{ "status": "completed", "applicable_count": 84, "completed_count": 84, "failed_count": 0, "schema_version": 4, "config_hash": "14c05253a60f4573", "data": { "contis": { "S1sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S2sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S3sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S3sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L194B01.png", "prompt": "The attached image is the LOCATION PHOTOGRAPH (loose spatial reference only).\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 moving dump truck's compact driver's cab, at the steering position with daylight beyond the windshield.\n\nSHOT TEXT (authoritative, Korean): 덤프트럭 운전석에서 고개를 떨군 채 조는 운전사의 모습.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): The dump-truck driver is seated asleep in the driver's seat with his head drooping forward. The source does not specify the placement of his arms and legs or whether his torso rests against the seat back.\n\nCARRIED STATE (persist exactly): The self-driving dump truck carries a full load of scrap, including the old robot Charlie, still entangled in netting with a worn Ubik logo on its chest.\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: Remain fixed inside the moving cab on the passenger side, slightly forward of the driver's shoulder and above seated eye level, looking diagonally down at his three-quarter profile. Frame his lowered head and upper torso left of center, catching the downward phase of a sleepy nod with his eyes closed rather than engaged with the road. Retain a narrow band of cab interior around him, letting the vehicle-relative stillness make his inattention unsettling.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Dump truck cab interior (Occupied by the dozing driver while the truck travels autonomously) — Viewed diagonally from the passenger side toward the driving position; used as Close spatial enclosure around the driver's lowered head and shoulders.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L194B01.png" ] ], "asset_id": "7f65b8b7-58fa-4511-842a-d448b0c82aac" }, "S4sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S4sh1.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: Inside the front seating compartment of a car parked in an affluent residential neighborhood, with daylight entering through the windows.\n\nSHOT TEXT (authoritative, Korean): 정차해 있는 차 안, 구겨진 도면을 가리키는 페드로의 손과 이를 미간을 찌푸린 채 내려다보는 현우의 모습.\n\nCARRIED STATE (persist exactly): The car is parked in the upscale residential district, and the house plan is crumpled and badly drawn. 페드로: Pedro occupies the driver's seat and wears an earpiece. 현우: Hyunwoo is seated in the passenger position, holding and examining the crumpled plan.\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 inside the stationary car, just behind and inboard of 페드로's driving position, looking diagonally down from above the occupants' heads. His shoulder forms a narrow left foreground edge as his indicating hand reaches toward the crumpled drawing in the lower center; 현우's three-quarter face occupies the right midground, brow furrowed and attention lowered to the same drawing. Keep the drawing below one-quarter of the frame and both teenagers' upper-body relationship readable, with the hand's indication carrying the emphasis.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Crumpled drawing (Crumpled and poorly drawn, being examined and indicated) — The marked face tilts upward toward the occupants and remains visible to the camera from above; used as Shared lower-center attention anchor linking the hand and 현우's reaction; Stationary car interior (Occupied by 페드로 in the driving position and 현우 beside him) — Viewed diagonally forward from behind the driving position; used as Maintains the compressed relationship between the two occupants.\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:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:페드로", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/037b034f-6a83-4071-99b1-32d2e4066fc0.png" ] ], "asset_id": "1362a583-3c44-441e-b1f4-d25af060171a" }, "S5sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S5sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L152B03.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 front door of an upscale house, beside the large living-room window through which the occupant is visible.\n\nSHOT TEXT (authoritative, Korean): 고급주택 거실 통유리창 너머로 먼지를 터는 젊은 여자를 응시하며 현관문 앞에 바짝 붙어선 현우의 모습.\n\nCARRIED STATE (persist exactly): The house has a full-height living-room window and an old-fashioned keyed front-door lock. The young female housekeeping robot is intact at this point. 현우: Hyunwoo has crossed the boundary wall and is keeping close to the front entrance.\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 gently from outside the entrance at 현우's shoulder height, behind and to one side of him, looking past his shoulder toward the living-room window. Keep his body close to the entrance along the left foreground, shoulders drawn inward as he watches the young Asian woman deeper inside at the right; she remains absorbed in dusting, looking down toward her working hand rather than toward him. Hold both spatial layers in readable focus, using the window as a transparent boundary rather than a reflection.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Living-room window with the dusting woman visible beyond in the middle-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: Living-room window (Closed at this moment, with the room and dusting woman visible through it) — Seen obliquely from outside; the woman is visible beyond the pane; used as Separates the concealed observer from the unaware interior figure; Entrance door (Not yet opened, with an old-style lock) — Its exterior side is beside 현우 in the left foreground; used as Explains his compressed posture and establishes the entrance-to-window route.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L152B03.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:젊은 아시아계 여자 로봇", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/146f33f5-d0d1-4c47-8e42-1921c27a7836.png" ] ], "asset_id": "dde54bdc-8795-4460-ac4c-7a559b6d6b14" }, "S5sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S5sh16": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S5sh16.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L152B01.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 upscale house near the street, facing the empty roadside where the getaway car had been parked.\n\nSHOT TEXT (authoritative, Korean): 경찰에게 양팔을 붙잡힌 채 페드로의 차가 사라진 텅 빈 길가 쪽을 원망스럽게 돌아보는 현우의 찡그린 얼굴.\n\nCARRIED STATE (persist exactly): The car has disappeared from the roadside; the living-room window and the second-floor escape window remain open. The female housekeeping robot remains on the floor with torn head skin and exposed metal. 현우: Hyunwoo has a fresh dog-bite wound on his leg and is being led away under arrest.\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 beside 현우 from slightly behind his shoulder at shoulder height, holding his grimacing face in a close three-quarter turn as he looks back toward the empty roadside at frame left. His face occupies the center-right while cropped police shoulders and gripping hands remain at opposite edges, making both restrained arms readable without competing with his reaction. Keep the officers' eyes outside the crop and their unequal shoulder positions consistent with an ongoing escort; the principal change is 현우's backward gaze.\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: Empty roadside formerly occupied by 페드로's car in the middle-left of the frame, background.\n- KEY BACKGROUND ELEMENTS: Roadside where 페드로's car had been (Empty; 페드로 and the car are no longer present); used as A visible left-background gap that gives 현우's backward look its meaning.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L152B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "32035306-c502-4408-8bfc-f7eedf49376d" }, "S6sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S6sh17": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S6sh26": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S6sh26.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_dump_sel.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 a dusty hillside path leaving the refugee settlement dump, with extensive makeshift dwellings spread behind it.\n\nSHOT TEXT (authoritative, Korean): 쓰레기로 덧대어 지어진 거대한 난민촌 판잣집들을 배경으로 흙먼지 날리는 언덕을 걷고 있는 mid-stride 상태의 앰버, 라울, 위장한 찰리의 뒷모습 풀샷.\n\nCARRIED STATE (persist exactly): Charlie is disguised in an old overcoat and hat over his dirty, aged gorilla-shaped body, with the netting and worn chest logo beneath the disguise. His blue-lit eyes remain unchanged, and the repaired jukebox was last left switched off. 앰버: Amber is walking away from the rubbish dump toward Pedro's home, still wearing her mask and waist tool pouch. 라울: Raul is walking toward Pedro's home after escaping notice.\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: Follow from behind and slightly off the center of their route at a low chest-height viewpoint, keeping 앰버, 라울, and disguised 찰리 visible from head to foot beneath the settlement. Arrange 앰버 at left, 라울 near center, and 찰리 at right with naturally unequal gaps: she transfers weight forward, 라울 lifts a trailing heel, and 찰리 carries his compact silhouette through a shorter step, all attending to the route toward 페드로's home rather than looking back. Ease the tracking toward its stop while retaining the complete figures, reserving the upward tilt for the next moment and letting their increasing distance carry the emphasis.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Refugee settlement dwellings (An extensive settlement of makeshift homes patched with discarded materials) — Overlapping sides and fronts extend beyond the departing figures; used as Broad background scale that will become the focus of the following upward tilt; Route toward 페드로's home (Being traversed by the three companions) — Recedes from the lower foreground into the settlement; used as Connects the full-body walking figures with their destination.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_dump_sel.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ] ], "asset_id": "e7cb1336-68ab-42f8-8caa-a8db9daa34a5" }, "S7sh11": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S7sh11.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 the ground beside the cracked seawall at the refugee settlement's suspended repair site.\n\nSHOT TEXT (authoritative, Korean): 심하게 금이 간 방벽 쪽을 손가락으로 가리키며 눈을 부릅뜬 미연의 절박한 얼굴.\n\nCARRIED STATE (persist exactly): The seawall has severe cracks and visible water leakage, with puddles on the worksite ground. The military truck remains stopped in front of the forklift amid the halted repair equipment and materials. 미연: Miyeon is out of the forklift and standing among the gathered workers, urgently indicating the leaking wall.\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: Finish the dolly approach on the established outer flank at 미연's eye height, retaining an oblique three-quarter view rather than moving onto the administrator's axis. Place her desperate face left of center, with her pointing arm extending into the right-hand space and a limited section of the cracked wall beyond it. Her upper body strains forward while her widened eyes remain fixed on the administrator just outside the frame; the closing distance is the sole emphasized change.\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: Cracked embankment wall indicated by the pointing arm in the middle-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: Cracked embankment wall (Severely cracked, with water leaking through the wall) — A narrow section of the damaged face is visible beyond the pointing arm on screen right; used as Provides visible evidence for the appeal 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, "no_plate": true, "ref_paths": [ [ "char:미연", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/e9e0c616-aa12-4a9f-a62c-9ab2d808e06c.png" ] ], "asset_id": "d68199d9-a355-482b-9cd4-df9585548d5e" }, "S7sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S7sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S8sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S8sh5.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L159B01.png", "prompt": "The attached image is the LOCATION PHOTOGRAPH (loose spatial reference only).\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: At the judge's worn table inside a shabby refugee tribunal, in subdued daytime interior light.\n\nSHOT TEXT (authoritative, Korean): 서류 종이 위로 붉은 도장을 거칠게 내리찍어 종이 표면에 막 닿은 재판관의 굵은 손.\n\nCARRIED STATE (persist exactly): A shabby table and chair serve as the judge's station, with a backlog of documents piled on the table.\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: Complete the inward move beside the table's outer end, looking steeply downward from the inherited oblique side onto 재판관's thick hand at the instant the red stamp touches the document. Let the descending hand and wrist carry the central emphasis, with the stamp small beneath the grip, the receiving sheet occupying less than a third, and the table edge and adjacent paperwork preserving scale. Crop his face out while his seated body remains a partial upper-edge reference, making the hand-to-paper contact—not a change of gaze or illumination—the decisive visual event.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Document receiving the stamp (The stamp has just contacted its surface) — The working face lies upward toward the downward-looking camera; no particular wording or completed seal is asserted; used as Makes the exact contact point visible beneath the hand; Red stamp (Held firmly against the document at first contact) — The gripped upper portion is visible while the stamping face is against the paper; used as Provides the small mechanical endpoint of the forceful hand movement; Shabby table and stacked paperwork (Documents remain piled before the seated judge) — The tabletop is seen obliquely, with its outer edge retained as a spatial reference; used as Grounds the close framing in the ongoing bureaucratic setting.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L159B01.png" ] ], "asset_id": "5bd46cd4-f353-4051-a92b-c244f42f383d" }, "S8sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S8sh13": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S8sh13.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L159B02.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 a city street at night during a violent riot, among civilians forced to kneel under intermittent gunfire flashes.\n\nSHOT TEXT (authoritative, Korean): 극도의 공포에 질린 표정으로 어린 현우와 앰버를 양팔로 빈틈없이 끌어안고 웅크린 미연의 상체.\n\nCARRIED STATE (persist exactly): This is a black-and-white nighttime memory of a U.S. street, with intermittent gunfire flashes and a large American flag. 미연: Miyeon is kneeling in terror, hunched with both arms wrapped protectively inward. 현우: Hyunwoo appears as a younger child, huddled low within a protective embrace. 앰버: Amber appears as a younger child, huddled low within a protective embrace.\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: Within 현우's explicitly separate nightmare, finish the descending move on 미연's three-quarter side and settle into a slightly downward view of her kneeling upper body. Place 미연 centrally, young 현우 tucked against her left side and young 앰버 against her right, retaining both children's faces and the enclosing shape of both arms rather than allowing a weapon to become the foreground subject. 미연 watches the armed attacker outside the upper-right frame while the children peer toward the same threat from different head angles; preserve the embrace and let only the final reduction in camera distance intensify the moment.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: American city street (The family is kneeling during the armed attack) — Only a limited area around and behind the huddled family remains visible; used as Establishes the separate nightmare location without diluting the protective embrace.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L159B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "863e681c-c732-49e9-9c06-7c759918fd73" }, "S9sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S9sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L161B01.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 rubbish-strewn ground outside the refugee tribunal at night, amid desolate heaps of waste.\n\nSHOT TEXT (authoritative, Korean): 고통으로 일그러진 표정을 한 채 한 손으로 가슴을 강하게 움켜쥐고 크게 숨을 들이마시며 입을 벌린 현우의 상체.\n\nCARRIED STATE (persist exactly): It is night outside the refugee court, surrounded by desolate rubbish heaps. 현우: Hyunwoo is waking outside with his dog-bitten leg and injuries from the baton blow still untreated, though his awareness is returning. The stolen wallet containing the judge's identification and cash is already in his pocket.\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: Finish the approach from the established oblique front side of seated 현우, with the camera above his seated chest and tilted slightly downward. Place his upper body just left of center, retaining the hand clamped to his chest, the open mouth drawing breath, and a narrow lower-frame indication that he has raised himself from the ground. His attention drops toward his own chest as his shoulders seize around the inhalation, while the camera stops short of the rise that will accompany his later attempt to stand.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Rubbish heaps outside the refugee court (Surround the place where 현우 awakens) — Broken-up portions remain behind his shoulders and along the frame edges; used as Locates his awakening in the desolate exterior without inventing individual discarded objects; Ground outside the court (현우 has just raised his body from it) — Visible beneath the lower edge of his seated torso; used as Preserves the physical transition from lying down to sitting up.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L161B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "e2420bad-c4d6-4722-a5e2-886e38397c1a" }, "S9sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S10sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S10sh3.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L162B01.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: At a secluded table inside a shabby alley restaurant, under dim restaurant lighting at night.\n\nSHOT TEXT (authoritative, Korean): 돈 봉투를 집어 들려는 남자의 손등 위를 다급한 힘으로 꽉 내리눌러 제압하고 있는 현우의 굳은 손 클로즈업.\n\nCARRIED STATE (persist exactly): A cash-filled envelope is on the table in an out-of-the-way part of the shabby restaurant. 현우: Hyunwoo is seated at the table and has taken hold of the money envelope again; his dog-bitten leg and earlier head injury remain untreated.\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: Complete the inward move immediately beside the table on the established conversation side, looking obliquely downward onto the joined hands. 현우's rigid hand enters from the lower left and pins the back of 장규석's reaching hand near center, with the money envelope beside the contact occupying less than a quarter of the frame and partial seated torsos retained at opposing edges. Both men attend downward to the arrested exchange, their faces outside the crop; emphasize the pressure between hands without changing the table geometry or lighting.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Money envelope (Within reach but prevented from being freely taken) — Lies on the tabletop beside the overlapping hands; used as Keeps the stakes of the physical interruption visible without competing with the hands; Secluded restaurant table (Occupied by the two men during the transaction) — The top and near edge are visible from the inherited oblique side; used as Connects the opposing forearms and anchors the continuous conversation axis.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L162B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "2c3ae081-487d-467f-b6d8-4c65de90d776" }, "S10sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S10sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S11sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S11sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.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: At the narrowing opening of the refugee settlement's heavy barred entrance gate, opening onto a dark alley.\n\nSHOT TEXT (authoritative, Korean): 어둠이 내린 좁은 골목길을 향해 닫히는 도중인 육중한 철창문 틈새로 몸을 비틀어 구겨 넣은 자세의 현우의 다급한 전신.\n\nCARRIED STATE (persist exactly): The camp entrance is closing for curfew; shop doors are shutting and the container homes and streetlights are being extinguished, leaving the streets dark. 현우: Hyunwoo is hurrying through the entrance before it closes, still carrying the untreated dog-bite injury and earlier head injury.\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 stationary just inside the entrance, below eye level and offset beside the opening, looking obliquely across the threshold before the following pan begins. Hold 현우's full body near center as he twists through the narrowing gap toward screen right, one shoulder leading and his attention fixed on the alley beyond the right edge. Keep the closing gate along the left third and retain the threshold beneath his feet, making his bodily displacement the principal visual change.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Closing entrance gate in the middle-left of the frame, midground; Alley beyond the entrance in the middle-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: Heavy barred entrance gate (Closing, leaving a narrowing passage) — Seen obliquely from inside the entrance, with its closing edge beside 현우; used as Creates the constricting left boundary without obscuring his complete body; Entrance threshold and alley (현우 is crossing into the settlement) — The threshold crosses the lower field, and the alley continues toward screen right; used as Establishes an unambiguous inward route for the subsequent pan.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "37dd0d43-2fdf-429b-82e4-045c520df701" }, "S11sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S11sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.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: At the open front threshold of a family's container home in the dark refugee settlement, viewed from the alley outside.\n\nSHOT TEXT (authoritative, Korean): 열린 컨테이너 문 안으로 한 발을 내딛은 현우의 뒷모습.\n\nCARRIED STATE (persist exactly): The home container is marked 7-31, and its door is open for entry. The surrounding camp streets remain dark after curfew lights-out. 현우: Hyunwoo is entering his home with his upper garment still on; his face and leg remain injured, and the leg wound has not yet been treated.\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 the established position behind and slightly left of 현우, above his eye line with a gentle downward tilt that retains his back and both feet. Frame his full figure slightly right of center as his leading foot crosses the open container doorway, his head directed into the interior rather than back toward the observer. Keep the camera still so his movement across the threshold alone resolves the preceding hesitation.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Container entrance door (Open as 현우 enters) — The open leaf is seen obliquely beside the entrance, leaving his back and leading foot visible; used as Frames the crossing without concealing the body's movement; Container number 7-31 (Identifies 현우's home) — The exterior-facing marking bearing 7-31 is visible beside the entrance; used as Provides a restrained location identifier outside the central action; Container doorway threshold (Being crossed) — Viewed from behind and above 현우's trailing foot; used as Separates the exterior passage from the interior destination.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "478420ea-6c5c-40ae-a832-b5c0b14b89aa" }, "S12sh7": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S12sh7.