc978079-d6ee-4d50-8a15-38ad425f9b11.png"
          ]
        ],
        "asset_id": "1c6a3248-5c89-437f-8a6c-4574121c42e4"
      },
      "S2sh5": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/conti/conti_S2sh5.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L02B01.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 second intercity bus’s narrow front aisle, among the fixed passenger seats and facing the empty mount beside the driver’s station.\n\nSHOT TEXT (authoritative, Korean): 통로에 꼿꼿이 선 정임의 고개가 운전석 옆의 빈 받침대 쪽을 향해 고정된 뒷모습.\n\nCARRIED STATE (persist exactly): Bus No. 2 has newly replaced seat covers, no aisle mat, and an empty mounting base beside the driver's seat instead of a fare box. 정임: She wears her navy conductor's uniform and brimmed cap and stands in the aisle oriented toward the empty mounting base.\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 two seat rows behind 정임 at upper-torso height, the camera remains slightly off the aisle centerline and looks past her rigid back toward the empty pedestal beside the driver's position. Her planted figure occupies the central foreground-to-midground axis, while the pedestal remains clearly visible at the end of her fixed head direction, making the absence there legible without shifting the static camera.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: 정임 in the middle-center of the frame, midground, looks toward empty pedestal beside the driver's position; empty pedestal beside the driver's position in the upper-center of the frame, background.\n- KEY BACKGROUND ELEMENTS: empty pedestal beside the driver's position (empty, with no fare box mounted on it) — Its vacant top and front side face the camera beyond 정임 at the end of the aisle; used as Principal recognition point at the end of 정임's fixed head direction; bus seats (seat covers replaced with new ones) — The backs flank both sides of the aisle and recede toward the driver's position; used as Create converging spatial lines around 정임 and the empty pedestal; aisle floor (no aisle mat installed); used as The uninterrupted floor plane leads from the camera toward 정임 and the front of the bus.\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/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L02B01.png"
          ],
          [
            "char:정임",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/reference/dc978079-d6ee-4d50-8a15-38ad425f9b11.png"
          ]
        ],
        "asset_id": "9d053cd6-ef80-4da0-ba27-804a1ef233aa"
      },
      "S2sh7": {
        "image_path": null,
        "plate_path": null,
        "prompt": null,
        "skipped_reason": "prev",
        "error": null
      },
      "S3sh5": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/conti/conti_S3sh5.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L01B01.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 aging intercity bus’s front seating area, beside the seat directly behind the driver’s position. The windows look out into full darkness.\n\nSHOT TEXT (authoritative, Korean): 정임의 쫙 펴진 손바닥 위에 고무줄로 묶인 낡은 회수권 뭉치가 평평하게 놓인 클로즈업.\n\nCARRIED STATE (persist exactly): Bus No. 1 still has its old vinyl seatback covers, rubber aisle mat, and chained fare box in the same position; the coins and two folded bills remain inside. The windows are dark with night outside. 정임: She wears her navy conductor's uniform and brimmed cap and stands near the fare box. A worn bundle of tickets bound with a rubber band lies flat on her open palm.\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 above and slightly beside 정임's hand, the camera takes a steep oblique view that excludes her face while preserving her fully spread palm, sleeve edge, and the complete ticket bundle. The rubber-banded stack lies flat across the central portion of her palm, occupying roughly the central quarter so the hand and a restrained fragment of the nearby seat remain as scale references.\n- FRAMING SCALE: insert close-up on a detail\n- FRAME LAYOUT: rubber-banded used ticket bundle in the middle-center of the frame, foreground; 정임's open hand in the middle-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: used ticket bundle (old, bound with a rubber band, with its cover folded) — The folded cover and layered paper edges face upward toward the oblique camera while the complete bundle lies flat across the palm; used as Primary insert detail centered on the hand without exceeding the hand's visible scale; rubber band (wrapped around the ticket bundle); used as Visually contains the old tickets and identifies the recovered bundle; edge of the seat behind the driver's position (seat back still fitted with its old vinyl cover) — A small oblique portion of the seat edge remains beyond the hand; used as Provides environmental and scale context without competing with the ticket bundle.\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/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L01B01.png"
          ],
          [
            "char:정임",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/reference/dc978079-d6ee-4d50-8a15-38ad425f9b11.png"
          ]
        ],
        "asset_id": "a52d59e5-718e-4413-8820-08655d495ba1"
      },
      "S3sh9": {
        "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/conti/conti_S3sh9.png",
        "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L01B01.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 narrow front seating area of the aging intercity bus, beside the seat behind the driver and near the chained farebox. The windows outside are completely dark.\n\nSHOT TEXT (authoritative, Korean): 회수권 뭉치를 쥔 정임이 고개를 든 채 옆에 선 최씨를 올려다보는 시선 교환.\n\nCARRIED STATE (persist exactly): The old vinyl seatback covers, rubber aisle mat, and chained fare box remain in their established positions, with darkness outside the windows. The coins and two folded bills remain at the bottom of the fare box. 정임: She stands in her navy conductor's uniform and brimmed cap, holding the rubber-banded ticket bundle in one hand. 최씨: He is inside the front of the bus in his work jumper and work gloves, with one hand resting on an adjacent seatback.\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: After tracking back from the hand insert, the camera settles at seated shoulder height on the aisle side, three-quarters off the axis between 정임 and 최씨. 정임 remains lower in the left foreground with the ticket bundle visible near her chest as she looks up, while 최씨 occupies the right midground above her with one hand supported on the adjacent seat back and his gaze directed down to her.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 정임 in the lower-left of the frame, foreground, looks toward 최씨 beside the seat back; 최씨 in the middle-right of the frame, midground, looks toward 정임 holding the ticket bundle; seat back supporting 최씨's hand in the middle-right of the frame, midground.\n- KEY BACKGROUND ELEMENTS: seat back beside 정임 (fitted with an old vinyl cover) — Its aisle-facing edge angles toward the camera beneath 최씨's supporting hand; used as Physical anchor for 최씨's higher position and the two characters' shared space; used ticket bundle (old, rubber-banded, and held in 정임's hand) — Part of the folded cover faces the camera while the bundle is clasped close to 정임; used as Keeps the recovered object visible within the reaction composition; side window (showing the already dark exterior) — The window is seen obliquely behind the two figures, with darkness visible beyond it; used as Separates the figures from the night exterior without becoming a light source; aisle rubber mat (still laid along the aisle floor); used as Provides a low spatial line beneath the two unequal figure heights.\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/da049582-2c6d-492c-979d-f468d61bab6e/episodes/0aea12c2-7e12-485f-b8c1-e20f4bf16185/images/background_chain/L01B01.png"
          ],
          [
            "char:정임",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/reference/dc978079-d6ee-4d50-8a15-38ad425f9b11.png"
          ],
          [
            "char:최씨",
            "/Users/manta/Documents/Projects/TheRoad-I1/projects/da049582-2c6d-492c-979d-f468d61bab6e/images/0aea12c2-7e12-485f-b8c1-e20f4bf16185/reference/7170fe42-eeb4-47c2-bba4-4dff6cb50099.png"
          ]
        ],
        "asset_id": "c8de0fbc-71a5-4b1f-8b94-0d8020210eba"
      }
    },
    "map_conti": {},
    "conti_pack": "5.202607222353",
    "lane_conti": {}
  },
  "step_id": "shot_conti_light",
  "run_id": "2c956c1b-8c90-46a7-9550-98b617e338cf",
  "resolved_model": "gpt-image-2",
  "updated_at": "2026-08-29T07:43:25.425736+00:00",
  "project_config_snapshot": {}
}