{ "status": "partial", "applicable_count": 11, "completed_count": 9, "failed_count": 2, "schema_version": 3, "config_hash": "b9c71c81b67c097c", "data": { "contis": { "S1sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S1sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L01B01.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside a high-school classroom, beside the window overlooking the sky. White LED classroom lighting fills the room.\n\nSHOT TEXT (authoritative, Korean): 창밖을 향해 고개를 돌린 현석의 눈동자에 희미한 생기가 도는 측면 얼굴.\n\nCARRIED STATE (persist exactly): Hyunseok is no longer wearing his transparent AR glasses; they remain discarded on his desk. Jeho remains seated in his own AR glasses with a writing instrument in his tense 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: At Hyunseok's seated eye height, the tracking camera briefly tightens from just behind his shoulder into a clean profile close-up, with his face held in the left half and generous look space opening toward the classroom window on the right. His head is caught midway through the turn, and shallow focus holds on the faint vitality returning to his eyes as he watches the birds outside.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: classroom window (visible beside Hyunseok; opening state unspecified) — The camera looks toward the window area with the flying flock visible outside beyond it; used as Provides right-side look space and the destination of Hyunseok's turning gaze; rows of seated students (wearing transparent AR glasses and watching the same government promotional video) — Only soft, partial figures remain behind Hyunseok along the classroom rows; used as Recedes out of focus to contrast collective uniformity with Hyunseok's private response.\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/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L01B01.png" ], [ "char:현석", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/24359dc0-6703-4e64-93d9-71408195ee41.png" ] ], "asset_id": "9f6d8dfe-d37d-443b-bb45-56e0d1940a11" }, "S1sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S2sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S2sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L02B01.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside a quiet school stairwell, midway along the gray concrete steps.\n\nSHOT TEXT (authoritative, Korean): 낡고 건조한 질감의 회색 콘크리트 계단 한가운데에 제호가 홀로 앉아 핸드폰 화면을 뚫어지게 내려다보는 전경.\n\nCARRIED STATE (persist exactly): Jeho continues to hold his smartphone, whose screen is still on the central “조회하기” button before he checks the result.\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 high above the lower side of the staircase, a steep downward wide composition holds Jeho alone near the middle of the steps before the crane begins its descent. His seated figure remains small within the gray stair geometry, torso folded toward the phone held between his hands and attention sealed to its screen.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: gray concrete staircase (old and dry in texture; otherwise empty around Jeho) — The flights and step edges run diagonally through the overhead frame around the isolated figure; used as Creates a severe geometric field that emphasizes Jeho's isolation; Jeho's phone (held in both hands with the '조회하기' button on screen) — The screen faces Jeho and is seen only at a steep, distant oblique angle from above; used as Forms the small focal point toward which the later crane descent will tighten.\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/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L02B01.png" ], [ "char:제호", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/257f4438-7fc3-45f2-bdbf-6a16d624b717.png" ] ], "asset_id": "ec41c5d6-7814-4d0a-a7ec-08eb9db47376" }, "S2sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S2sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S3sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S3sh2.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: Outside in a narrow, worn urban alley bordered by advertising-covered walls and neon light.\n\nSHOT TEXT (authoritative, Korean): '너는 내 마지막 희망이다'라고 적힌 종이를 움켜쥔 제호의 주먹에 핏대가 선 클로즈업.\n\nCARRIED STATE (persist exactly): Jeho keeps the note from his father's opened package clenched and crumpled in his hand. Hyunseok is nearby with his camera and two backpacks, as established moments later.\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: Beside Jeho at waist height, the dolly-in ends on the explicitly extreme close oblique view of his fist crushing the note, with raised tendons and knuckles carrying most of the frame while the paper remains below the nonhuman-object occupancy limit. The words '너는 내 마지막 희망이다' stay legible across the creased section, and a narrow edge of the opened package provides physical context behind his hand.