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L166B01.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: In the dining area inside a refugee family's container home, lit by a candle on the table.\n\nSHOT TEXT (authoritative, Korean): 상체를 뒤로 물린 자세로 미연이 내민 약병을 차가운 눈빛으로 노려보는 현우.\n\nCARRIED STATE (persist exactly): A candle continues to light the dining table, where the meal was served; the mending clothes remain in the room and the medicine container is now open. 현우: Hyunwoo has removed his upper garment and is seated at the table with visible facial injuries and a bleeding dog-bite wound on his leg. 미연: Miyeon is at the dining table with the opened medicine container, preparing to examine the leg injury.\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: Settle the inward move behind and beside 미연's shoulder at 현우's seated eye height, maintaining the established oblique conversation axis. Her shoulder occupies a narrow left foreground edge and her extended medicine bottle remains small in the lower center, while 현우's upper body recoils into the right half with a clearly visible gap between his torso and the bottle. His cold gaze angles down toward the offered medicine, while 미연 inclines her head toward her extended hand; the backward shift of his body supplies the refusal.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Medicine bottle (Held out by 미연) — Seen from the side in her extended hand, below 현우's chest; used as Provides the focus of refusal while remaining small enough for the intervening empty space to read; Dining table (현우's meal remains set out) — An oblique portion of the tabletop crosses the lower frame; used as Anchors the domestic context beneath the separated hand and 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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L166B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:미연", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/e9e0c616-aa12-4a9f-a62c-9ab2d808e06c.png" ] ], "asset_id": "70be5339-3395-4c59-bd14-9f3f92278784" }, "S12sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S12sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S13sh10": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S13sh10.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: In an outdoor gang gathering spot beside the refugee settlement's seawall, near burning metal barrels and a barbecue grill.\n\nSHOT TEXT (authoritative, Korean): 빼앗은 권총의 차가운 총구를 쿠마의 이마 정중앙에 맞닿게 댄 현우의 단호한 옆얼굴.\n\nCARRIED STATE (persist exactly): A fire burns in a metal drum at the gang's roadside hideout, and chicken skewers are on the barbecue grill. The adjoining seawall remains cracked and leaking. 현우: Hyunwoo wears his upper garment and holds a seized gun in an aiming posture; his facial injuries and dog-bitten leg remain untreated. 쿠마: Kuma remains at the barbecue gathering with a chicken skewer in hand.\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: Ease the lateral approach almost to a stop on the established side of the 현우–쿠마 axis, below 현우's eye height and looking slightly upward across his gun arm. Hold 현우's determined profile in the left half and 쿠마's seated head at the right edge, with the handgun running between them and its muzzle visibly touching the center of 쿠마's forehead rather than overlapping it ambiguously. 현우 looks down toward the contact point while 쿠마 lifts his attention toward 현우's face, retaining a relaxed torso beneath the threat; the closing distance is the dominant emphasis.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Seized handgun (Held with its muzzle against 쿠마's forehead) — Seen laterally, with the barrel axis running from 현우's hand toward 쿠마; used as Connects the two profiles while leaving the contact point readable and the weapon proportionate to the hands.\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:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:쿠마", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/f811dc55-7959-4845-b219-c94dbba1c104.png" ] ], "asset_id": "a2b7d59b-6427-4f49-8773-4ed140b22cee" }, "S13sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S13sh20": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S14sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S14sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S14sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S15sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S15sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L168B03.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: In the customer area inside a refugee settlement junk shop, amid piled appliances and scrap in subdued daytime light.\n\nSHOT TEXT (authoritative, Korean): 찰리의 가슴 장갑 표면에 남은 로고를 손가락으로 가리키는 마츠다의 팔.\n\nCARRIED STATE (persist exactly): Appliances and scrap are piled throughout the shop. Charlie remains dirty and worn, with blue-lit eyes, an old coat and hat, and a visibly worn Ubik logo on his chest. 마츠다: He has moved away from his repair work and is standing in the shop's inspection area with an arm extended.\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 inward dolly on the open side of the inspection axis, slightly above 찰리's chest and looking obliquely downward rather than squarely at the armor. Keep 찰리's chest and shoulder at center-right, with 마츠다's extended forearm entering from the left and his fingertip stopping beside the worn 유빅 logo; only the edge of his downward-turned profile need remain visible as he studies the mark. Emphasize the closing distance alone, retaining soft appliance piles around the bodies and leaving 찰리's face outside the upper edge.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Worn 유빅 chest logo (Partially worn away but still identifiable) — The marked outward face of Charlie's chest is visible obliquely, with the surviving 유빅 lettering beside Matsuda's fingertip; used as Provide the precise evidence being identified, as a small detail within the chest rather than an enlarged isolated graphic; Piled appliances and scrap (Accumulated throughout the shop) — Partial outlines remain around the inspected upper body; used as Preserve the shop context and realistic scale behind the close inspection.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L168B03.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ], [ "char:마츠다", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/5183d512-3f43-487b-8014-960c92e6d68a.png" ] ], "asset_id": "8a256e3b-52f6-4af6-aa77-ef9e992d170a" }, "S15sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S16sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S16sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S17sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S17sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S18sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S18sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L171B01.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: At the desk inside a militia commander's office, beside a speakerphone in ordinary daytime interior light.\n\nSHOT TEXT (authoritative, Korean): 책상 위의 스피커폰을 향해 몸을 기울인 채 능글맞게 웃고 있는 박철진의 상체.\n\nCARRIED STATE (persist exactly): The speakerphone is in use in the militia office. 박철진: He has a knife in hand, playing with it during the speakerphone conversation.\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 the entry composition beside the desk before the inward dolly develops, below 박철진's eyes at a three-quarter angle to his torso and on the established side of the interpersonal axis. Place his leaning upper body at center-right and the speakerphone below his face near the lower center, small enough to preserve the desk's scale. His smile and lowered eyes remain directed toward the speakerphone as he speaks, with 윤성찬 outside the selected frame.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Desk (Supporting the speakerphone during the call) — The near edge runs obliquely across the bottom of the composition; used as Connect the leaning torso to the call while preserving a modest foreground footprint; Speakerphone (In use for the ongoing call) — Seen obliquely from above on the desktop beneath Park's face; used as Supply the visible focus of his speech and downward attention.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L171B01.png" ], [ "char:박철진", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8426809f-6189-44b9-b275-da8ab73d1352.png" ] ], "asset_id": "86ca7f7a-7c3a-4769-b837-fca22d49aac1" }, "S18sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S18sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S19sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S19sh3.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: Inside the rear passenger compartment of a car, immediately behind the front seats, with daylight entering through the windows.\n\nSHOT TEXT (authoritative, Korean): 주먹을 꽉 쥔 채 앞좌석을 향해 상체를 바짝 내민 윤성찬의 격양된 얼굴.\n\nCARRIED STATE (persist exactly): 윤성찬: He is seated inside the car and retains his handkerchief.\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: Finish the low approach between the front seats on the passenger side, looking slightly upward from upper-chest height at 윤성찬's three-quarter face. His forward-thrust head occupies the upper center-right and his clenched fist remains along the lower edge, with narrow seat edges retaining the car's scale. He directs his anger toward the driver outside the left edge, never toward the lens; proximity supplies the final intensification.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Front seats (Their inner edges remain visible beside the camera's viewing gap) — The inner sides and partial rear faces bracket the view toward the rear passenger; used as Create a narrow spatial channel around the face and fist without obscuring either.\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:윤성찬", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ca351fd2-cdd4-40c3-b589-9cb376c17d84.png" ] ], "asset_id": "feea18f2-58ff-46c5-a690-fa0785b3fe66" }, "S20sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S20sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S20sh16": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S20sh16.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 the ground at a narrow alley off the refugee settlement market, where the fleeing youth is subdued.\n\nSHOT TEXT (authoritative, Korean): 바닥에 쓰러져 일그러진 현우의 등 위를 무릎으로 짓누른 채 체중을 싣고 고정된 경찰(현우 체포·호송)의 굳은 상체.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Hyunwoo is pinned face-down on the ground beneath a plainclothes officer's knee pressing into his back. His head's direction and the positions of his arms and legs are not specified.\n\nCARRIED STATE (persist exactly): Boxes knocked over during the escape remain scattered through the market alley. 현우: He has been brought down by a rifle-butt strike, with his outer shirt still on. His earlier facial injuries and dog-bite leg injury remain.\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: Let the rising camera settle diagonally beside the restraint, looking down from the officer's lateral three-quarter side rather than directly overhead. Arrange the officer's rigid torso in the upper right, his weight-bearing knee near center, and 현우's pinned back across the lower left, preserving an uninterrupted visual connection between all three. The officer looks down at the restraint while 현우's turned, contorted face is directed toward the ground beside him; the settled hold makes the fixed bodily relationship the emphasis.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Ground at the alley restraint point (Supporting 현우's prone body and the kneeling officer); used as Provide a visible margin around the contact points so the restraint does not become an ambiguous overlap of bodies.\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:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "45af8bb5-9f53-4e4a-a819-7a8c7ba17ccd" }, "S21sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S21sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L170B01.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: Just inside the open doorway of a container home, with daylight entering the room where a child has been sleeping.\n\nSHOT TEXT (authoritative, Korean): 거칠게 열린 문 안으로 불쑥 몸을 들이민 라울의 다급한 전신.\n\nCARRIED STATE (persist exactly): The door of Raul's container has been thrown open. 라울: He has just entered the container through the open doorway.\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: Complete the pan from the footward side of 앰버's sleeping position and settle below 라울's eye level, laterally offset from the doorway's central axis. Hold his full body in the right-center of the frame as he pitches through the abruptly opened doorway, one foot carrying his weight inside and the trailing leg still completing the entry. His head turns toward 앰버 outside the left edge, making his urgent arrival—not a frontal presentation to the viewer—the organizing action.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Container doorway and door (The door has been abruptly opened and 라울 is entering) — Viewed obliquely from inside, with the opening and part of the open door visible beside his body; used as Frame his full-height entry and establish the threshold without enlarging the door through foreground distortion.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L170B01.png" ], [ "char:라울", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8a273153-5439-457f-8304-2020bf6ac74b.png" ] ], "asset_id": "f81f4ae2-7f77-4950-92a2-abc01a2199a4" }, "S21sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S22sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S22sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S22sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S23sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S23sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L173B01.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: At the central table inside a spacious detention-center visiting room, in plain daytime interior light.\n\nSHOT TEXT (authoritative, Korean): 얼굴 곳곳에 피멍이 든 채 수갑 찬 양손을 테이블 위로 길게 뻗은 현우의 절박한 상체.\n\nCARRIED STATE (persist exactly): A table stands in the middle of the large visitation room. 현우: He sits at the table with his wrists still handcuffed and visible bruising on his face. His dog-bitten leg remains injured.\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 stationary beyond the front corner of the table, slightly above seated eye level, looking down obliquely at 현우 in a three-quarter view. Place his bruised face in the upper-left portion and his cuffed, outstretched hands across the lower center, keeping the visible tabletop below one-third of the frame. His torso strains forward as he pleads toward 윤성찬 approaching outside the right edge; this is direct observation, not his subjective view.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 면회실 테이블 (Positioned in the middle of the visiting room, supporting 현우's extended hands) — The near corner and a shallow view across the top face the camera; used as Carries the diagonal from the restrained hands toward the pleading face; 수갑 (Fastened around both wrists) — Seen obliquely around the wrists above the tabletop; used as A small but readable restraint detail within the upper-body composition; 넓은 면회실 (Open room space remains visible beyond the centrally placed table); used as Negative space separates the isolated seated figure from the surrounding room.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L173B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "69e13ce4-f531-431c-a45d-c3679c68fd0e" }, "S23sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S23sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S24sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S24sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S24sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S25sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S25sh19": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S25sh22": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S25sh22.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_outdoor_reception_sel.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: Against a wall in a narrow, dark alley of the refugee settlement, away from the reception lot.\n\nSHOT TEXT (authoritative, Korean): 좁고 어두운 골목길 벽에 바짝 기대어 선 채 밖의 눈치를 살피는 현우 일행의 전신.\n\nCARRIED STATE (persist exactly): The settlement's restored lighting remains established, although this alley provides concealment behind a wall. At the reception, the tents, parked militia truck, jukebox and burst lamps remain; Charlie still wears his old coat and hat. 현우: He has taken cover behind the alley wall, still wearing his outer shirt. His facial bruises and leg injury persist. 앰버: She is hiding behind the alley wall with her mask and waist tool pouch retained. 라울: He is hiding behind the alley wall after running. 페드로: He is hiding behind the alley wall after running.\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 on the concealed side of the alley corner at a low height, looking diagonally along the wall with a slight upward tilt and enough room for all five figures from head to foot. Place 현우 nearest the opening at right, then 앰버, 찰리, 라울 and 페드로 receding leftward along the wall, varying their gaps, bent knees and shoulder contact so their shared concealment does not resemble a lineup. All attend to the militia beyond the upper-right opening with only slight head turns—현우 leaning just enough to check, 앰버 folded inward, 찰리 tilting his head, 라울 lowering his weight and 페드로 catching his breath—while nobody steps out of cover.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Narrow exposed opening beyond the concealing corner in the upper-right of the frame, background; Inner wall shielding all five figures in the middle-center of the frame, midground.\n- KEY BACKGROUND ELEMENTS: 골목 벽 (Concealing the group from the militia beyond the corner) — The camera looks along its inner face at a shallow angle toward the corner; used as Forms the shared hiding boundary and a receding line through the five figures; 골목 모퉁이와 바깥으로 열린 틈 (Only a narrow view beyond the hiding place is available) — The corner interrupts the view at upper right, with the exposed passage visible beyond its edge; used as Makes the danger direction legible without revealing the group's bodies to it; 좁은 골목 바닥 (Visible under the group's feet); used as Preserves full-body readability and shows their uneven, compressed spacing.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_outdoor_reception_sel.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "ed35ed23-b843-4470-bb40-db03b4117fa0" }, "S26sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S26sh9": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S26sh9.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L175B01.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: At a two-way junction inside the refugee settlement's underground sewer, where both branches recede into darkness.\n\nSHOT TEXT (authoritative, Korean): 어두운 하수도 두 갈래 길 앞에서 단호한 표정으로 페드로의 어깨를 꽉 쥔 현우의 상체.\n\nCARRIED STATE (persist exactly): The underground sewer divides into two passages. Charlie remains a worn gorilla-shaped robot in an old coat and hat, with blue-lit eyes and a faded UBIK chest logo. 현우: He is at the sewer fork without his outer garment; his face remains bruised and his dog-bitten leg remains injured. The contact card is concealed in his shoe. 페드로: He has reached the sewer fork and is about to take a separate route.\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 beside the sewer fork at upper-body height, looking past the outer edge of 페드로's shoulder toward 현우 in three-quarter view, with almost no lateral drift at this stage entrance. 페드로 occupies the lower-left foreground while 현우's upper body sits center-right; 현우 leans into the grip, his attention lowered toward 페드로's near shoulder, while 페드로 lifts his chin toward him. Keep the gripping hand, resolute face, and shoulder readable together, with the two passages separated behind them rather than introducing another compositional change.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Sewer fork (The passage divides into two routes) — The two branch entrances are visible obliquely behind the interaction; used as Provides the spatial evidence for the decision to separate.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L175B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:페드로", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/037b034f-6a83-4071-99b1-32d2e4066fc0.png" ] ], "asset_id": "bad5b160-fb00-401b-90e3-64652fe59154" }, "S26sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S27sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S27sh18": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S27sh21": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S28sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S28sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L179B01.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 van's rear passenger-and-cargo area, among scattered cardboard boxes in the nighttime darkness.\n\nSHOT TEXT (authoritative, Korean): 차 안 뒷좌석, 낡은 종이상자 더미 사이사이에 몸을 욱여넣고 웅크린 현우, 앰버, 찰리의 굳은 전신.\n\nCARRIED STATE (persist exactly): Scattered cargo boxes occupy the van's rear seating area, and a crude halogen cross is mounted on the roof. Charlie remains concealed among the boxes in his old coat and hat. 현우: He is concealed among the rear cargo boxes, with facial bruises and an injured leg; his outer garment remains removed. The contact card remains concealed in his shoe. 앰버: She is concealed among the rear boxes, still exhausted, with the outer garment used as a mouth covering.\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 ahead of the rear seating area on the passenger side, looking diagonally backward and downward from a high position that contains all three crouched bodies. Arrange 현우 left, 앰버 center, and 찰리 right within separate gaps between the worn paper boxes, using staggered knees and shoulders rather than a uniform row; no individual box should occupy more than a quarter of the image. 현우 finishes compressing himself beside 찰리, 앰버 folds tightly over her knees, and 찰리 remains tucked where he has been pushed, all keeping their attention down within the hiding spaces.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Worn paper boxes (Distributed through the rear seating area with gaps occupied by the hiding group) — Their tops and differently angled sides are visible from above; used as Create separate pockets of concealment without obscuring the three complete crouched poses; Rear seating area (Occupied by boxes and the concealed group) — Seen diagonally from the front passenger side; used as Establishes the limited shared space and realistic scale of the boxes.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L179B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "999f65d7-3a65-487a-8bd7-c6b9ebc6b8a4" }, "S28sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S28sh5.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L179B01.png", "prompt": "The attached image is the LOCATION PHOTOGRAPH (loose spatial reference only).\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 nighttime road directly ahead of the van at a militia checkpoint, seen through its windshield.\n\nSHOT TEXT (authoritative, Korean): 자동차 앞유리창 너머로 무기를 든 채 차의 앞길을 막아선 민병대원들의 위협적인 전경.\n\nCARRIED STATE (persist exactly): The rear cargo boxes and roof-mounted halogen cross remain in place. Charlie is concealed among the boxes, still wearing his old coat and hat.\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 immediately behind the front passenger seat after the forward track and pivot, looking slightly upward through the windshield from the driver's right. Retain the windshield edges as thin borders and distribute the armed militia across the middle distance so their bodies and the blocked road remain visible, making the redirected view—not a tighter distance—the principal change. They attend to the van's front cabin rather than the camera, with offset weight, different shoulder angles, and uneven weapon-carrying heights expressing the same blocking action without cloned poses.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Front windshield (The armed militia are visible through it) — Seen from inside the van, with the blocked road and militia beyond; used as Frames the threat as a direct exterior view from the protected cabin rather than a reflection or screen image; Road ahead (Blocked by the armed militia) — Extends forward beyond the windshield; used as Shows that the van's route is physically obstructed; Militia weapons (Held by the figures blocking the van) — Visible at varied oblique angles alongside their holders; used as Supply the immediate threat while remaining subordinate in size to the people.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L179B01.png" ] ], "asset_id": "029b4a24-f56c-4f1f-aeee-61bd3bdf819c" }, "S28sh7": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S28sh7.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L179B01.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: At the driver's seat inside the van's compact front cab, beside the lowered side window during the nighttime checkpoint stop.\n\nSHOT TEXT (authoritative, Korean): 열린 운전석 창문 너머의 민병대원들을 향해 활짝 웃으며 찡긋 눈웃음을 짓는 신부의 여유로운 얼굴.\n\nCARRIED STATE (persist exactly): The driver's window is lowered for the inspection, with the halogen cross fixed on the roof. The rear boxes continue to conceal Charlie in his old coat and hat. 신부: He remains seated at the wheel in his clerical collar, smiling through the lowered window.\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: Finish the inward move from the front passenger area at 신부's seated eye height, slightly ahead of his right shoulder, looking diagonally across the cabin at his near-profile face. Emphasize the reduced camera distance, placing his face center-right and the open driver's window along the left, with only a narrow portion of the surrounding cabin retained. He turns toward the militia outside the frame and holds a broad smile at the instant one eye narrows into a wink, never redirecting his attention toward the lens.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Open driver's window (Lowered for the exchange with the militia) — Its open aperture is seen obliquely beyond 신부's profile; no glass lies across the opening; used as Establishes the direction of his smile and offscreen attention; Driver's seat (Occupied by 신부) — A limited portion is visible behind his shoulder; used as Keeps the close portrait physically grounded inside the van.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L179B01.png" ], [ "char:신부", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/9dc6a5e5-ea08-4feb-a4b2-47229d567009.png" ] ], "asset_id": "a953ea46-2e6b-474f-bd4b-16263623425a" }, "S29sh6": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S29sh6.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L180B02.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 church's sparsely furnished basement prayer room, lit by the priest's candle beside a small organ, table, and chairs.\n\nSHOT TEXT (authoritative, Korean): 1층에서 들려오는 둔탁한 타격음에 일제히 어깨를 움츠린 채 위를 올려다보며 얼어붙은 일행의 전경.\n\nCARRIED STATE (persist exactly): The basement prayer room contains a cross, a small desk, chairs and a small organ, with candlelight brought down the stairs. Charlie retains his old coat and hat. 현우: He is in the basement prayer room with facial bruises and an injured leg, without his outer garment. The contact card remains concealed in his shoe. 앰버: She is in the basement, tired and hungry, retaining the outer garment used as a mouth covering. 신부: He is in the basement wearing his clerical collar and carrying a lit candle.\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 on the lower stairs in a shallow high-angle view across the entire group, capturing the opening instant of their reaction before 신부 gives the quieting gesture. Place 신부 nearest the stair base at left, 현우 center-left, 앰버 center-right, and 찰리 farther right, with full bodies visible and clear space allowing each to look naturally toward the upper floor beyond the frame. Their attention turns upward together, but the recoil is asynchronous—신부 pauses mid-weight transfer, 현우 draws one shoulder inward, 앰버 contracts over bent knees, and 찰리 halts a turn—so the shared alarm does not become a posed lineup.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Stairs to the upper floor (Connect the prayer room to the source of the knocking) — The lower steps enter along the left foreground and continue out of view upward; used as Anchor the camera position and explain the group's common upward attention; Small desk and chair (Present in the sparsely furnished prayer room) — Seen obliquely beyond the group; used as Provide modest human-scale context without crowding the reaction tableau; Small reed organ (Present among the room's few furnishings) — Partially visible at an oblique angle in the rear of the frame; used as Preserves the room's identity while remaining secondary to the startled figures; Cross (Present in the prayer room) — Its recognizable form remains visible in the background; used as Adds a restrained location cue without becoming the group's gaze target.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L180B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "51f9964d-9eec-4e5f-a76a-7feb0e6f9752" }, "S29sh10": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S29sh10.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L182B01.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 church's ground-floor entrance at night, seen through the door opening from inside.\n\nSHOT TEXT (authoritative, Korean): 살짝 열린 문틈으로 신부와 낯선 남자가 마주 서 있는 모습을 훔쳐보는 현우의 시점 쇼트.\n\nCARRIED STATE (persist exactly): The church entrance has been opened, and its small viewing window is open. The basement furnishings remain unchanged, with Charlie still downstairs in the old coat and hat. 신부: He is outside the church entrance, wearing his clerical collar. 구도환: He stands outside the church entrance, engaged in conversation.\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: Remain immediately inside the entrance at 현우's eye height, looking obliquely through the narrow opening of the door's small viewing window rather than through an invented gap beside the main door. Keep the opening's edges as slim foreground borders around 신부 at left and the unfamiliar man in his fifties at right, showing their upper bodies as they face one another; 현우, including his hands, stays entirely absent. 신부 inclines slightly toward the conversation with a lowered eyeline while the man lifts his gaze to meet him, preserving mutual attention rather than lens address in this static concealed view.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: Open viewing window in the entrance door in the middle-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: Entrance door's small viewing window (Open sufficiently for 현우 to look outside) — The opening is viewed from inside, with 신부 and the visitor directly visible beyond its edges; used as Restricts the field of view and establishes the concealed first-person perspective.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L182B01.png" ], [ "char:신부", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/9dc6a5e5-ea08-4feb-a4b2-47229d567009.png" ], [ "char:구도환", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/d5805340-a6a5-4677-96e4-1c7e8b89a6ef.png" ] ], "asset_id": "552fe877-7268-4883-a1c6-0d965dfe77b6" }, "S29sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S30sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S30sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S30sh17": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S31sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S31sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L189B01.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 a third-floor detention room in the brightly lit refugee administration building, at the facing interrogation chairs.\n\nSHOT TEXT (authoritative, Korean): 퉁퉁 부은 얼굴의 미연 앞에 바짝 의자를 당겨 앉은 박철진의 거만한 상체.\n\nCARRIED STATE (persist exactly): The management office is brightly lit, with the interrogation taking place on the third floor. 미연: Her face is badly swollen from the beating, and she remains in the interrogation room. 박철진: He is seated in the interrogation room after dismissing the subordinate from the beating.\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: Complete the dolly from just outside 미연's shoulder at a low seated height, looking slightly upward across the established interaction axis toward 박철진's three-quarter upper body. Keep the edge of 미연's swollen cheek and shoulder in the left foreground while 박철진 occupies the center-right, seated close with his torso angled into her space. They remain focused on each other, and the reduced camera distance—not a lighting or eyeline change—makes his conversational pressure tangible.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 박철진's chair (Occupied and pulled close to 미연) — A partial side edge is visible beneath his seated torso; used as The cropped chair establishes his seated position and intrusive proximity.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L189B01.png" ], [ "char:미연", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/e9e0c616-aa12-4a9f-a62c-9ab2d808e06c.png" ], [ "char:박철진", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8426809f-6189-44b9-b275-da8ab73d1352.png" ] ], "asset_id": "c9bf8684-260f-4c7f-bb67-b37f8e71578e" }, "S31sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S31sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S32sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S32sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S32sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S33sh6": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S33sh6.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L190B02.png", "prompt": "The attached image is the LOCATION PHOTOGRAPH (loose spatial reference only).\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 church worship hall, at the wooden basement hatch in the floor amid the nighttime search.\n\nSHOT TEXT (authoritative, Korean): 예배소 바닥의 나무 지하실 문을 손가락으로 가리키며 입을 크게 벌려 소리치는 민병대원의 역동적인 자세.\n\nCARRIED STATE (persist exactly): A basement access door has been located in the church floor. The intercut seawall still has severe cracks and seepage, with a vehicle convoy travelling along the embankment 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: Finish the chapel approach from slightly above the militia member and oblique to his forward axis, tilting down to retain his open mouth, pointing hand, and the floor entrance together. Place him in the left half, bent forward with his weight committed toward the wooden basement door in the lower right; his attention remains directed down at the discovery as he shouts. Let the closing camera distance provide the emphasis, without changing the established viewing side.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: Wooden basement door indicated by the militia member in the lower-right of the frame, midground.\n- KEY BACKGROUND ELEMENTS: Wooden basement door (Discovered in the chapel floor) — Its upper face is visible obliquely beneath the pointing hand; used as Receives the pointing gesture in the lower right while remaining smaller than the figure; Chapel floor (Being searched) — Seen from a downward oblique angle around the basement entrance; used as Connects the discoverer's stance to the entrance without introducing additional furnishings.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L190B02.png" ] ], "asset_id": "b50d98cd-e71c-4b90-928e-99153b8d142f" }, "S33sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S33sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S34sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S34sh3.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L188B02.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: In the third-floor corridor of the illuminated refugee administration building, directly outside a locked detention-room door.\n\nSHOT TEXT (authoritative, Korean): 양손에 거머쥔 붉은 소화기가 단단한 문고리에 강하게 충돌한 순간의 역동적인 현우의 자세.\n\nCARRIED STATE (persist exactly): The third-floor room door is still shut and resisting forced entry; its handle has not yet broken free. The management office remains lit. 현우: He holds the fire extinguisher for battering the door, with facial bruises, an injured leg and no outer garment. The contact card remains concealed in his shoe.\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 just behind and beside 현우 outside the doorway, below shoulder height and looking obliquely past his arms while staying outside the extinguisher's swing. Place his torso on the left and the handle at center-right, catching his forward weight transfer as both hands drive the red extinguisher into contact; his attention is fixed on the handle rather than the lens. Keep both gripping hands and the impact visible together, shifting only slightly outward if the near forearm masks contact, with the extinguisher occupying less than a third of the frame.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Office door and handle (Door still resisting entry as the handle is struck) — The exterior face and projecting handle are visible at an oblique angle; used as Anchor the impact point at center-right and establish the threshold for the following entry; Red fire extinguisher (Held in both hands and striking the handle) — Its body crosses diagonally from 현우's grip toward the handle; used as Connect the two-handed effort to the contact point without obscuring either.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L188B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "3c73b6f6-486c-4b9f-93e3-d1822cce367e" }, "S34sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S34sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S35sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S35sh1.png", "plate_path": null, "prompt": "Draw 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 an outdoor lane among the refugee settlement's makeshift homes, under emergency warning lights as the ground trembles.\n\nSHOT TEXT (authoritative, Korean): 요란한 비상 사이렌 불빛 아래, 흔들리는 바닥을 디딘 채 공포에 질린 표정으로 허공을 올려다보는 난민촌 사람들의 굳은 전경.\n\nCARRIED STATE (persist exactly): The seawall breach remains open and seawater is advancing into the nighttime settlement. The ground is beginning to shake.\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 motionless on the group's escape side, below adult eye level and oblique to their bodies, with a slight upward inclination that still retains planted feet near the lower edge. Arrange the frightened residents across the middle distance with open escape space in the foreground, their attention lifted toward the threat above and beyond the frame. Their alarmed hesitation should be asynchronous: one weight shift caught halfway, another person's knees bent, and differing shoulder and head angles, all responding to the same trembling ground rather than posing in a uniform row.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Refugee-camp ground (Beginning to shake beneath the residents) — Visible beneath their unevenly braced feet and into the foreground; used as Connect bodily instability to the space along which the camera will retreat.\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": [], "asset_id": "d7134b9e-61cf-401a-932e-ef0971017649" }, "S35sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S36sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S36sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L176B01.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 dark underground sewer beneath the refugee settlement, at the tunnel section where seawater bursts toward the fleeing group.\n\nSHOT TEXT (authoritative, Korean): 구도환의 등 뒤쪽 터널 끝에서 거대한 바닷물이 무서운 기세로 터져 나오는 찰나.\n\nCARRIED STATE (persist exactly): Seawater bursts into the underground sewer passages and begins filling them. Charlie retains his old coat, hat and radio as the flood reaches the escape route. 구도환: He is running through the sewer escape route.\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 withdrawal ahead of and laterally offset from 구도환, low above the passage floor and looking back past his side rather than along his frontal axis. Catch his forward stride at the left frame edge, his attention fixed on the escape route beyond the camera's right side, while the tunnel behind him stays exposed through the center and right as seawater erupts into it. Hold this diagonal relationship as the retreat begins, showing the surge behind him before it reaches his body.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Unobstructed tunnel and erupting seawater behind 구도환 in the middle-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: Sewer passage behind 구도환 (Being invaded by seawater) — Its length recedes obliquely behind the figure rather than being blocked by his torso; used as Provide an unobstructed central corridor for the flood reveal; Erupting seawater (Bursting into the tunnel behind 구도환); used as Advance through the central and right background toward the foreground escape route.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L176B01.png" ], [ "char:구도환", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/d5805340-a6a5-4677-96e4-1c7e8b89a6ef.png" ] ], "asset_id": "6c12b889-9578-4c38-95ec-c46ab7596741" }, "S36sh7": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S36sh7.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L176B01.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: Under the floodwater outside the sewer outlet, in the inundated refugee settlement.\n\nSHOT TEXT (authoritative, Korean): 수중에서 앰버의 작은 손목을 꽉 움켜쥔 찰리의 커다란 금속 손 클로즈업.\n\nCARRIED STATE (persist exactly): The sewer is inundated, and the flood has forced the escape into open water. Charlie is submerged and swimming, with his worn metal body and old disguise now soaked. 앰버: She has been swept out of the sewer and is submerged, struggling in the seawater with soaked clothing.\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: Underwater outside the sewer, track level with the joined hands from 앰버's side, looking diagonally across the grip and remaining offset from 찰리's reaching forearm. Place 앰버's small wrist through the lower center and 찰리's larger metal hand around it at center, with both forearms continuing toward opposite frame edges and partial bodies providing natural scale. Keep faces outside the crop as both remain oriented toward their off-screen swimming route, using the unbroken grip rather than a new camera angle to carry the rescue.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Seawater outside the sewer (Surrounding the submerged pair as they swim) — The hands and partial bodies are viewed directly through the surrounding water; used as Maintain underwater spatial continuity while leaving the joined hands clearly legible.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L176B01.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ] ], "asset_id": "e8a72824-fe1d-4ef0-b1b3-784cdbd25fdc" }, "S37sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S37sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L188B01.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: Beside corridor windows on an upper floor of the refugee administration building, with the dark incoming surge visible outside.\n\nSHOT TEXT (authoritative, Korean): 두 눈을 질끈 감은 채 현우의 머리를 자신의 가슴팍에 빈틈없이 끌어안은 미연의 절박한 자세.\n\nCARRIED STATE (persist exactly): The management-office corridor windows are still intact as the approaching tidal wave fills the view outside. 미연: Her face remains badly swollen from the beating. She stands with both arms closed tightly against her chest in a protective embrace. 현우: He retains facial bruising and the untreated dog-bite wound on his leg, and his outer garment remains removed. Yoon's contact card is concealed inside his shoe.\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: Finish the inward dolly on the corridor's interior side at 미연's shoulder height, looking obliquely across her face and slightly down toward 현우's head. Her tightly closed eyes occupy the upper-left portion of the frame, while her enclosing arms and his buried head form a compact shape below; he turns inward against her chest rather than toward the lens. Hold this final compression before the retreat, with only narrow portions of the corridor visible around their embrace.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Upper-floor corridor (The pair have stopped here and embraced) — The corridor interior appears obliquely around the pair; used as Narrow peripheral context keeps the embrace physically grounded without competing with the faces and arms.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L188B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:미연", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/e9e0c616-aa12-4a9f-a62c-9ab2d808e06c.png" ] ], "asset_id": "eda28974-c427-4e36-a410-4567430cdb20" }, "S37sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S38sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S38sh2.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 floating container panel amid the submerged refugee settlement, visible across open floodwater at dawn.\n\nSHOT TEXT (authoritative, Korean): 멀리 떨어진 판자 위에 축 늘어진 채 누워있는 미연의 핏기 없는 전신을 바라보는 현우의 시점 쇼트.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Miyeon is stretched out on a floating container panel, her body supported by the panel and her abdomen bleeding from a puncture wound. The source does not specify whether she rests on her back or side, her head's direction, or the arrangement of her arms and legs.\n\nCARRIED STATE (persist exactly): At dawn, separate container panels float on the sea amid the flood wreckage. Storage boxes remain inside the container that has served as overnight shelter. 미연: She lies soaked and motionless on a floating container panel, with her face still swollen. Her abdominal puncture wound is already bleeding, although it is discovered only upon closer approach.\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: Settle the pan into a stationary view from 현우's reclining eye position just above board level, looking almost horizontally across the water. Place 미연's entire pale, limp body on the distant container board in the upper-right middle distance, seen obliquely along her body, with a broad interval of water separating her from the viewing position. Keep 현우 completely outside the image, and let 미연's closed eyes and unresponsive posture register without moving closer or revealing wound details at this distance.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 미연's container board (Floating on the water with 미연 lying on it) — Its supporting face and a narrow edge are visible from the low, oblique viewpoint; used as Supports the distant full-body silhouette and remains small within the surrounding water; Intervening sea (Separating 현우's viewing position from 미연's board); used as A broad, uninterrupted interval makes the distance and helplessness readable.\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:미연", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/e9e0c616-aa12-4a9f-a62c-9ab2d808e06c.png" ] ], "asset_id": "316d049e-c00b-4b04-9191-f52cdd862974" }, "S38sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S38sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S39sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S39sh2.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 muddy water surface over the submerged refugee settlement, among floating boards and debris in daylight.\n\nSHOT TEXT (authoritative, Korean): 탁한 흙탕물 속에서 널빤지를 꽉 움켜쥔 채 버티고 있는 페드로와 구도환의 지친 상체.\n\nCARRIED STATE (persist exactly): The refugee settlement is submerged in daylight, with containers and other wreckage afloat. 페드로: He is afloat in the flooded settlement, wet from immersion. 