\n- FRAMING SCALE: insert close-up on a detail\n- KEY BACKGROUND ELEMENTS: father's note (being tightly crumpled; message remains legible) — The written face is angled obliquely toward camera, exposing the phrase '너는 내 마지막 희망이다' across the creased paper; used as Serves as the emotional focal detail pressed against Jeho's tense knuckles; opened delivery package (opened by Jeho) — Only a narrow portion sits beyond the fist as scale and narrative context; used as Prevents the note from becoming an ungrounded isolated graphic.\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:제호", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/257f4438-7fc3-45f2-bdbf-6a16d624b717.png" ] ], "asset_id": "b206f38f-0c1f-4c0a-91ff-cd7c355b12e4" }, "S3sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S3sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S4sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S4sh4.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: Outside on the playing surface of an empty, worn basketball court near its old hoop.\n\nSHOT TEXT (authoritative, Korean): 치열한 시합 중, 땀방울이 흩날리며 현석과 제호의 어깨가 공중에서 강하게 부딪히는 찰나.\n\nCARRIED STATE (persist exactly): Hyunseok's camera remains set up at the side of the court and recording throughout the basketball game.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: The lateral track tightens along the side of the playing area and dips slightly below shoulder level, holding Hyunseok and Jeho in opposing crossing profiles at the instant their airborne shoulders collide. Their torsos divide the left and right halves, legs caught in different phases of lift, while scattered sweat crosses the narrow central gap and each remains absorbed in overpowering the other.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: 현석 in the middle-left of the frame, midground, moves toward 제호's shoulder; 제호 in the middle-right of the frame, midground, moves toward 현석's shoulder.\n- KEY BACKGROUND ELEMENTS: court floor (part of the empty basketball court) — Its plane cuts diagonally below the airborne players and leaves visible landing space beneath them; used as Provides a stable horizon and makes the collision's lift readable; worn basketball hoop (old and standing on the empty court) — The hoop is seen off-axis in the background rather than aligned behind either player's head; used as Anchors the competitive setting while remaining secondary to the collision.\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:현석", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/24359dc0-6703-4e64-93d9-71408195ee41.png" ], [ "char:제호", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/257f4438-7fc3-45f2-bdbf-6a16d624b717.png" ] ], "asset_id": "43802d27-0be6-4e5f-a75b-0282eeb4e4b5" }, "S4sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S5sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S5sh2.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: Outside on a central-city street under a red sunset, with wind moving fallen leaves through the open roadway.\n\nSHOT TEXT (authoritative, Korean): 제호가 목에 핏대를 세운 채 얼굴을 찌푸리며 현석을 향해 격렬하게 소리치는 찰나.\n\nCARRIED STATE (persist exactly): Hyunseok continues to carry the camera he has been using to photograph the city scenery.\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: Place the handheld camera close behind Hyunseok's three-quarter shoulder, slightly below Jeho's eye line, with Hyunseok forming a soft foreground edge on the left and Jeho's strained face occupying the right half. Jeho pitches forward in the instant of shouting, neck taut and eyes fixed on Hyunseok's face, while restrained handheld drift preserves the unstable space between them.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: urban street (visible as limited background context); used as Held softly behind Jeho so the close confrontation remains grounded in the street.\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:현석", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/24359dc0-6703-4e64-93d9-71408195ee41.png" ], [ "char:제호", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/257f4438-7fc3-45f2-bdbf-6a16d624b717.png" ] ], "asset_id": "662ca270-70dc-4b2a-ba37-7b838d4e874d" }, "S5sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S6sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S6sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L06B01.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 at the bench directly in front of a massive futuristic examination-facility entrance and its metal facade.\n\nSHOT TEXT (authoritative, Korean): '유니타스 프로젝트' 로고가 박힌 육중한 미래식 금속 건물 앞, 낡은 벤치에 제호와 현석이 굳은 묵념 자세로 나란히 앉아 있는 전경.\n\nCARRIED STATE (persist exactly): Hyunseok has brought his camera to the bench and retains it until he hands it to Jeho.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At the widest point of the elevated crane path, look diagonally down across Jeho and Hyunseok on the bench toward the examination building, briefly holding before the descent begins. The two seated figures remain separated but small in the lower third, the worn bench spans beneath them, and the visible Unitus Project logo anchors the upper portion of the building without flattening the oblique axis.