구도환: He is afloat in the flooded settlement, wet from immersion; his condition is not yet established.\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 steadily beside 페드로 and 구도환 from a three-quarter angle close above the water, looking slightly down at their exhausted upper bodies and gripping hands. Place 페드로 left and nearer, with 구도환 right and slightly farther along the plank; one draws an elbow inward while the other hangs more heavily through his forearms, and both look down toward their grip. Keep the plank across the lower middle at its natural scale, with the opaque muddy water visible around their bodies, presenting direct observation rather than a drone-screen image.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Floating plank (Gripped tightly by both survivors) — Its upper face and near edge run obliquely across the lower middle; used as Links the two different gripping postures without occupying more than two-fifths of the frame; Floodwater (Opaque and muddy around the floating survivors); used as Surrounds the visible upper bodies and establishes their lack of secure footing.\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:페드로", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/037b034f-6a83-4071-99b1-32d2e4066fc0.png" ], [ "char:구도환", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/d5805340-a6a5-4677-96e4-1c7e8b89a6ef.png" ] ], "asset_id": "019a6799-a901-4c35-8fb2-1592f569dde6" }, "S39sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S40sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S40sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L194B02.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 an empty asphalt road at the outer edge of the refugee settlement, along the escape route toward the city.\n\nSHOT TEXT (authoritative, Korean): 텅 빈 잿빛 아스팔트 도로 위, 땀과 눈물로 엉망이 된 얼굴로 멍하니 서 있는 앰버의 지친 상체.\n\nCARRIED STATE (persist exactly): It is daylight on the outskirts of the flooded refugee settlement. 앰버: She has stopped from exhaustion, with tears covering her face and her attention repeatedly turning backward.\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 stationary near 앰버's front three-quarter side, slightly above her eyes with a gentle downward tilt, framing her exhausted upper body left of center. Catch the arrested momentum of her run in uneven shoulders and a backward head turn, her tear- and sweat-marked face directed toward the route they have just fled beyond the frame rather than toward the lens. Leave an open wedge of empty asphalt to the right, holding the entry composition before moving around her near shoulder.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Asphalt road (Empty in the visible portion around 앰버) — The road surface recedes obliquely behind her; used as An open right-side wedge isolates her stalled movement without introducing other street activity.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L194B02.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "e04d942a-da09-45cf-bfc4-228283629bc9" }, "S40sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S40sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S41sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S41sh22": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S41sh26": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S42sh2": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S42sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S42sh19": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S43sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S43sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L196B01.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: At a sofa inside the defense minister's executive office, under ordinary office lighting during the phone call.\n\nSHOT TEXT (authoritative, Korean): 집무실 소파에 깊숙이 기댄 채 서늘한 눈빛으로 허공을 응시하는 국방장관의 여유로운 상체.\n\nCARRIED STATE (persist exactly): The knife previously thrown into the militia-office wall remains embedded there. 국방장관: He is in his own office, engaged in the same telephone call.\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 in the prescribed static sofa-side position at seated chest height, viewing 국방장관's upper body from a three-quarter angle with a slight upward tilt. Set him left of center, sunk deeply into the sofa, leaving open room space on the right along his distant, unfocused eyeline. His attention belongs to the telephone exchange while his cold eyes rest beyond the frame, making the relaxed backward weight—not lens contact—the expression of authority.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 집무실 소파 (Occupied by the deeply reclining 국방장관) — An oblique section of its seat and back is visible beneath and behind him; used as Supports the backward body weight and visually substantiates his ease.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L196B01.png" ], [ "char:국방장관", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/4796782a-f559-45e9-be9f-a82a3d56f904.png" ] ], "asset_id": "b8079413-7782-40e9-9e87-17589712c08c" }, "S43sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S43sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S44sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S44sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S45sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S45sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S45sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L199B05.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 camper's compact driving cab at night, at the steering wheel and rearview mirror, with a small rear-compartment lamp behind.\n\nSHOT TEXT (authoritative, Korean): 백미러를 통해 뒷좌석을 차갑게 노려보는 현우의 매서운 눈매 클로즈업.\n\nCARRIED STATE (persist exactly): Heavy rain continues around the moving camper; its headlights remain off and the small rear lamp remains lit. The luggage and supplies remain inside. 현우: He remains at the wheel with facial bruises and the untreated leg wound. Yoon's contact card remains hidden in his shoe.\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 between the front seats at rearview-mirror height, offset toward the passenger seat and outside the reflected line connecting 현우 to the rear seats. Tighten on his reflected brow and narrowed eyes, retaining the mirror rim and a soft border of cabin around it; the mirror occupies about two-thirds of this human-centered close frame. His reflected gaze passes beside the lens toward the rear seating beyond the crop, with mirror reversal preserved and no direct eye contact.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Rearview mirror (Reflecting 현우's narrowed eyes) — Its reflective face is visible with a small rim retained; the reflected face is mirror-reversed and its eyeline runs toward the rear seats rather than the lens; used as Frames the indirect view and separates his hostile scrutiny from direct audience address; Front cabin (Occupied driving compartment) — Only soft peripheral fragments remain around the mirror; used as Maintains an interior spatial reference around the reflected close-up.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L199B05.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "4645f18f-c0de-40a0-9d9e-1657b538dfe5" }, "S45sh9": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S45sh9.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L199B03.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 camper's rear seating area, beside a leaking window under the single small rear lamp.\n\nSHOT TEXT (authoritative, Korean): 창문 틈새로 들이치는 빗물을 막기 위해 헝겊을 강하게 누르고 있는 앰버의 찡그린 상체.\n\nCARRIED STATE (persist exactly): Rainwater leaks through the camper's roof and window frames despite cloth pressed against the openings. The headlights remain off and the small rear lamp remains lit. 앰버: She presses clothing against a leaking window frame.\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: Finish the lateral track on the cabin side of 앰버 at seated shoulder height, slightly behind her window-facing axis and tilted gently upward. Place her strained upper body across the left and center, with her near profile, pressing hands, and leaking window gap held together on the right; her lowered eyes stay on the cloth's contact with the gap. Ease to a stop without changing distance, letting the pressure through her shoulders and forearms carry the moment.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Rear-seat window frame and gap (Rain entering through the gap) — Interior edge seen obliquely beside 앰버's hands; used as Keeps the source of her effort visible beside her grimacing profile; Cloth (Pressed firmly against the leaking window gap) — Compressed between her hands and the window frame; used as Small contact detail linking her upper-body tension to the leak.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L199B03.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "b921f333-63fe-415e-a03d-af2cd1337f45" }, "S46sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S46sh17": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S46sh17.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L202B04.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: At the group's makeshift resting spot inside the dusty abandoned-library reading room, in the dim nighttime interior.\n\nSHOT TEXT (authoritative, Korean): 찰리의 손에 들린 책을 향해 거칠게 팔을 뻗어 타격하는 mid-impact 순간의 현우.\n\nCARRIED STATE (persist exactly): The abandoned reading room remains dusty and cobwebbed, with disordered shelves and books. Opened canned food and the scavenged bags remain at the makeshift eating place, while the Ubik book is open to its next-generation robot chapter. 현우: He remains at the eating place with facial bruises and the untreated leg wound. The contact card is still inside his shoe, and the scavenged disposable phone remains among his belongings. 찰리: He holds the Ubik book open for display, retaining his worn body, earlier disguise and store blanket.\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: Settle the lateral move at impact from the children's side of the facing axis, at 현우's seated chest height with a slight upward tilt. Favor 현우's upper body on the left and 찰리's partial profile and presenting hands on the right, keeping the book and striking forearm unobstructed in the lower center; both direct their attention downward to the contact point. Emphasize the change in 현우's arm position rather than a new camera angle, cropping 앰버 and 라울 out while the book is still at 찰리's hands.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Presented robotics book (Open to the next-generation robot chapter and still at 찰리's hands during impact) — The open printed pages are angled toward 현우, with part of the chapter visible obliquely to camera; used as Small central contact point joining the extended forearm and 찰리's hands; Reading-room bookshelves (Disordered and dusty) — Partial shelf faces remain behind the two figures; used as Soft spatial context without cluttering the impact silhouette.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L202B04.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ] ], "asset_id": "c2cd0399-5f87-4274-8987-1f4261def294" }, "S46sh28": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S47sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S47sh9": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S47sh9.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L202B02.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: In a secluded outdoor corner beside the abandoned library, away from the reading-room group in the morning.\n\nSHOT TEXT (authoritative, Korean): 도서관 외진 구석 바닥에 쭈그려 앉아 벗어놓은 신발 안에서 빳빳한 카드를 반쯤 뽑아 올린 자세로 멈춘 현우의 거친 손 클로즈업.\n\nCARRIED STATE (persist exactly): The completed portions of the colorful Haenam mural and its written message remain on the library wall. The camper remains outside the abandoned library. 현우: He has removed one shoe and is extracting the intact contact card concealed inside it, with the disposable phone ready. His facial bruises and untreated leg wound remain.\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 low beside 현우's crouched body, looking diagonally downward in a close view of his rough hands and the removed shoe. His hands occupy the center, the stiff card remains halfway out of the shoe below them, and a cropped knee at the left provides scale without enlarging either object unnaturally. Keep his face outside the upper edge and his attention directed down to the extraction, holding the moment before the camera rises toward the call.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Removed shoe (Off 현우's foot, with the card being extracted from inside) — Opening faces diagonally upward toward his hands and the camera; used as Reveals the hiding place while remaining smaller than the hand-and-knee context; Contact card (Stiff, intact after the flooding, and halfway withdrawn) — A narrow portion of the contact-bearing face is visible at an oblique angle, without resolving invented contact details; used as Small focal evidence of his concealed means of contact; Secluded library corner floor (Beneath 현우's crouched body and removed shoe); used as Ground plane anchoring the intimate hand detail.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L202B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "198f725a-7e21-4a39-9d9c-8249fc9fea2c" }, "S47sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S48sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S48sh5.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: Inside the camper's front passenger seat, looking through the windshield toward a distant road checkpoint in daylight.\n\nSHOT TEXT (authoritative, Korean): 멀리 도로 끝에 세워진 바리케이드와 경찰 검문소를 바라보며 두 눈을 동그랗게 뜬 앰버의 놀란 얼굴.\n\nCARRIED STATE (persist exactly): The aging camper has a leaking roof and window frames, with the gathered supplies aboard; a police checkpoint stands farther along the road through barren fields, dead trees and abandoned houses. Charlie retains his worn metal body and blanket covering and is in the rear seat. 앰버: She occupies the passenger seat with the map and wears the replacement shoes obtained at the unmanned store.\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: Settle the interior track beside the outer edge of the front passenger seat, at seated shoulder height and ahead of 앰버's shoulder, looking slightly upward at her three-quarter face. Her widened eyes occupy the right half of the close frame, directed past the left edge toward the distant checkpoint rather than the lens; retain a narrow seat edge for spatial context. Emphasize only the change in her attention, keeping the established camera distance and interior exposure steady.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Front passenger seat (Occupied by 앰버) — A narrow portion of the seat beside her shoulder is visible; used as Grounds the close reaction within the vehicle without revealing the other passengers.\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:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "28aa3148-695f-44d5-9beb-819eb9dbb531" }, "S48sh16": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S48sh22": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S49sh14": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S49sh14.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L205B01.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 service-station convenience store, near the medicine aisle, in daytime shop light.\n\nSHOT TEXT (authoritative, Korean): 아이들 등 뒤에서 산탄총 총구를 차갑게 겨누고 선 조일광의 위협적인 전신.\n\nCARRIED STATE (persist exactly): The camper is outside at the fuel pump with the luggage reloaded, and the shop television carries the wanted report. Charlie retains his worn metal body and blanket covering and holds the medicine bottle taken from the medicine section. 조일광: He wears a military uniform with medals and a Marine Corps cap. He holds a shotgun in an aiming position. 앰버: She is inside the mart near the medicine section, still wearing the replacement shoes. 라울: He is inside the mart near the medicine section.\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: Slow the lateral track behind and slightly beside 앰버 and 라울, keeping the lens below their shoulder line and angled slightly upward along the store aisle. Their turned shoulders form unequal foreground edges, with 앰버 already looking up toward the threat and 라울 still completing his turn; beyond them, retain 조일광's entire body, Marine cap, decorated uniform, feet, and shotgun. 조일광 braces the weapon toward the children and looks down their direction, with the muzzle visibly offset from the lens; the reveal through their changing positions is the sole emphasis.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Store shelving and merchandise (Still in place before the later collision) — Shelf fronts and receding ends border the confrontation aisle; used as Define the shared space and frame the gunman's full-body reveal; Shotgun (Raised and aimed at the children) — Seen obliquely along its side, with the muzzle directed toward the foreground children rather than the camera; used as Connects the distant threat to the foreground shoulders without oversized perspective.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L205B01.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ], [ "char:라울", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8a273153-5439-457f-8304-2020bf6ac74b.png" ] ], "asset_id": "4280069e-a896-4a04-9a87-3534c1d3220b" }, "S49sh47": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S49sh51": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S49sh51.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L205B02.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 overturned camper's broken window at the roadside rubbish embankment, seen from the wreck's interior.\n\nSHOT TEXT (authoritative, Korean): 깨진 창문 밖에서 거꾸로 뒤집힌 차 안을 심각한 표정으로 들여다보는 은영과 태진의 상체.\n\nCARRIED STATE (persist exactly): The camper lies completely overturned with shattered windows, smoke inside and an interior bulb flickering faintly. Charlie is unconscious inside with the damaged shoulder sustained during the shooting. 태진: She stands outside the wreck looking into it and has short bobbed hair. 은영: She stands outside the wreck looking into it.\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 low inside the overturned camper beside 현우, ease the forward move to a stop and look obliquely upward through the broken window, remaining off both women's frontal axes. Frame 은영's upper body on the left and 태진's on the right within the opening, with 은영 bending nearer and 태진 inclining her head at a different angle as both inspect 현우 and the occupants below the frame. Keep the window rim at the margins and preserve their actual faces without subjective distortion; only the closing camera distance changes.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Broken camper window opening (Broken in the overturned vehicle) — The interior-facing rim surrounds an unobstructed view of the women outside; used as Creates an irregular frame around the upper-body two-shot without treating the view as a reflection; Overturned interior edges (Inverted after the crash) — Partial interior surfaces enter the lower and side margins at their overturned angles; used as Establishes the camera's vulnerable position inside the wreck.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L205B02.png" ], [ "char:태진", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/eb59965c-6428-444f-b7e2-60a3b3bd9ba8.png" ] ], "asset_id": "f4934d4b-9116-40dd-a1b2-2a834fade0e4" }, "S50sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S50sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L209B01.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: In the resting corner inside an auto-repair warehouse, with band posters nearby and daytime ambient light from the workshop.\n\nSHOT TEXT (authoritative, Korean): 태진의 뒷모습을 날카롭게 노려보며 바닥의 커다란 펜치를 향해 손을 뻗은 현우의 굳은 상체.\n\nCARRIED STATE (persist exactly): Rock-band posters cover the room, with a large pair of pliers within reach and a large speaker in the repair area. The camper is under repair and has extensive damage to its engine and brakes. 현우: He has awakened with his injured leg bandaged and visible treatment marks elsewhere on his body. The contact card remains concealed in his shoe.\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 gently along 현우's near side at seated chest height, well off his eyeline toward the repair area, and tilt slightly down to include his reaching arm and the floor. Hold his rigid upper body in the left foreground, the large pliers at natural scale in the lower center, and 태진's back farther right beside the camper; 현우 keeps his narrowed gaze fixed into that distant repair area rather than checking his hand. 태진 remains bent toward the vehicle, absorbed in repairing it, while the extension of 현우's arm supplies the single emphasized positional change.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: Large pliers on the floor beneath 현우's reaching hand in the lower-center of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: Large pliers (On the floor, not yet grasped) — Lie obliquely below 현우's approaching hand; used as Make his defensive intention legible without enlarging the tool beyond realistic scale; Damaged camper (Under repair by 태진) — A partial side section appears beside 태진 in the background; used as Anchors her activity and the depth separating the characters; Rock-band posters (Attached to the room's walls) — Printed band imagery faces into the room and is visible obliquely, without invented readable titles; used as Gives the unfamiliar space its scripted visual identity.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L209B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "36a68918-70ef-4f62-a881-1c4458c88531" }, "S50sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S50sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S51sh10": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S51sh10.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L211B01.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: At a dining table inside the converted-container canteen beside the auto-repair shop, in daytime ambient light.\n\nSHOT TEXT (authoritative, Korean): 해남이라는 말에 눈을 부릅뜬 채 앰버를 향해 고함을 치듯 입을 크게 벌린 현우의 분노한 얼굴.\n\nCARRIED STATE (persist exactly): Bowls of rice soup are in the container dining area beside the repair shop. Charlie has been repaired and can rotate his arm again; the previous shoulder malfunction should no longer be shown as active. 현우: His leg remains bandaged and his body retains treatment marks. The contact card remains hidden in his shoe.\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: Tighten the approach from just behind and beside 앰버's shoulder, keeping the lens slightly below 현우's eyes and tilted upward, safely offset from their direct confrontation axis. His three-quarter face occupies most of the center-right frame, with only a narrow edge of 앰버's shoulder at left; his widened eyes and open mouth are directed toward her face just outside that edge, never toward the lens. 앰버 holds her turned shoulder toward him as he leans into the reprimand, while the decrease in camera distance alone intensifies the shot before the later lateral move toward 찰리.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Container dining-space interior (Occupied during the conversation) — A narrow, softly resolved interior background remains behind 현우; used as Retains the shared location while excluding unrelated diners from the tight confrontation.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L211B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "30650cc7-b31b-433e-b1bc-a519c8b82177" }, "S51sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S51sh19": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S51sh19.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L211B02.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 departing camper's passenger area, with daylight entering through the windows facing the auto-repair shop.