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: 제호 in the lower-left of the frame, midground; 현석 in the lower-center of the frame, midground; Unitus Project logo on examination building in the upper-center of the frame, background.\n- KEY BACKGROUND ELEMENTS: future-style examination building (fully visible behind the bench) — Its main mass faces the camera obliquely, preserving both the front and one receding side; used as Establishes the institutional scale over the two seated figures; Unitus Project logo (clearly visible on the building) — The logo-bearing face is turned toward the camera and displays the text “유니타스 프로젝트.”; used as Occupies the upper background as the institutional narrative anchor; worn bench (occupied by Jeho and Hyunseok) — The bench is seen from an elevated diagonal angle, with its seat length running across the lower frame; used as Links both characters within the same silent foreground 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/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L06B01.png" ], [ "char:제호", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/257f4438-7fc3-45f2-bdbf-6a16d624b717.png" ], [ "char:현석", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/24359dc0-6703-4e64-93d9-71408195ee41.png" ] ], "asset_id": "6ac60dff-2248-4420-bf37-c2164aed6f5c" }, "S6sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S7sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S7sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L07B01.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 corner recess of a broad, cold metal corridor in the examination facility. Red guide lights blink along the passage.\n\nSHOT TEXT (authoritative, Korean): 복도 모퉁이 구석 바닥에 주저앉은 현석이 자신의 목을 강하게 움켜쥔 채 고통으로 일그러진 얼굴로 오열하는 모습.\n\nCARRIED STATE (persist exactly): The camera entrusted to Jeho remains in Jeho's possession, although its exact placement is not specified in the 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: Just beyond the corridor corner at seated chest height, complete the dolly-in on an off-axis three-quarter view of Hyunseok pressed into the corner. His folded body occupies the right two-thirds, keeping his throat-gripping hand and anguished face in the same focal plane as the move settles into a brief near-static hold; the receding corridor remains visible along the left edge.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: metal corridor corner (encloses Hyunseok on two sides) — The inner corner opens diagonally toward the camera, with one wall receding into the corridor; used as Compresses Hyunseok into the right side while leaving the corridor as a narrow escape line; corridor floor (supporting Hyunseok's seated body); used as Keeps his collapsed posture physically legible beneath him; red guide light (blinking) — Its visible signaling face is angled along the corridor rather than square to the lens; used as Adds intermittent red emphasis within the wider corridor context.\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/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L07B01.png" ], [ "char:현석", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/24359dc0-6703-4e64-93d9-71408195ee41.png" ] ], "asset_id": "7552d22d-dc73-4e5b-8088-f36727f1e4a3" }, "S7sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S8sh2": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S8sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S9sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S9sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L08B01.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 low-lit procedure area of an examination laboratory, centered on two adjacent tilted metal tables with restraints. Red warning lights glow through dense white vapor around the operating machinery.\n\nSHOT TEXT (authoritative, Korean): 통제된 낮은 조도 아래 붉은 경고등과 짙은 흰 연기가 깔린 실험실, 45도 기울어진 차가운 금속 실험대 위에 현석과 제호가 두꺼운 구속구로 나란히 결박된 전경.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Hyunseok is positioned lengthwise on the 45-degree-inclined metal experiment table beside Jeho, with his torso, arms, and legs held against the table by thick restraints. His head rests against the inclined surface as his body faces upward.\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Jeho is positioned lengthwise on the 45-degree-inclined metal experiment table beside Hyunseok, with his torso, arms, and legs held against the table by thick restraints. His head rests against the inclined surface as his body faces upward.\n\nCARRIED STATE (persist exactly): Hyunseok is held by restraints beside Jeho as they lose consciousness. Jeho is positioned lengthwise on the 45-degree-inclined metal experiment table beside Hyunseok, with his torso, arms, and legs held against the table by thick restraints. His head rests against the inclined surface as his body faces upward. The camera remains Jeho's entrusted possession, though the script does not establish its placement around the restraints.\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 a high three-quarter position beyond the foot end of the forty-five-degree inclined table, hold a static diagonal wide view that preserves the full table, both restrained figures, and the surrounding laboratory. Hyunseok and Jeho lie side by side across the middle of frame with their secured limbs following the table's incline, while the foot end remains nearer the lower foreground and their faces recede toward the upper background.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: 현석 in the middle-left of the frame, midground; 제호 in the middle-right of the frame, midground; forty-five-degree inclined experimental table in the middle-center of the frame, midground.\n- KEY BACKGROUND ELEMENTS: inclined experimental table (fixed at a forty-five-degree angle and occupied by both men) — The foot end faces the lower foreground while the table rises diagonally toward the restrained men's heads; used as Defines the dominant diagonal and displays both captives in one institutional apparatus; thick restraints (fastened around both men) — Their fastening sections cross the bodies and follow the angled plane of the table; used as Makes the loss of movement legible within the wide composition; red warning light (active) — Its signaling face is visible obliquely within the wider laboratory space; used as Provides the red warning illumination specified in the laboratory; white smoke (thick across the laboratory); used as Layers the open space around the inclined table without obscuring both restrained 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/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L08B01.png" ], [ "char:현석", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/24359dc0-6703-4e64-93d9-71408195ee41.png" ], [ "char:제호", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/257f4438-7fc3-45f2-bdbf-6a16d624b717.png" ] ], "asset_id": "436d380b-8294-4bd6-8c76-487ca58584f1" }, "S10sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S10sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L10B01.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 home bathroom, directly before the mirror and washbasin area.\n\nSHOT TEXT (authoritative, Korean): 현석이 고통스럽게 입을 크게 벌리고 처절한 눈물을 쏟아내는 얼굴 클로즈업.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At slightly below eye height and offset from the mirror axis, the dolly-in ends on an extreme off-axis close-up of 현석, his tear-streaked face occupying roughly four-fifths of the frame as his jaw opens in anguish. His face is held in a three-quarter angle rather than toward the lens, with the camera-distance change carrying the escalation while the bathroom surroundings fall outside the narrow frame.\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: 현석 in the middle-center of the frame, 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/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L10B01.png" ], [ "char:현석", "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/reference/24359dc0-6703-4e64-93d9-71408195ee41.png" ] ], "asset_id": "459bd549-42b4-4d7f-8de9-697897232749" }, "S10sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S10sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S11sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null } }, "map_conti": {}, "conti_pack": "5.202607222353", "lane_conti": { "S3sh4": { "lane": "structure_plate", "group_id": "bg_narrow_alley", "segment_id": "SEG_01", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/background_chain/seed_bg_narrow_alley_sel.png", "seed_asset_id": "2ebe2c69-b115-43c8-9ce0-b0bc0a4ea213", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/background_chain/seed_bg_narrow_alley_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S4sh7": { "lane": "map_marker", "group_id": "bg_outdoor_basketball_court", "segment_id": "SEG_01", "marker_attempts": 3, "status": "failed", "error": "marker map check 3회 소진: 원본 도면의 중앙에 있던 A1 라벨이 삭제되었습니다.", "marker_check": { "markers_ok": false, "details_ko": "원본 도면의 중앙에 있던 A1 라벨이 삭제되었습니다." } }, "S6sh1": { "lane": "structure_plate", "group_id": "bg_testing_facility", "segment_id": "SEG_FRONTAGE", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/background_chain/seed_bg_testing_facility_sel.png", "seed_asset_id": "2d749cfd-06fa-4381-808b-b8ad65961980", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L06B01.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/images/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/conti/conti_S6sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/46575226-4c2f-4334-b16a-429b11371e24/episodes/5a7f5cfd-5b80-4f10-a4e5-1c8519aa244c/images/background_chain/L06B01.png" }, "S11sh1": { "lane": "map_marker", "group_id": "bg_city_street", "segment_id": "SEG_2", "marker_attempts": 3, "status": "failed", "error": "marker map check 3회 소진: CAM 마커가 지정된 보행자 구역 내부가 아닌 도면 하단 여백(외부)에 잘못 배치되었으며, E2 마커도 중앙 부근이 아닌 너무 왼쪽에 위치해 있습니다.", "marker_check": { "markers_ok": false, "details_ko": "CAM 마커가 지정된 보행자 구역 내부가 아닌 도면 하단 여백(외부)에 잘못 배치되었으며, E2 마커도 중앙 부근이 아닌 너무 왼쪽에 위치해 있습니다." } } } }, "step_id": "shot_conti_light", "run_id": "e29d838d-b8c7-4227-9149-3b49161ac0e0", "resolved_model": "gpt-image-2", "updated_at": "2026-08-24T10:49:40.595361+00:00", "project_config_snapshot": {} }