\n\nSHOT TEXT (authoritative, Korean): 출발하는 차 안에서 은영과 태진을 향해 양손을 높이 든 채 활짝 웃는 앰버와 라울의 환한 상체.\n\nCARRIED STATE (persist exactly): The camper is operational again and has the luggage loaded for departure. Additional food and Amber's medicine have been placed aboard. 앰버: She is aboard the departing camper. 라울: He is aboard the departing camper, with his earlier injury treated.\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: Remain fixed inside the departing camper, inward from the children and slightly below their eyes, viewing their upper bodies directly at an oblique three-quarter angle. Place 앰버 left of center and 라울 right of center, retaining both pairs of raised hands with unequal elbow bends and slightly staggered hand heights as they smile toward 은영 and 태진 outside the frame. Preserve the interior camera position through the departure, letting the children's outward attention, rather than a lighting change or frontal pose, complete the farewell.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Camper interior (Occupied by the children as the vehicle departs) — An oblique interior view establishes the children's outward-facing position; used as A narrow contextual surround anchors the upper-body farewell without competing with their hands.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L211B02.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ], [ "char:라울", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8a273153-5439-457f-8304-2020bf6ac74b.png" ] ], "asset_id": "9849057f-ede4-459a-804c-8659aaf33808" }, "S52sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S53sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S53sh2.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 map-covered desk inside an urban militia office, under ordinary office lighting.\n\nSHOT TEXT (authoritative, Korean): 핏발 선 눈으로 두 주먹이 책상에 강하게 충돌한 순간, 고래고래 소리치듯 입을 크게 벌린 박철진의 광기 어린 얼굴.\n\nCARRIED STATE (persist exactly): A map of the Korean Peninsula lies spread across the militia office desk.\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: Reach the endpoint of the inward move outside the established desk corner, at 박철진's upper-chest height with a slight upward tilt and an oblique view of his face. His bloodshot eyes and shouting mouth occupy the upper center while both fists strike along the lower edge, leaving a narrow strip of the map-bearing desktop visible. He pitches toward the desk but directs his accusation past it toward the off-screen room, making the reduced camera distance the principal emphasis.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Desk corner (Receiving the impact of both fists) — The near corner crosses the lower edge obliquely; used as Connects the facial outburst to its physical impact without oversized foreground distortion; Map of the Korean Peninsula (Spread across the desktop) — A partial view of the upward-facing printed map is visible between and behind the fists; used as Retains the search context at the frame boundary.\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:박철진", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8426809f-6189-44b9-b275-da8ab73d1352.png" ] ], "asset_id": "70416dc7-78a1-45aa-80e3-0fdad91a577a" }, "S53sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S54sh2": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S54sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S54sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S55sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S55sh3.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L199B03.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 camper's passenger area, beside a window overlooking roadside woodland in daylight after rain.\n\nSHOT TEXT (authoritative, Korean): 창밖의 숲 쪽을 향해 검지손가락을 길게 뻗은 라울의 상체.\n\nCARRIED STATE (persist exactly): A rain shower has recently passed, and the operational camper carries the luggage, added food and medicine supplied at the repair shop. 라울: He is riding in the camper, soaked and exhausted, with his earlier injury treated.\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: Reach the close endpoint of the aisle track beside the rear seats, slightly above 라울's seated eyes and angled diagonally toward him and the window. Keep his rain-soaked upper body in the left half, his extended index finger crossing toward the upper-right window area, and enough forest beyond it to establish the direction of the search. His eyes follow the pointing line toward the trees beyond the right edge, with the extended arm supplying the principal change before the camera continues toward the driver.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: Forest visible beyond the camper side window in the upper-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: Camper side window (Providing a view of the forest outside) — Seen obliquely from the aisle, with the forest visible beyond the pointing hand; used as Connects the interior gesture to its exterior destination without requiring the camera to leave the camper; Forest beside the route (Visible outside as a possible route taken by 찰리) — Appears beyond the window toward the upper right and continues outside the crop; used as Provides an intelligible destination for the pointing line; Rear seating (Occupied by 라울) — A partial seat edge remains beneath his leaning torso; used as Anchors his seated posture and prevents the pointing gesture from reading as a standing pose.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L199B03.png" ], [ "char:라울", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8a273153-5439-457f-8304-2020bf6ac74b.png" ] ], "asset_id": "30ef55b8-86fa-49ef-81a1-ac257a19f52a" }, "S55sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S56sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S56sh5.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 muddy ground near the stranded camper in the marsh, along the search route for boards or timber.\n\nSHOT TEXT (authoritative, Korean): 늪지대 바닥의 진흙 속에 선명하게 찍힌 거대한 신발 자국을 향해 쪼그려 앉은 앰버의 자세.\n\nCARRIED STATE (persist exactly): The camper is stuck in the swamp, and large shoeprints mark the nearby mud beside a no-entry sign and a badly corroded radiation warning sign. Charlie is already in the forest wearing the oversized straw hat, rubber boots and colorful raincoat. 앰버: She is searching for wood near the large shoeprints and remains damp and tired from the preceding journey.\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: Observe directly from low behind and beside 앰버, looking obliquely downward beside her shoulder rather than across it, holding the stable midpoint of the lateral track. Her complete crouched figure occupies the left third, her head lowered toward the large shoeprint at lower right; keep the entire impression visible with surrounding ground as a scale reference, while 현우 remains outside the crop. Let camera distance carry the emphasis, retaining her downward attention and settled crouch.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Large shoeprint in mud (Clearly impressed in the swamp ground) — The complete impression is visible obliquely from above; used as Lower-right focal evidence, kept smaller than the crouching figure; Swamp ground (Mud surrounding the shoeprint); used as Continuous ground plane connects 앰버 to the impression.\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:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "e0803289-5e5b-4591-a71c-27038d182ed9" }, "S56sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S56sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S57sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S57sh3.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_ruined_village_square_sel.png", "prompt": "The attached image is the LOCATION PHOTOGRAPH (loose spatial reference only).\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: Along the village street beside the passing prisoner truck, amid a crowd of masked guards and residents.\n\nSHOT TEXT (authoritative, Korean): 창과 몽둥이를 높이 치켜든 채 트럭을 향해 함성을 지르는 하회탈 병사들과 사람들의 광기 어린 전경.\n\nCARRIED STATE (persist exactly): A barred cage is mounted on the transporting truck, and a tall water-tank-like tower stands in the village. Water bottles are being distributed nearby.\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 inside the cage's side, begin the established pan obliquely downward across the adjacent crowd, observing directly through the gaps rather than adopting either captive's eyes. Keep a narrow cage bar at the left edge and spread 하회탈 병사들 and 사람들 across the middle and lower frame, their heads lifted and shouts directed toward the truck above them, not toward the lens. Show raised spears and clubs at different phases and angles, with uneven shoulder turns and spacing; stop this opening composition before the water distribution enters view.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Cage bars (Enclosing the captives on the moving truck) — Seen obliquely from inside, with the crowd visible between them; used as A thin edge obstruction establishes the observer's confined position; Raised spears and clubs (Held aloft by the shouting crowd) — Their tips and shafts form unequal diagonals rather than matching verticals; used as Connects the lower crowd to the space beside the elevated truck; Hahoe masks (Worn throughout the visible crowd) — Shown in varied upward-facing three-quarter and profile views; used as Creates a collective threat without duplicating individual poses.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_ruined_village_square_sel.png" ] ], "asset_id": "eea69cbc-ad3c-4b30-99fa-fe8f252efa26" }, "S57sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S57sh5.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 truck's rear loading edge in front of the village church, where bound prisoners are pulled down.\n\nSHOT TEXT (authoritative, Korean): 성당 건물 앞, 트럭 적재함 밖으로 현우를 거칠게 끌어당기는 하회탈 병사들의 굳은 상체, 그 힘에 의해 현우의 몸이 트럭 밖으로 막 쏠려 나온 mid-action 순간.\n\nCARRIED STATE (persist exactly): The truck and its barred cage are stopped outside the church-like building. A Hahoe mask covers the face of the outstretched-armed Jesus statue. 현우: He is bound while being unloaded from the truck, retaining his treated injuries. The contact card remains hidden in his shoe.\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 the explicit arrival cut, observe directly beside the stopped truck from below the soldiers' shoulders, using the prescribed three-quarter side view with a slight upward inclination. Keep the bed edge at right and the 하회탈 병사들 at left as 현우's bound upper body tips diagonally out toward them, his eyes lowered toward the ground beyond the crop. Freeze the pull before his weight settles: one soldier leans back while another braces through a bent elbow, both watching their grip below, making body displacement the sole action emphasis.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: truck bed edge in the middle-right of the frame, midground.\n- KEY BACKGROUND ELEMENTS: Truck bed edge (Stationary during the captives' removal) — The side edge recedes diagonally from the right of frame; used as Fixed reference proving that 현우 is being pulled out rather than pushed aboard; Church-like building (Behind the stopped truck) — A partial exterior view remains behind the extraction; used as Maintains the destination context without competing with the bodies.\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:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "6666cfb4-3bf5-43d4-ac6f-3942d2bd5e0a" }, "S57sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S58sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S58sh5.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L220B01.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 approach to the raised platform inside the ruined village church, lit by daylight through stained glass.\n\nSHOT TEXT (authoritative, Korean): 육중한 황금빛 하회탈을 쓴 거대한 백산이 화려한 의복을 입은 채 단상을 향해 한쪽 발을 공중에 든 mid-action 자세의 위압적인 전신.\n\nCARRIED STATE (persist exactly): Daylight filters through stained glass into the damaged church. Charlie is already confined in a steel cage behind the barred entrance, retaining the oversized straw hat, boots and colorful raincoat from his capture. 백산: He has a massive, obese build and wears regal clothing and an intact golden Hahoe mask. His pre-existing radiation-disfigured face remains concealed beneath it.\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: Observe directly from the established low position beside the kneeling captives, tracking laterally at a three-quarter angle to 백산's route while retaining his full body. Place him just right of center with one foot suspended before landing, his masked head directed toward the platform beyond the right edge; leave floor visible beneath the raised foot so the arrested step reads clearly. Bowed 군중들 form an irregular lower background band, with differing depths of inclination, while the emphasis remains on his advancing body rather than a new camera angle.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Platform (Awaiting 백산's arrival) — Its side edge is visible along the rightward route; used as Gives his suspended step a destination without frontal staging; Ruined church interior (Damaged) — Seen laterally behind the approach and bowed crowd; used as Provides scale around 백산's full-body silhouette; Golden Hahoe mask (Worn by 백산) — Visible in three-quarter view, aligned with his route toward the platform; used as Concentrates authority within the full-body 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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L220B01.png" ], [ "char:백산", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/843b7b94-5746-4311-ae8d-735c1b16066b.png" ] ], "asset_id": "6d80eb92-6d35-4bd5-bfec-92b0a707c02a" }, "S58sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S58sh25": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S59sh10": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S59sh10.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L222B02.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 a bare underground village-prison cell, beside its iron bars in the dim light of the dungeon.\n\nSHOT TEXT (authoritative, Korean): 쇠창살 앞의 현우를 향해 둥근 감자를 내민 채 허공에 고정된 수빈의 손.\n\nCARRIED STATE (persist exactly): The cell remains locked, with hay on the floor and pooled water inside; a handful of hay has already been wetted. A potato is being offered inside the cell. 수빈: Her face is scratched and dirty, and pre-existing radiation damage to her torso remains covered by her T-shirt. She holds out a potato.\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: Pause the lateral track inside the cell beside the bars at hand height, using a direct three-quarter view across the space between 수빈 and 현우 without crossing their interaction axis. 수빈's extended hand enters from lower left and holds the potato near lower center, while 현우 remains beyond it at right beside the bars; include portions of both inclined faces and torsos so the modest-sized potato cannot read as an oversized foreground object. Both lower their eyes toward the offered food, with 수빈's elbow still slightly bent and 현우's shoulders compressed after striking the bars, holding the gesture before acceptance.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Potato (Held out by 수빈, not yet accepted); used as Small focal object supported by the hand, with both bodies providing scale; Cell bars (Intact after 현우's attempts to force them) — Seen obliquely beside and behind 현우; both people remain on the same interior side; used as Connects the offered food to the immediate fact of confinement.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L222B02.png" ], [ "char:수빈", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/fc06326d-c2c8-4f56-aeda-26e5efb0d8cd.png" ] ], "asset_id": "0b9b8bdc-0f3c-40f7-a516-90ff65fd60d8" }, "S59sh18": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S59sh36": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S60sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S60sh52": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S60sh52.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L229B03.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 wet ground beside the collapsed village water-tank tower, amid the wreckage in the evening light.\n\nSHOT TEXT (authoritative, Korean): 바닥에 주저앉은 백산의 절반쯤 깨진 황금 가면 아래로 드러난, 흉측하게 녹아내린 화상 얼굴 클로즈업.\n\nCARRIED STATE (persist exactly): The water tower has been shot through and toppled, releasing a large flood of stored water in the sunset light. Charlie bears accumulated dents and holes from the fighting, while B-200's deployed gun-hands remain intact. 백산: He is soaking wet, with his gold Hahoe mask half broken and his radiation-disfigured face exposed. His royal-style clothing has not yet been stripped away.\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 diagonal push close to 백산, slightly above his seated face but below the surrounding soldiers' eye line, looking gently downward at a three-quarter angle. Place the exposed, radiation-disfigured side of his face near center and the remaining gold mask toward the opposite edge, retaining soaked shoulders below as he gathers himself to rise and looks toward the soldiers outside the frame. Capture the instant before his hands conceal the damage, emphasizing proximity alone and preserving the same diagonal for the subsequent withdrawal.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 반쯤 깨진 황금 가면 (Half broken, exposing the previously concealed facial damage) — The remaining outer facial surface and broken edge are visible obliquely beside the exposed face; used as Keeps the failed concealment and the evidence beneath it in the same focal plane.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L229B03.png" ], [ "char:백산", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/843b7b94-5746-4311-ae8d-735c1b16066b.png" ] ], "asset_id": "4d52529a-4346-46e6-91fd-c388e0037459" }, "S60sh63": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S60sh63.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L229B02.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 a ridge overlooking the damaged village at sunset, where the youth and robot sit together.\n\nSHOT TEXT (authoritative, Korean): 노을 빛 아래, 서로를 향해 뻗은 현우의 거친 손과 찰리의 육중한 금속 손이 단단히 맞잡힌 찰나의 클로즈업.\n\nCARRIED STATE (persist exactly): Sunset lights the ridge above the devastated village. Charlie remains badly dented and punctured, with malfunctioning sensors, and extends a metal hand. 현우: He sits on the ridge, visibly battered from the fighting, with a brighter expression and one hand extended.\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 beside the seated pair on the established side of the descent, complete the push just above hand height, looking diagonally downward across both wrists. 현우's rough hand enters from the left and 찰리's heavier metal hand from the right, their fingers closing firmly at center while portions of both forearms and seated laps preserve scale along the edges. Keep both faces out of frame as they remain engaged with each other, emphasizing only the closer distance to their clasp rather than changing the axis or their positions.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 능선의 지면 (Visible only in the small interval beneath the seated pair's forearms); used as Retains the physical setting behind the handclasp without competing with it.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L229B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ] ], "asset_id": "3f4ba729-6aad-496e-a709-774fcddbcb83" }, "S61sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S61sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S61sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S62sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S62sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S62sh18": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S63sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S63sh16": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S63sh17": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S63sh17.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 wheel inside the old truck's compact cab, with warm daylight entering through the passenger-side window.\n\nSHOT TEXT (authoritative, Korean): 조수석 창문으로 들어온 따스한 햇빛을 받으며 입술을 꽉 다문 현우의 결의에 찬 얼굴 클로즈업.\n\nCARRIED STATE (persist exactly): The old village truck continues along the road in daylight. 현우: He remains in the driver's seat, with his fighting injuries still present and a resolute expression.\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: Return exactly to the established passenger-side position inside the cab, close to 현우 at seated mouth height with a slight upward view, and hold still before the planned pan toward 수빈. Frame his profile on the right with breathing room to the left along his forward eyeline toward the road beyond the frame; his lips are pressed together and his driving posture remains taut. Retain a narrow, out-of-focus strip of the cab behind him, making the light on his resolved face the principal emphasis rather than adding a new move.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Truck cab interior (현우 remains seated in the driver's position) — A narrow interior portion behind the driver is seen from the passenger side; used as Maintains the restored present-tense location without bringing 수빈 into this close-up.\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:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "3f3f762f-4c55-4603-a064-cbc070983439" }, "S64sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S64sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S64sh24": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S65sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S65sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S65sh20": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S66sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S66sh26": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S66sh26.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L240B01.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 ruined department store's upper sales level, at the edge of the floor collapse above the dark food section.\n\nSHOT TEXT (authoritative, Korean): 천장 붕괴 구멍 위쪽 가장자리로 소리 없이 다가선 낯선 남자의 짙은 실루엣 전경.\n\nCARRIED STATE (persist exactly): The collapse opening remains far above the food department, and the other exits are blocked. Dusty food stock remains in place, with canned food opened during the wait. 한수: He stands near the upper edge of the collapse opening, with short hair and a sharp gaze.\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: Finish the upper-floor tracking approach behind and slightly beside 한수, observing his full rear silhouette from adult eye height with a gentle downward tilt toward the opening. Place him left of center, caught transferring his weight into the final step toward the rim, his head inclined toward the space below while the opening remains visible beyond his right side. Stop before passing his shoulder, withholding every facial feature and holding this upper-floor position for the subsequent temporal cut.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Collapsed floor opening (Open following the collapse that dropped 현우 and 수빈 below) — The near upper-floor rim is seen obliquely from behind the approaching man; used as Connect the concealed observer to the lower-floor space without revealing its occupants.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L240B01.png" ], [ "char:한수", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/6c8efaab-baad-42e3-bddc-b742ca9825e5.png" ] ], "asset_id": "a6150871-4cda-4118-b344-d3f6a8f9efc5" }, "S66sh36": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S67sh40": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S67sh40.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: In the village's outdoor residential gathering area at night, under military vehicle headlights during the roundup.\n\nSHOT TEXT (authoritative, Korean): 현우의 관자놀이에 차가운 권총 총구를 바짝 들이댄 박철진의 살벌한 밀착 상체.\n\nCARRIED STATE (persist exactly): The village is lit by a bright full moon and military headlights, and the dump truck used for the infiltration remains present. Charlie stands with his previously dented, punctured body and impaired systems; B-200's gun-hands are still intact. 박철진: He holds a raised pistol in a hostage-threatening position. 현우: He is held captive in the village and retains his earlier fighting injuries.\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: Settle at the closest point of the dolly approach beside their shared shoulder line, at 현우's temple height and well off 박철진's frontal axis, making distance the pressure-building change. 현우's tense profile occupies the left foreground and 박철진's upper body the right, with the pistol crossing the narrow interval and its muzzle visibly pressed to the temple; keep both faces and the contact point legible without exaggerating the weapon's size. 박철진 leans into the threat while looking toward 찰리 outside the frame, and 현우 holds his jaw tight with his attention fixed on the same off-screen friend.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Pistol (Muzzle pressed against 현우's temple) — The side of the weapon is visible between 박철진's hand and 현우's head; used as Make the physical threat readable within the shared close framing.\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:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:박철진", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8426809f-6189-44b9-b275-da8ab73d1352.png" ] ], "asset_id": "a32fd8a9-4876-47cb-ad74-e319feef74f4" }, "S67sh49": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S67sh70": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S68sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S69sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S69sh3.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.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: Over the open rear cargo bed of a truck parked beside a shaded rock formation, where a cloth canopy shields the sleepers.\n\nSHOT TEXT (authoritative, Korean): 잠든 일행의 위로 커다란 그늘 막 천을 양손으로 넓게 펼쳐 든 찰리의 역동적인 상체.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Hyunwoo is asleep in the truck's rear cargo bed with his head grouped closely beside Amber's and Raul's heads beneath the shade Charlie provides. The source does not specify his torso's orientation or the positions of his arms and legs.\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Amber is asleep in the truck's rear cargo bed with her head grouped closely beside Hyunwoo's and Raul's heads beneath the shade Charlie provides. The source does not specify her torso's orientation or the positions of her arms and legs.\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Raul is asleep in the truck's rear cargo bed with his head grouped closely beside Hyunwoo's and Amber's heads beneath the shade Charlie provides. The source does not specify his torso's orientation or the positions of his arms and legs.\n\nCARRIED STATE (persist exactly): The roofless truck is parked beside rocks for shade, with a movable shade cloth over the cargo-bed resting area. Charlie adjusts the cloth while retaining his unrepaired battle damage and the recovered B-200 chest component in his possession. 현우: He is asleep in the rear cargo bed, still bearing his recent injuries. 앰버: She is asleep in the rear cargo bed; no treatment of her recent head injury has been established. 라울: He is asleep in the rear cargo bed.\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 same-side dolly backward outside the truck bed, holding at 찰리's chest height with a slight upward tilt and an oblique view of his upper body. Place him on the right with both hands spread above shoulder level, gently drawing the shade cloth across the upper third as he looks down toward the sleepers; the pullback in distance reveals the act of care without changing the established axis. Along the lower-left edge, 현우 lies with his face turned inward, 앰버 rests cheek-down, and 라울 reclines with his head angled toward theirs, their closed eyes and differently settled shoulders preserving the shared head-to-head arrangement.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: shade cloth stretched above the sleeping group in the upper-center of the frame, midground.\n- KEY BACKGROUND ELEMENTS: Shade cloth (Being spread and repositioned by 찰리 to shield the sleepers) — Its underside extends obliquely across the upper third, above rather than in front of the sleeping faces; used as Connect both raised hands and visibly shelter the group without obscuring 찰리's face; Parked truck cargo bed (Stationary, with 현우, 앰버, and 라울 asleep head-to-head) — Seen from outside the same side established during 찰리's approach; used as Provide the shared spatial base beneath the raised cloth; Rock formations beside the truck (The truck is parked in their shade); used as Provide a restrained background boundary locating the resting place.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "acde8000-023e-40d0-b3ff-468a1735a66a" }, "S70sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S70sh5.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: Inside a military-hospital patient room, beside the injured commander's bed under nighttime ward lighting.\n\nSHOT TEXT (authoritative, Korean): 병상에 누운 박철진을 차가운 눈빛으로 멸시하듯 내려다보는 국방장관의 상체.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Park Cheoljin is reclined on a hospital bed, with one eye covered and an arm and a leg immobilized in casts, looking upward with his uncovered eye. The source does not identify the affected sides or specify his limbs' exact placement and his head's angle.\n\nCARRIED STATE (persist exactly): It is night in a military hospital ward containing beds for wounded patients. 박철진: He is reclined on a hospital bed under treatment for severe injuries, with one eye covered and an arm and a leg immobilized in casts. He is only faintly conscious. 국방장관: He has reached the ward and stands looking into it.\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 beside the bed near 박철진's shoulder, looking upward at 국방장관's upper body from a low, three-quarter angle offset from the minister-to-patient axis. 국방장관 occupies the upper-right center with his chin lowered and torso subtly inclined toward the patient, directing his contempt at 박철진 rather than the lens. Keep 박철진's reclined head and near shoulder small in the lower-left foreground, his uncovered eye lifted toward the minister, so the height difference expresses authority without turning the shot into his literal POV.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Hospital bed (Occupied by 박철진 during treatment for his injuries) — The shoulder end and near side are seen from the bedside camera position; used as Anchor the patient's low foreground position beneath the minister's upper body.\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:박철진", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8426809f-6189-44b9-b275-da8ab73d1352.png" ], [ "char:국방장관", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/4796782a-f559-45e9-be9f-a82a3d56f904.png" ] ], "asset_id": "e18af667-e876-4f68-a303-2e9caf00a411" }, "S70sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S71sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S71sh4.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 passenger area adjoining the old truck's open cargo bed during the predawn drive, with faint dawn light outside.\n\nSHOT TEXT (authoritative, Korean): 찰리가 내민 삐뚤빼뚤한 꽃 그림 종이를 쥔 채 어리둥절한 표정을 짓는 앰버의 상체.\n\nCARRIED STATE (persist exactly): The old truck is traveling south at dawn; the violet sketch is drawn on the reverse of a sheet of paper. Charlie remains damaged, with punctured and dented bodywork, an exposed chest opening and malfunctioning sensors, and retains B-200's chest component. 앰버: She holds the sheet bearing the flower drawing. The injury to the back of her head from the rifle-butt blow has not been treated on screen.\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 near the passenger-side dashboard at 앰버's seated shoulder height, finish the pan diagonally back toward her, observing her upper body directly in three-quarter view. Place her at center-right and the paper below her chest, occupying less than a fifth of the image with its drawn face angled toward the camera; catch her puzzled attention shifting from the drawing toward 찰리 off-screen behind her in the truck bed. Keep 찰리 outside this settled composition rather than relocating him into the cab.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Flower drawing paper (Held by 앰버 after 찰리 hands it over) — The reverse side bearing the uneven flower drawing faces obliquely toward the camera; no pigment color is specified; used as Connects her puzzled expression to the inadequate clue in her hands; Truck passenger-side dashboard (Inside the traveling truck) — A shallow oblique edge appears along the lower foreground; used as Locates the camera inside the cab without blocking the paper.\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:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "2d015eed-4450-4662-acb3-9b08a2be5734" }, "S71sh7": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S71sh7.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 the coastal roadside hill where the group has stopped to search the ridges for violet flowers.\n\nSHOT TEXT (authoritative, Korean): 이별을 직감한 듯 눈물이 맺힌 눈으로 찰리를 올려다보는 앰버의 굳은 얼굴 클로즈업.\n\nCARRIED STATE (persist exactly): The truck has stopped near the coastal hills, and the flower sketch remains available without any stated disposal. Charlie's damaged bodywork, exposed chest opening and B-200 chest component persist. 앰버: She has tearful eyes and is wiping away tears; her earlier head injury remains unresolved.\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: Reach the close endpoint beside 찰리's near shoulder, just above 앰버's crouched eye level, looking slightly downward and obliquely across her upward eyeline. Her rigid, tearful face occupies center-left while only a narrow, soft trace of 찰리's shoulder remains at the right edge; she looks up toward him as his attention lowers toward her. Hold this direct over-shoulder observation before she wipes her eyes, emphasizing the approach in camera distance rather than a new lighting or gaze change.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Hillside ground (Where the companions have been playing with soil); used as A softly resolved lower background preserves the outdoor setting without competing with her expression.\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:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "6eebd1f8-91eb-42c9-ac4e-716f7b521fe1" }, "S71sh17": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S71sh17.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.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 old truck's front cab, at the driver and passenger seats facing a vast violet field through the daylight windshield.\n\nSHOT TEXT (authoritative, Korean): 트럭 앞 유리창 너머로 끝없이 펼쳐진 보라색 제비꽃 밭을 멍하니 바라보는 현우와 앰버의 뒷모습.\n\nCARRIED STATE (persist exactly): An extensive field of purple violets stretches ahead, with Ji Dong-hyun's research institute visible in the distance. Charlie retains his damaged bodywork, chest opening and B-200's chest component. 현우: He is at the wheel after being startled awake from drowsy driving, with his earlier injuries still present. 앰버: She is riding in the truck after wiping away her tears, pointing forward. Her earlier head injury has no stated treatment.\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: Inside the cab behind both occupants, settle the lateral track slightly toward the passenger side at seated shoulder height, looking forward through the gap between them. 현우's back anchors the lower-left and 앰버's the lower-right, their differently inclined heads directed toward the distant violet field; neither turns toward the camera. Keep the windshield opening centered in the upper third and unobstructed between their shoulders, presenting the flowers directly through glass rather than as a reflection or screen image.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Unobstructed windshield view of the violet field in the upper-center of the frame, background.\n- KEY BACKGROUND ELEMENTS: Truck windshield (The violet field is visible through it) — Seen from inside the cab, with the field beyond the glass rather than reflected on it; used as Creates an unobstructed central view between the occupants; Violet field (Extensively covered in blooming purple violets); used as Provides the shared distant object of attention and the visual payoff beyond the cab; Truck seats (Occupied by 현우 and 앰버) — Their rear portions border the central viewing gap; used as Establishes the interior depth and supports the two separated foreground figures.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "e11ab42b-f9db-4b07-a1ea-f6c60a63aa66" }, "S72sh38": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S72sh43": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S72sh43.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L248B03.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: In the old truck's passenger area during the nighttime escape, with the injured child sheltered within the vehicle.\n\nSHOT TEXT (authoritative, Korean): 피 묻은 손으로 자신의 옆구리를 강하게 움켜쥔 채 고통스럽게 눈을 감은 앰버의 웅크린 상체.\n\nCARRIED STATE (persist exactly): The escape truck is speeding along the road at night. Charlie's damaged chest remains open, and his diagnostic view displays a 'CAUTION' warning when checking the injury. 앰버: She has a severe, actively bleeding wound in her side and is groaning in pain. The earlier injury to the back of her head also remains unresolved.\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: Enter the injury-discovery stage from diagonally beside 앰버 inside the moving truck, above her seated eyeline and angled down toward her curled upper body. Frame her from head to waist at center-right, keeping her closed eyes near the upper third and her bloodied hand clamped over her side near the lower center; her attention has contracted entirely to the pain beneath that hand. Use restrained handheld instability for direct observation, excluding the adjacent companions without changing their established positions.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Truck interior (Enclosing 앰버 while the vehicle is moving) — Only an oblique strip of the interior remains behind her upper body; used as Maintains the confined setting while leaving the injury and protective posture unobstructed.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L248B03.png" ], [ "char:앰버", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ee07b2e0-2ef8-48b5-abc7-647f59992844.png" ] ], "asset_id": "5cff0d94-8701-405a-b9fc-ab23b5fb7cba" }, "S72sh58": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S73sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S73sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L253B02.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: Beside the child's bed inside a harbor-town public clinic, under ordinary nighttime treatment-room lighting.\n\nSHOT TEXT (authoritative, Korean): 침대 곁에 서서 걱정스러운 표정으로 앰버를 내려다보는 현우의 상체.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Amber is reclined on the clinic bed, supported by the mattress as she sleeps after emergency treatment and later develops a high fever. The source does not specify whether she rests on her back or side, her head's direction, or the positions of her arms and legs.\n\nCARRIED STATE (persist exactly): The setting is the health center at night, with a bed in use. Charlie's previously damaged bodywork and exposed chest opening remain unrepaired. 현우: He remains beside the bed, worried, with dirty skin, shabby clothing and accumulated injuries.\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: Complete the bedside crane just above 현우's eye level, looking diagonally downward in a direct three-quarter medium view of his upper body. Place him on the right with his torso inclined toward the bed and his eyes lowered to 앰버; retain only her sleeping face and a small portion of her reclined upper body in the lower-left foreground. Hold the crane's endpoint without an additional push-in, allowing his worried face to carry the bedside observation.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Clinic bed (Occupied by 앰버, sleeping after emergency treatment) — The bedside edge runs diagonally across the lower-left of the composition; used as Connects her sleeping foreground presence with 현우's downward attention.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L253B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "480435f8-c957-407f-9883-a0ac016f25eb" }, "S73sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S73sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S74sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S74sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S75sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S75sh5.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L256B02.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 abandoned airfield's large aircraft-storage hangar, among dusty light aircraft in the dim nighttime interior.\n\nSHOT TEXT (authoritative, Korean): 창고 안, 먼지가 뽀얗게 쌓인 낡은 경비행기 무더기들을 올려다보는 현우의 멍한 얼굴.\n\nCARRIED STATE (persist exactly): The large hangar door is open, revealing numerous old, nonfunctional light aircraft. The abandoned airport has moss, broken paving and a deteriorated, partly fallen sign. 현우: He is inside the hangar, still dirty and battered from the journey.\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: Finish the dolly approach inside the warehouse at 현우's upper-chest height, looking slightly upward from an oblique angle rather than along his facial centerline. His blank face occupies the lower-right portion, with breathing room above and left toward the old aircraft he studies beyond the frame; keep him sufficiently back from them for a natural, modest upward gaze. Preserve the established staging and illumination, using the closer distance alone to intensify his disbelief.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Stored light aircraft (Old, abandoned, and covered with accumulated dust) — Partial aircraft contours remain oblique and out of focus behind 현우; the aircraft receiving his gaze lie beyond the frame; used as Soft contextual fragments rather than an oversized aircraft foreground.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L256B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "78ed0e38-f357-47d7-96e6-bcaf44bbe506" }, "S75sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S76sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S76sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S76sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S77sh22": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S77sh43": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S77sh43.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L257B01.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 airfield apron in daylight, beside the helicopter's takeoff point and outside the hangar.\n\nSHOT TEXT (authoritative, Korean): 멀어지는 헬리콥터를 향해 커다란 금속 팔을 힘차게 흔드는 찰리와 그 옆에 우뚝 선 현우의 뒷모습.\n\nCARRIED STATE (persist exactly): It is now daylight, and the helicopter is airborne and receding from the airport. Charlie remains on the ground with his unrepaired body damage and exposed chest opening. 현우: He remains on the ground at the airport, still dirty and battered.\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: Finish the retreat in the prescribed rear three-quarter position behind 현우 and 찰리, below their eye line and tilted gently upward toward the departing helicopter. Place 찰리 lower-left and 현우 lower-center, both fully visible and watching the distant helicopter in the upper-right; keep the entire sweep of 찰리's metal arm inside the frame while 현우's stillness expresses his decision to remain. Maintain the established daylight and ground position, emphasizing only the increasing distance to the helicopter before the explicit cut to 앰버 inside it.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Distant airborne helicopter in the upper-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: Departing helicopter (Airborne and receding from the two figures) — Seen obliquely from below and behind as it moves away; used as Small upper-right destination for both figures' attention and 찰리's farewell; Airport ground (The two figures remain on the ground after the helicopter's departure); used as Lower framing band establishing their separation from the airborne passengers.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L257B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ] ], "asset_id": "5d426069-57f7-4d5a-b31e-f5848a2bcb37" }, "S77sh53": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S78sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S78sh2.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 the harbor quay's exposed edge at dusk, beside fish vendors and moored boats.\n\nSHOT TEXT (authoritative, Korean): 커다란 모포를 머리끝까지 푹 뒤집어쓴 찰리와 현우가 부둣가에 나란히 앉아있는 전신.\n\nCARRIED STATE (persist exactly): Boats are moored along the harbor in the evening. Charlie sits on the quay under a large blanket, concealing his damaged body; the backpack brought from the airport has no stated removal. 현우: He sits on the quay, still dirty and battered, carrying the backpack from the airport.\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 dock, hold the opening position of the approach in an elevated, diagonally downward three-quarter view, observing 찰리 and 현우 directly with both seated bodies fully visible. Place 찰리 left of 현우 across the lower middle of the frame, their blankets pulled over their heads; 찰리 leans slightly forward while 현우 turns his covered head toward the distant moored boats. Let the dock edge lead behind their legs toward the harbor, preserving a quiet pause before the dolly advances.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Dock edge (Occupied by the seated pair) — Runs diagonally behind and beneath the seated figures; used as Establishes their position at the harbor boundary; Moored boats (Stationary in the harbor) — Seen obliquely beyond the pair, with no single boat occupying a large portion of the frame; used as Provides the destination of their searching attention; Sea (Undulating); used as Separates the seated figures from the moored boats.\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:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ] ], "asset_id": "aed4a301-2447-4839-a8a5-7d2e86e4dc08" }, "S78sh13": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S78sh13.png", "plate_path": null, "prompt": "Draw 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 outdoor repair spot beside an old boat moored in the harbor, where its captain pauses work at dusk.\n\nSHOT TEXT (authoritative, Korean): 용접기를 내린 채 차가운 눈빛으로 현우와 모포 쓴 찰리를 빤히 주시하는 크리스의 얼굴 클로즈업.\n\nCARRIED STATE (persist exactly): The old boat remains moored for maintenance. Charlie's large blanket conceals his damaged body, and his travel backpack has not been discarded. 크리스: He is beside the old boat, where he has been carrying out maintenance.\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: Settle at the near endpoint just outside 현우's shoulder line, looking slightly upward at 크리스 in three-quarter view; let the closer distance, rather than a new interaction axis, sharpen the scrutiny. His early-forties face occupies the center-right, his chin held before the boarding nod and his attention fixed on 현우 and the blanket-covered 찰리 just outside frame left, never on the lens. Keep his lowered welding tool outside the crop and retain a soft fragment of the old boat behind him.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Old boat (Undergoing maintenance) — Only an oblique fragment of its dock-facing side is visible behind 크리스; used as Keeps the close scrutiny grounded in the boarding encounter.\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": [], "asset_id": "4effe083-7d46-4dd7-a28a-33b44efc4e7b" }, "S78sh17": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S79sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S79sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S79sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S80sh9": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S80sh9.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L261B01.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: At the exposed edge of the boat's storm-lashed deck, beside the upright support gripped by the robot.\n\nSHOT TEXT (authoritative, Korean): 허공으로 떨어지는 현우의 손목을 낚아채듯 꽉 움켜쥔 찰리의 다른 금속 손 클로즈업.\n\nCARRIED STATE (persist exactly): Torrential rain, typhoon winds and huge waves batter the ship at night. Charlie's already damaged body is rain-soaked, with one hand braced around a shipboard post and the other extended over the edge. 현우: He is soaked and suspended at the ship's edge with one arm stretched upward, his earlier injuries still present.\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: Finish the deck-side approach slightly above wrist height, looking diagonally down across the joined arms rather than along either person's frontal axis. Center 찰리's metal hand clamped around 현우's wrist, with 찰리's forearm entering from upper left and 현우's tensioned arm extending toward lower right beyond the ship's edge; their faces remain outside the crop as the catching action embodies their attention to one another. Retain a narrow strip of deck and the supporting post farther upper left at natural scale, fixing the grip's screen direction for the later return.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Ship's edge (Beside 현우's interrupted fall during the storm) — Seen diagonally from the deck side beneath the extending arms; used as Separates the supported deck side from the space of the fall; Supporting post (Serving as 찰리's anchor) — A small oblique portion is visible toward upper left behind his forearm; used as Explains the direction of resistance without competing with the grip.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L261B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ] ], "asset_id": "7e2e9a21-fd2a-469c-b057-4ecfe185964a" }, "S80sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S80sh20": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S80sh20.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L261B02.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: Deep underwater beneath the storm-struck boat, in near-total darkness among sinking cargo.\n\nSHOT TEXT (authoritative, Korean): 칠흑 같은 심해 속으로 축 늘어진 채 나란히 떠 있는 현우와 찰리의 거대한 실루엣.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Hyunwoo is unconscious and sinking beneath the sea beside Charlie, his body limp and unsupported in the water. The source does not establish the direction of his head, the orientation of his torso, or the arrangement of his arms and legs.\n\nCARRIED STATE (persist exactly): Heavy shipboard cargo sinks through increasingly dark water. Charlie is submerged and descending with his preexisting body damage still present. 현우: He is unconscious and sinking deeper underwater with his body limp.\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 submerged side position below their torsos, look obliquely upward and descend at the pair's pace, observing them directly rather than through 현우's failing consciousness. Keep 현우 on the left and 찰리 on the right, their complete limp silhouettes together occupying most of the central image height, with a narrow separation and different slack angles in their arms and knees. 현우's bowed head and 찰리's lowered face turn into the water beneath them without an active exchange of looks; hold their relative placement while the surrounding darkness deepens toward the fade.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Deep surrounding water (Increasingly dark as the pair descend); used as Provides unbroken negative space around the paired silhouettes without introducing a seabed or visible surface.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L261B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ] ], "asset_id": "fee007fc-1173-489b-af5a-181096534991" }, "S81sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S81sh5.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L266B02.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: At the doorway inside an island research facility's temporary-care room, lit by strong fluorescent lights and daylight from a sea-facing window.\n\nSHOT TEXT (authoritative, Korean): 병실 문가에 서서 다정하게 미소 짓는 서지민의 전신.\n\nCARRIED STATE (persist exactly): A white bed is lit by strong fluorescent lighting in the temporary shelter, with an emerald-blue sea visible through the window. The storm-dark shipboard setting has ended. 서지민: She wears research clothing and has her researcher access card available.\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: Complete the turn from beside the bed and briefly hold below 서지민's eye level, viewing her obliquely from inside the room with her full body visible in the doorway. Place the twenty-year-old researcher in the right third, wearing her research clothes and easing her weight onto one leg as she smiles gently toward 현우 at the bed outside frame left. Use the doorway's interior edges as a loose frame and retain only a small white bed corner in the lower left, making her reassurance personal rather than a frontal portrait.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Room doorway (Open, with 서지민 at the threshold) — Seen obliquely from the room's interior; used as Frames her full body while leaving space toward 현우; White bed (A small corner remains visible beside the camera position) — Only a cropped near corner appears at lower left; used as Anchors the view to 현우's bedside without showing him.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L266B02.png" ], [ "char:서지민", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/def5e4e9-de41-4cca-bf6e-2c4c10df7f7e.png" ] ], "asset_id": "87280629-3bc9-4dc2-9c89-4967995f760f" }, "S81sh13": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S81sh13.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L266B01.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: In the corridor connecting the temporary-care rooms to the island research facility, under ordinary corridor lighting.\n\nSHOT TEXT (authoritative, Korean): 멈춰 선 채 두 눈이 동그라져 앞을 빤히 주시하는 현우의 놀란 얼굴 클로즈업.\n\nCARRIED STATE (persist exactly): 현우: He is wearing the fresh white clothes provided during his recovery and has stopped in the research-facility corridor.\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: Settle at the nearest point of the corridor track, at 현우's eye height and on the established oblique side of his face. His face occupies the left two-thirds, with shallow-focus corridor space to the right along his widened gaze toward 서지민 off-screen; his arrested forward momentum remains visible in his tense neck and slightly parted lips. Emphasize only the final reduction in camera distance, holding the established eyeline and lighting.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Research laboratory corridor (Visible behind 현우 as he stops following 서지민) — The corridor recedes along the established walking line; used as Soft background depth and open space along his eyeline.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L266B01.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ] ], "asset_id": "2d7ff4e0-834c-440a-92c5-40e9da371422" }, "S81sh16": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S82sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S82sh17": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S82sh26": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S83sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S83sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S83sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S84sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S84sh11": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S84sh11.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L269B03.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: Beside the old piano in the central hall of the research director's suite, under subdued nighttime interior lighting.\n\nSHOT TEXT (authoritative, Korean): 자신 앞까지 다가온 찰리를 올려다보며 온화한 미소를 지은 채 정지해 있는 지소영의 얼굴 클로즈업.\n\nCARRIED STATE (persist exactly): An old piano stands in the central hall of the modern director's office. Charlie is now mobile beside the piano, with the laboratory wires detached and the glass-enclosure exit left open. 지소영: She remains at the piano in her neat research coat, having paused her playing.\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: Settle the forward track beside 찰리's trailing shoulder on the established side of their eyeline, slightly above 지소영's seated eye height with a shallow downward tilt. Her face occupies the center-right, while only a narrow edge of 찰리's near shoulder remains at left and a small portion of the piano grounds her seated position below. 지소영 pauses with a gentle smile and a natural upward gaze toward 찰리's face, while his halted, slightly inclined posture turns his attention down toward her; emphasize the completed approach rather than a new lighting cue.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Old piano (Playing has paused while 지소영 addresses 찰리) — A small oblique section of the keyboard side appears at the lower edge; used as Locates her seated posture and preserves continuity with the interrupted music.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L269B03.png" ], [ "char:지소영", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/037e436c-7af9-4409-bbc8-895bd4174d11.png" ] ], "asset_id": "b7d06adc-c73d-44f7-8b3e-12527f45e14c" }, "S84sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S85sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S85sh22": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S85sh22.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L268B01.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: At a dining table inside the research facility's communal cafeteria, in daytime interior light near the meal-service area.\n\nSHOT TEXT (authoritative, Korean): 양손으로 자신의 입을 헉 하고 틀어막은 서지민의 당황한 얼굴 클로즈업.\n\nCARRIED STATE (persist exactly): Appetizing bread and other food remain on the dining table, still uneaten. 서지민: She is at the dining conversation in her research coat, abruptly checking herself after an unintended disclosure.\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 just outside 현우's shoulder on the established dialogue-axis side, slightly above 서지민's seated eye height and angled gently downward into a three-quarter close view. Keep 현우 outside the crop, placing 서지민's face just right of center with both hands covering her mouth and enough room below for her raised wrists. Her eyes remain fixed on 현우 just off the left edge, making the arrested gesture—not a lighting change—the emphasis of this direct observation.\n- FRAMING SCALE: close-up\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L268B01.png" ], [ "char:서지민", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/def5e4e9-de41-4cca-bf6e-2c4c10df7f7e.png" ] ], "asset_id": "382f3829-e015-47c7-ab5e-b6be933588ec" }, "S85sh23": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S86sh2": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S86sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S87sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S87sh4.png", "plate_path": null, "prompt": "Draw 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: Inside the special-operations commander's office, in the briefing area under nighttime office lighting.\n\nSHOT TEXT (authoritative, Korean): 허공을 향해 주먹을 꽉 쥔 채, 출동을 지시하듯 크게 입을 벌리고 있는 이강준의 핏대 선 상체.\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: Settle the desk-side approach into the prescribed static position at 이강준's chest height, offset from his line toward the reporting soldier and tilted slightly upward. Place his tense torso center-left, with his raised clenched fist in the upper-left area and breathing room above it, while his open mouth and eyes direct the departure order toward the soldier off-screen right. Observe him directly rather than from the soldier's subjective viewpoint, and hold this endpoint for the command to bridge the subsequent cut.\n- FRAMING SCALE: medium 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, "no_plate": true, "ref_paths": [], "asset_id": "50017786-0851-4a08-8e8f-72323e26d3ef" }, "S87sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S87sh5.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: Inside a corporate chairman's office, at the communications-monitoring position under nighttime office lighting.\n\nSHOT TEXT (authoritative, Korean): 유빅사 사무실, 귀에 꽂힌 통신용 이어폰에 손을 댄 채 비열하게 입꼬리를 한껏 올린 윤성찬의 얼굴.\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 the explicit office-to-office cut, hold at 윤성찬's eye height on the side of his ear-touching hand, retaining the inherited oblique three-quarter position. Place his face left of center, his fingers and communication earpiece along the left contour, and leave space to the right for his gaze toward the mercenary commander outside the frame. Show the lifted mouth corner and slight head turn in the same focal plane; this is a direct view of a man listening, not an image transmitted through the earpiece.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Communication earpiece (Inserted in his ear and touched by his fingers) — Its exposed outer portion is visible beside the near ear; used as Small narrative detail linking his expression to the intercepted command.\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:윤성찬", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ca351fd2-cdd4-40c3-b589-9cb376c17d84.png" ] ], "asset_id": "f85ce6f3-3160-4f21-847d-73d55d234f47" }, "S88sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S88sh24": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S88sh29": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S89sh42": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S89sh42.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L278B01.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: At the step of a helicopter landed on the island research facility's rooftop, beside the rooftop lawn and antenna area.\n\nSHOT TEXT (authoritative, Korean): 헬기 스텝에 한 발을 딛고 선 채 피 흘리는 현우를 향해 입꼬리를 비스듬히 올리고 내려다보는 윤성찬의 거만한 전신.\n\nCARRIED STATE (persist exactly): The rooftop garden retains its large antenna and all-direction speakers, now amid bombardment damage and collapsed combat robots. A Yubik command helicopter has landed on the roof while other armed aircraft surround the facility; Charlie is free of the bed restraints and still carries the experimental sensors. 윤성찬: He is disembarking from the command helicopter on the rooftop, smiling.\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: Ease the lateral track into a low-angle hold on the established side of the confrontation, showing 윤성찬's entire body in a three-quarter view at center-right with one foot still planted on the helicopter step. Keep the cropped back and bloodied shoulder of 현우 low at the left edge as 윤성찬 directs his crooked smile downward toward him, never toward the lens. The helicopter's step and adjacent fuselage occupy less than two-fifths of the image, while the rooftop between the men preserves the physical distance underlying the humiliation.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 윤성찬's helicopter (Landed on the rooftop) — The step-bearing side is seen obliquely, with most of the aircraft outside the right edge; used as Provides the practical elevation beneath 윤성찬 without overwhelming his full-body silhouette; Research facility rooftop (The confrontation takes place here after the helicopter lands) — The ground plane recedes from 현우 toward the helicopter step; used as Connects the injured foreground figure and elevated antagonist within one continuous 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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L278B01.png" ], [ "char:윤성찬", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/ca351fd2-cdd4-40c3-b589-9cb376c17d84.png" ] ], "asset_id": "2a41fdeb-7ce7-4a06-960e-c2b1ec36de8b" }, "S89sh53": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S89sh66": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S89sh66.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L278B02.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: In the devastated outdoor area of the island research facility at night, beside the robot's remaining wreckage after the blast.\n\nSHOT TEXT (authoritative, Korean): 찰리의 차가운 잔해를 양팔로 빈틈없이 끌어안은 채 하늘을 향해 고개를 젖히고 입을 크게 벌린 현우의 오열하는 굳은 전신.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Charlie's powered-off remains are held tightly against Hyunwoo's body in both of his arms. Only part of Charlie's destroyed body remains, and the source does not specify its orientation within the embrace or the arrangement of any surviving appendages.\n\nCARRIED STATE (persist exactly): The beam has vanished, leaving only a partially surviving torso and charred remnants of Charlie outside the research facility at night. Charlie's remaining power has shut down completely. 현우: He remains wounded from the attack and is sobbing with both arms tightly closed around the remains in his grasp.\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: Complete the rising retreat beside 찰리's remains and settle into an elevated oblique side view, looking down on 현우's entire kneeling body in the lower middle of the frame. His knees bear his weight as both arms close tightly around the surviving torso; his head is thrown toward the sky and his open mouth carries the cry, with no appeal toward the camera. Preserve generous empty ground around the embrace, making withdrawal in camera distance the principal visual change and treating 찰리's inert remains as a held body rather than a separate display object.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Ground outside the research facility (The nighttime location of Charlie's surviving remains); used as Surrounds the full-body embrace with unoccupied space as the camera withdraws.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L278B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:찰리", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/1a5b319b-f111-43e4-a710-9a53f25fd587.png" ] ], "asset_id": "7273645e-cb70-462d-a06c-54beb3d21fa8" }, "S90sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S90sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L282B02.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: Beside the altar-like parts table inside a spacious, dark research room, lit by a large display showing deployed energy robots.\n\nSHOT TEXT (authoritative, Korean): 현우의 어깨를 한 손으로 부드럽게 감싸 쥔 채 앞으로 작은 데이터 칩을 불쑥 내민 자세의 지소영의 상체.\n\nCARRIED STATE (persist exactly): The large room is dim, with disassembled Charlie components arranged on an altar-like table. The large monitor shows Charlie energy units supplied to locations including Dubai, Europe, China and Africa. 현우: He is seated behind the display table, still covered in wounds. 지소영: She is beside the seated area, holding out the small data chip containing Charlie's stored memories.\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: Maintain the diagonal approach beside seated 현우, looking slightly upward past his near shoulder toward 지소영's three-quarter upper body at center-right. Her near hand gently encloses his shoulder while the other extends the small chip into the lower center, its scale kept natural against her fingers; she looks down toward him as he begins to lift his face toward hers. Keep the contact and offering within one continuous plane of attention, with the camera's approach—not a lighting or axis change—carrying the moment toward intimacy.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Data chip (Held out by 지소영 before the transfer) — Seen obliquely between her fingers, with no invented markings or readable face; used as Links her supportive hand and 현우's response without becoming an oversized foreground object; 현우's seat (Occupied) — A partial side is visible beneath and behind his cropped torso; used as Establishes the seated-to-standing relationship underlying her downward attention.\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/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L282B02.png" ], [ "char:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:지소영", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/037e436c-7af9-4409-bbc8-895bd4174d11.png" ] ], "asset_id": "9d655ae0-d34a-4dc7-bb3a-f3c76225f96b" }, "S90sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S90sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S91sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S91sh4.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 a temporary dining table set on the exposed rock surface of a small sea islet in daylight.\n\nSHOT TEXT (authoritative, Korean): 바위섬 위 임시 식탁에 예쁜 접시를 올려둔 채 서로를 향해 활짝 웃고 있는 현우와 서지민의 전신.\n\nCARRIED STATE (persist exactly): Clear seawater reveals fish beneath the rocky island, and an outdoor dining table is being laid with an ample meal. Charlie is fully reassembled and active again, trying to catch fish. 현우: He is at the dining table arranging food. 서지민: She is at the dining table arranging food.\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: Travel beside the temporary dining table at approximately eye level, retaining an oblique view across the pair's facing axis and showing both full bodies. Place 현우 left and 서지민 right at adjacent sides of the table, their torsos turned warmly toward each other as they smile over the meal; 현우 is finishing the placement of a plate while 서지민 leans toward another setting, both glancing down at the arrangement between them. Keep their hands in different phases of the shared task and the table below two-fifths of the frame, allowing the island rock around their feet to establish an unforced domestic moment.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Temporary dining table (Being set with food and attractive plates) — Its top and near side are visible diagonally between the two figures; used as Connects their separate gestures while preserving full-body visibility at its adjacent sides; Food and plates (Partly arranged for the meal) — The plate interiors and food are visible from the oblique camera position; used as Provide the shared focus of their activity at natural scale; Island rock (Supporting the table and both figures); used as Keeps the meal grounded in the island setting without adding furnishings.\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:현우", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/8d393e7f-ac13-4764-a7cc-05adcb3e7ad8.png" ], [ "char:서지민", "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/reference/def5e4e9-de41-4cca-bf6e-2c4c10df7f7e.png" ] ], "asset_id": "8048621a-1847-4b10-b7c7-7f2985a29c65" }, "S91sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null } }, "map_conti": {}, "conti_pack": "5.202607222353", "lane_conti": { "S6sh26": { "lane": "structure_plate", "group_id": "bg_refugee_dump", "segment_id": "segment_01", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_dump_sel.png", "seed_asset_id": "c7293dea-4a59-4086-b333-889f46e571b8", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_dump_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S6sh26.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_dump_sel.png" }, "S7sh15": { "lane": "structure_plate", "group_id": "bg_seawall_construction", "segment_id": "truck_entry", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_seawall_construction_sel.png", "seed_asset_id": "b2bbedaf-f3a0-45d8-a9d8-1e833de3bb1c", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_seawall_construction_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S11sh1": { "lane": "structure_plate", "group_id": "bg_refugee_gate", "segment_id": "seg_gate", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png", "seed_asset_id": "331ee13b-1a46-4cba-9a37-07f52e1d1493", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S11sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png" }, "S11sh4": { "lane": "structure_plate", "group_id": "bg_refugee_gate", "segment_id": "seg_container_doorway", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png", "seed_asset_id": "331ee13b-1a46-4cba-9a37-07f52e1d1493", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S11sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png" }, "S13sh13": { "lane": "structure_plate", "group_id": "bg_seawall_construction", "segment_id": "wall_frontage", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_seawall_construction_sel.png", "seed_asset_id": "b2bbedaf-f3a0-45d8-a9d8-1e833de3bb1c", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_seawall_construction_sel.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S20sh3": { "lane": "structure_plate", "group_id": "bg_refugee_market", "segment_id": "container_approach", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_market_sel.png", "seed_asset_id": "6d54c6c7-2c28-4a2b-b86c-5354ceb223d7", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_market_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S25sh22": { "lane": "structure_plate", "group_id": "bg_outdoor_reception", "segment_id": "seg_02", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_outdoor_reception_sel.png", "seed_asset_id": "eac29610-01b6-43a7-9e6e-9e2387ddd674", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_outdoor_reception_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S25sh22.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_outdoor_reception_sel.png" }, "S27sh12": { "lane": "structure_plate", "group_id": "bg_sewer_and_manhole", "segment_id": "SEG01", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_sewer_and_manhole_sel.png", "seed_asset_id": "2b4b407b-73bc-405e-8265-11c6b8d30ef7", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L177B01.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S27sh18": { "lane": "structure_plate", "group_id": "bg_sewer_and_manhole", "segment_id": "SEG01", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_sewer_and_manhole_sel.png", "seed_asset_id": "2b4b407b-73bc-405e-8265-11c6b8d30ef7", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L177B01.png", "bg_reason": "", "bypass_reason": "prev" }, "S35sh3": { "lane": "structure_plate", "group_id": "bg_shanty_flood", "segment_id": "seg_02", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_shanty_flood_sel.png", "seed_asset_id": "79aa97f9-0142-4127-b62e-63daa2c92a68", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_shanty_flood_sel.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S40sh6": { "lane": "structure_plate", "group_id": "bg_unstaffed_shop", "segment_id": "seg_3", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_unstaffed_shop_sel.png", "seed_asset_id": "7bd64ce2-2bcb-4046-adef-f7b03b116747", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L194B02.png", "bg_reason": "", "bypass_reason": "prev" }, "S42sh11": { "lane": "structure_plate", "group_id": "bg_refugee_gate", "segment_id": "seg_sedan_doorway", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png", "seed_asset_id": "331ee13b-1a46-4cba-9a37-07f52e1d1493", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_refugee_gate_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S49sh47": { "lane": "structure_plate", "group_id": "bg_roadside_service_station", "segment_id": "seg_02", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_roadside_service_station_sel.png", "seed_asset_id": "ab322096-550b-4b37-8cda-d1efdc3c511b", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L205B02.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S49sh51": { "lane": "structure_plate", "group_id": "bg_roadside_service_station", "segment_id": "seg_02", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_roadside_service_station_sel.png", "seed_asset_id": "ab322096-550b-4b37-8cda-d1efdc3c511b", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L205B02.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S49sh51.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L205B02.png" }, "S56sh14": { "lane": "structure_plate", "group_id": "bg_swamp_vehicle_trap", "segment_id": "trap_pit", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_swamp_vehicle_trap_sel.png", "seed_asset_id": "35daf1c0-9bf7-43b6-88f5-bd8ce48ceb64", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_swamp_vehicle_trap_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S57sh3": { "lane": "structure_plate", "group_id": "bg_ruined_village_square", "segment_id": "seg_01", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_ruined_village_square_sel.png", "seed_asset_id": "e716b949-d46e-4479-90bb-be052601519b", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_ruined_village_square_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S57sh3.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_ruined_village_square_sel.png" }, "S57sh7": { "lane": "structure_plate", "group_id": "bg_ruined_village_square", "segment_id": "seg_02", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_ruined_village_square_sel.png", "seed_asset_id": "e716b949-d46e-4479-90bb-be052601519b", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_ruined_village_square_sel.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S60sh4": { "lane": "structure_plate", "group_id": "bg_village_church_arena", "segment_id": "arena_frontage", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_village_church_arena_sel.png", "seed_asset_id": "7cc6d446-071f-4801-886a-a504b66fe88c", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L229B01.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S61sh1": { "lane": "structure_plate", "group_id": "bg_swamp_vehicle_trap", "segment_id": "stranded_vehicle", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_swamp_vehicle_trap_sel.png", "seed_asset_id": "35daf1c0-9bf7-43b6-88f5-bd8ce48ceb64", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_swamp_vehicle_trap_sel.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S62sh3": { "lane": "structure_plate", "group_id": "bg_ruined_village_square", "segment_id": "seg_03", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_ruined_village_square_sel.png", "seed_asset_id": "e716b949-d46e-4479-90bb-be052601519b", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_ruined_village_square_sel.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S63sh1": { "lane": "structure_plate", "group_id": "bg_open_roof_truck", "segment_id": "seg_01", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png", "seed_asset_id": "c94c53e3-76a2-4f78-b4ae-95204318d3c2", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S65sh20": { "lane": "structure_plate", "group_id": "bg_collapsed_department_store", "segment_id": "seg_02", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_collapsed_department_store_sel.png", "seed_asset_id": "9411baa0-6efd-40c9-98ca-5ccb207fae76", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L239B01.png", "bg_reason": "", "bypass_reason": "prev" }, "S68sh3": { "lane": "map_marker", "group_id": "bg_inland_road_fork", "segment_id": "seg_01", "marker_attempts": 3, "marker_best_effort": true, "marker_pick_index": 1, "marker_pick_count": 3, "marker_pick_why_ko": "후보 2와 3은 각각 3개의 평가 항목(후보 2: 방향 누락 등, 후보 3: 시야각 이탈 및 도면 훼손 등)을 위반한 반면, 후보 1은 피사체 위치와 추가 요소 등 2개의 위반 사항만 가지고 있어 지시된 연출 기획에서 가장 적게 벗어났습니다.", "marker_model": "nb2", "marker_check": { "markers_ok": false, "details_ko": "피사체 마커들(E1, E2, E3)이 지정된 도로 영역을 벗어나 잘못된 위치에 배치되었으며, 라벨이 없는 마커가 추가로 존재합니다.", "violations": [ { "axis": "entity_position", "note_ko": "E1, E2, E3 마커가 지시된 좌표(도로 위)가 아닌 잔디밭이나 도로 외곽 경계 등 완전히 다른 구역에 배치되었습니다." }, { "axis": "extra_content", "note_ko": "지정되지 않은 라벨 없는 마커(오른쪽 하단 도로 위)가 임의로 추가되었습니다." } ] }, "marker_models_tried": [ "nb2" ], "sketch_attempts": 1, "status": "ok", "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/lane_sketch_S68sh3.png", "base_map_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/canon_bg_inland_road_fork_map.png", "base_map_asset_id": "338adabe-3c75-42ec-965b-94ddfc8abab4", "marker_map_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/lane_marker_map_S68sh3.png", "marker_prompt": "Edit the attached TOP-DOWN SITE PLAN image: draw STAGING MARKERS on it\nat the positions described below. This is a planning aid for a film\ncrew, drawn over the plan.\n\nPLACEMENT AUTHORITY: each marker line below gives its position as\nnormalized fractions of this canvas — x runs left→right 0..1, y runs\ntop→bottom 0..1 — and THOSE FRACTIONS ARE THE AUTHORITY. Measure them\non the attached image and put the marker there. Each line also names a\nnearby landmark; use it to check you landed on the right feature, and\nwhen a landmark phrase and the fractions disagree, follow the\nfractions. This applies to compass words (north, south, east, west)\ntoo: read them only if this plan actually shows a compass or labels\nits own approaches, and even then they never move a marker away from\nits fractions. Do NOT relocate a marker onto a different salient line\nor feature than the one its fractions land on.\n\nNEVER move a marker to make the drawing fit. The camera circle and\nevery subject circle go exactly where their descriptions place them,\neven when that leaves the view wedge or an arrow running off the edge\nof the image — in that case just let the wedge or arrow continue to\nthe image border and stop there. Shifting the camera outward, pulling\na subject aside, or shrinking the wedge to keep it inside the canvas\nall break the plan this map exists to record.\n\nDraw EXACTLY these markers, flat and high-contrast, small enough not\nto hide the plan under them:\n- CAMERA: one filled circle at the camera position, labelled CAM, and\n out of that circle a FIELD-OF-VIEW WEDGE showing what this shot\n sees — two straight thin lines, one running toward each of the two\n frame-edge positions given below, and a third thinner line to the\n look-target position between them. Fill the area between the two\n edge lines with a light translucent tint so the wedge reads as the\n camera's view; the plan underneath must stay fully readable through\n the tint. Every subject listed below stands inside this wedge —\n if your drawing leaves one outside it, the wedge is drawn wrong,\n not the subject.\n- SUBJECTS: one filled circle per subject at its position, labelled\n with its slot code (E1, E2, ...) followed by its short description\n in parentheses, and one short ARROW leaving that circle toward the\n spot the subject faces, so the direction each subject is turned is\n readable at a glance.\n\nChange NOTHING else: keep every zone, landmark, line, label and color\nof the plan exactly as attached — do not redraw, recolor, move or\nremove anything, do not add scenery, shadows or any other symbols or\ntext beyond the markers, wedge, arrows and labels specified above. The\noutput is the SAME plan image with only these staging markers added.\n\nMARKERS TO DRAW:\n- CAM (camera): circle at x=0.10, y=0.50 — the left edge area of the plan (landmark, for reference: on the Common road, well before the fork); its sight line ends at LOOK TARGET: at x=0.50, y=0.50 — the center of the plan (landmark, for reference: at the center of the two-branch road fork); the frame's LEFT edge cuts through at x=0.80, y=0.10 — the upper-right area of the plan (landmark, for reference: along the upper edge of the Left road branch zone) and its RIGHT edge through at x=0.80, y=0.90 — the lower-right area of the plan (landmark, for reference: along the lower edge of the Right road branch zone)\n- E1 (first old truck): circle at x=0.75, y=0.28 — the upper-right area of the plan (landmark, for reference: on the Left road branch, moving rightward away from the fork), facing at x=0.95, y=0.28 — the upper-right area of the plan (landmark, for reference: further rightward along the Left road branch)\n- E2 (second old truck): circle at x=0.75, y=0.72 — the lower-right area of the plan (landmark, for reference: on the Right road branch, moving rightward away from the fork), facing at x=0.95, y=0.72 — the lower-right area of the plan (landmark, for reference: further rightward along the Right road branch)\n- E3 (convoy of vehicles): circle at x=0.62, y=0.65 — the center of the plan (landmark, for reference: on the Right road branch, just past the junction), facing at x=0.85, y=0.72 — the lower-right area of the plan (landmark, for reference: further down the Right road branch)", "geometry": { "entity_placements": [ { "slot": "E1", "subject_en": "first old truck", "x": 0.75, "y": 0.28, "anchor_en": "on the Left road branch, moving rightward away from the fork", "facing": { "x": 0.95, "y": 0.28 }, "facing_anchor_en": "further rightward along the Left road branch", "camera_facing_relation": "away_from_camera", "camera_facing_evidence": "뒷모습" }, { "slot": "E2", "subject_en": "second old truck", "x": 0.75, "y": 0.72, "anchor_en": "on the Right road branch, moving rightward away from the fork", "facing": { "x": 0.95, "y": 0.72 }, "facing_anchor_en": "further rightward along the Right road branch", "camera_facing_relation": "away_from_camera", "camera_facing_evidence": "뒷모습" }, { "slot": "E3", "subject_en": "convoy of vehicles", "x": 0.62, "y": 0.65, "anchor_en": "on the Right road branch, just past the junction", "facing": { "x": 0.85, "y": 0.72 }, "facing_anchor_en": "further down the Right road branch", "camera_facing_relation": "unspecified", "camera_facing_evidence": "" } ], "camera": { "origin": { "x": 0.1, "y": 0.5 }, "look_target": { "x": 0.5, "y": 0.5 }, "origin_anchor_en": "on the Common road, well before the fork", "look_target_anchor_en": "at the center of the two-branch road fork", "view_left": { "x": 0.8, "y": 0.1 }, "view_right": { "x": 0.8, "y": 0.9 }, "view_left_anchor_en": "along the upper edge of the Left road branch zone", "view_right_anchor_en": "along the lower edge of the Right road branch zone" }, "rationale_ko": "카메라는 공통 도로 뒤편(Common road) 높은 위치에서 갈림길 전체를 부감으로 포착하는 넓은 화각을 형성합니다. 지시문에 따라 첫 번째 트럭은 왼쪽 길(Left road branch)로, 두 번째 트럭과 이를 따르는 차량들은 오른쪽 길(Right road branch)로 멀어지도록 배치하였으며, 두 트럭 모두 렌즈 시선을 등지고 멀어지는 '뒷모습(away_from_camera)' 방향성을 명확히 반영했습니다." }, "geometry_attempts": 1, "leakage": { "has_marker_leakage": false, "details_ko": "도해용 기호나 불필요한 문자가 스케치에 없습니다." }, "prompt": "Draw a single CAMERA-VIEW storyboard frame (16:9) of the scene staged\non the attached MARKER-ANNOTATED TOP-DOWN SITE PLAN, seen from the\ncamera position marked on it.\n\nThe attached plan carries STAGING MARKERS drawn over it: a\ncamera-position marker with a field-of-view wedge (where the camera\nstands, which way it looks and how wide it sees) and one labelled\ncircle per subject with an arrow (where each subject stands and which\nway that subject is turned). Jurisdiction of sources — follow all three, they do not\nconflict:\n- The SITE PLAN under the markers is the SOT for what exists on the\n site and how its zones and landmarks are arranged relative to each\n other. The markers themselves are staging aids, NOT site content.\n- The markers on the plan are the SOT for XY POSITIONS, horizontal\n heading and body facing ONLY: where each subject stands on that\n plan, which way each one is turned, where the camera stands, which\n way it looks and how wide its wedge opens. Distances, directions\n and relative depths between subjects come from the marked\n positions; what the wedge covers is what this frame contains, and\n subjects outside the wedge are out of frame. The STAGING GEOMETRY\n text below restates the same staging with coarse normalized\n estimates — it never overrides the marked plan.\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. It does NOT govern horizontal\n placement: which side of the frame a subject occupies and which way\n that subject is turned come from the marked plan and the staging\n text, even when that memo also mentions left, right, foreground or\n background.\n\nSTYLE — MANNEQUIN BLOCKING SKETCH: the lightest possible director's\nlayout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR LINES ONLY on pure\nwhite paper. Absolutely NO shading, NO tone, NO texture, NO grayscale\nfill, NO light-and-shadow, NO material rendering. It must read as a\nquick layout guide, never as a finished drawing.\n\nDraw every person as a PLAIN ARTIST'S MANNEQUIN: a featureless oval head\nwith NO face, NO hair, NO clothing and no costume detail — simple tapered\nlimbs and torso. Because the head has no face and no hair, the ONLY thing\nthat shows which way a figure is turned is the BODY ITSELF: the direction\nthe chest, hips and feet point, and the way the head-oval sits on the\nshoulders. Aim each mannequin's chest and feet at the spot the staging\ntext says that person faces, and let the arms carry the action. A\nmannequin turned to the wrong side is the single worst error in this\ndrawing. Environment is reduced to a few placement lines (ground line,\nkey landmark silhouettes) — just enough to read positions and depth.\n\nSTAGING GEOMETRY — PLANNING DATA ONLY, NEVER RENDER IT: the lines\nbelow restate, marker by marker, the staging already marked on the\nattached plan: each landmark-relative description restates the\nmarker-map authority in words, and the normalized fractions in\nparentheses (x left→right 0..1, y top→bottom 0..1) are coarse audit\nestimates only — neither ever overrides the marked plan.\n\nThose fractions are TOP-DOWN bookkeeping. Never read them as left and\nright of your frame: on a plan seen from above, a subject \"to the\nright\" can sit on either side of a camera that looks any direction.\nEach subject line therefore ends with the SAME staging expressed from\nTHIS camera — which part of the frame the subject occupies, and which\nway that subject faces in screen terms (toward the left or right of\nthe frame, toward or away from the camera or side-on to it in\nprofile, and whom they are looking at). Those screen-space statements\nare what your drawing must match:\na figure said to face the right of the frame is turned to the right in\nyour drawing, never mirrored.\n\nDo NOT draw any of this data in the image — no numbers, no\ncoordinates, no labels, no arrows, no cones, no dots, no diagram\nsymbols of any kind.\n\nWhere the CAMERA DIRECTION text below also describes horizontal\nplacement (which side of the frame someone occupies, foreground left,\nbackground right), treat that as background reading only: for anything\nabout left, right and where a subject sits in this frame, the staging\nabove wins. CAMERA DIRECTION governs the vertical angle, elevation,\ntilt and framing.\n\nFor whether a subject faces the camera or is turned away from it, each\nsubject line above already states it in screen terms and the SHOT TEXT\nis the source it was derived from — draw exactly what the subject line\nsays, and never mirror it.\n- the camera stands on the Common road, well before the fork (coarse estimate x=0.10, y=0.50); its sight line ends at LOOK TARGET: at the center of the two-branch road fork (coarse estimate x=0.50, y=0.50); the frame's LEFT edge cuts through along the upper edge of the Left road branch zone (coarse estimate x=0.80, y=0.10) and its RIGHT edge through along the lower edge of the Right road branch zone (coarse estimate x=0.80, y=0.90) — everything between those two edges is in frame, anything outside them is out of frame\n- first old truck stands on the Left road branch, moving rightward away from the fork (coarse estimate x=0.75, y=0.28), facing further rightward along the Left road branch (coarse estimate x=0.95, y=0.28) — from this camera the subject is in the LEFT part of the frame and faces away from the camera, into the depth of the shot, so the camera sees this subject from behind\n- second old truck stands on the Right road branch, moving rightward away from the fork (coarse estimate x=0.75, y=0.72), facing further rightward along the Right road branch (coarse estimate x=0.95, y=0.72) — from this camera the subject is in the RIGHT part of the frame and faces away from the camera, into the depth of the shot, so the camera sees this subject from behind\n- convoy of vehicles stands on the Right road branch, just past the junction (coarse estimate x=0.62, y=0.65), facing further down the Right road branch (coarse estimate x=0.85, y=0.72) — from this camera the subject is in the RIGHT part of the frame and faces toward the RIGHT of the frame and away from the camera, into the depth of the shot, so the camera sees this subject from behind\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): From the elevated position behind the fork, hold the crane's stable middle composition with a downward angle that includes both trucks in complete rear three-quarter view. 현우's truck recedes along the left branch and 수빈's along the right, each occupying less than a quarter of the image, with the following vehicles taking the right branch and wheel-raised dust tracing the divergence. Keep the fork visible in the lower center and the occupants outside readable view, reserving the later descent and pursuit for 현우's branch.\n\nTHE LOCATION: 익산과 서남부 내륙의 지방도로\n\nSHOT TEXT (authoritative, Korean): 양 갈래 흙길에서 서로 다른 방향을 향해 달려가며 바퀴 뒤로 흙먼지를 일으키고 있는 두 낡은 트럭의 뒷모습 풀샷.\n\nCARRIED STATE (persist exactly): Two old roofless trucks separate at the fork, with more vehicles following one branch. Charlie rides in the cargo bed with his battle damage unrepaired and the recovered B-200 chest component in his possession.\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, head-oval and chest turned toward the target the\nSHOT TEXT implies; avoid a stiff attention stance (feet together, arms\nhanging straight down) and a head-oval squared flat to the lens. If the\nSHOT TEXT or any POSE contract above stages stillness, death, sleep,\nunconsciousness, restraint, drill or an explicit direct-to-camera look,\ndraw THAT exactly — this clause never overrides it.\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.", "lane_sketch_pack": "16.202608252310", "lane_geometry_pack": "4.202607270248", "mannequin_chain_contract": "1", "asset_id": "815b621b-2e6e-493b-afbf-f2b2614706ac" }, "S69sh3": { "lane": "structure_plate", "group_id": "bg_open_roof_truck", "segment_id": "seg_03", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png", "seed_asset_id": "c94c53e3-76a2-4f78-b4ae-95204318d3c2", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S69sh3.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png" }, "S71sh17": { "lane": "structure_plate", "group_id": "bg_open_roof_truck", "segment_id": "seg_02", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png", "seed_asset_id": "c94c53e3-76a2-4f78-b4ae-95204318d3c2", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S71sh17.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_open_roof_truck_sel.png" }, "S75sh10": { "lane": "structure_plate", "group_id": "bg_abandoned_airport", "segment_id": "warehouse_threshold", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_abandoned_airport_sel.png", "seed_asset_id": "fa2c7e30-8192-4bac-9a49-706031bf5a13", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L256B01.png", "bg_reason": "", "bypass_reason": "prev" }, "S89sh42": { "lane": "structure_plate", "group_id": "bg_island_research_complex", "segment_id": "seg_rooftop", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/background_chain/seed_bg_island_research_complex_sel.png", "seed_asset_id": "ae92432a-4956-46ca-9845-8c2d71d637c5", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L278B01.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/images/a28fb896-b811-463c-8bcc-ba732968bd7c/conti/conti_S89sh42.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/8f8a58f6-cc7d-4143-940a-1c9c6ab707f7/episodes/a28fb896-b811-463c-8bcc-ba732968bd7c/images/background_chain/L278B01.png" } } }, "step_id": "shot_conti_light", "run_id": "988ded67-56ca-4d76-9936-888c13c33aa3", "resolved_model": "gpt-image-2.5-sunburst", "updated_at": "2026-09-19T02:49:39.060264+00:00", "project_config_snapshot": {} }