{ "status": "completed", "applicable_count": 65, "completed_count": 65, "failed_count": 0, "schema_version": 4, "config_hash": "123987836f4b9e64", "data": { "contis": { "S1sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S1sh4.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The outdoor frontage of an earthenware stall in a crowded market, under harsh midday sun.\n\nSHOT TEXT (authoritative, Korean): 헌병 장교의 총구가 이관회의 턱밑 살에 바짝 눌린 측면 클로즈업.\n\nCARRIED STATE (persist exactly): Harsh midday sunlight covers the market; smoke rises beside the pottery stalls. 이관회: He stands in front of the pottery stall with a muzzle pressed beneath his chin.\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 beside the two men, just below 이관회's chin with a slight upward tilt, observing the actual contact nearly perpendicular to their confrontation axis. His tense profile occupies the right half while the 헌병 장교's gripping hand and partial profile enter from the left; the muzzle presses beneath the chin without obscuring the compressed skin, and both men's attention remains on each other rather than the lens. Emphasize only the final reduction in camera distance, retaining the established profile alignment and shallow background separation.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 장교의 총 (Muzzle pressed tightly beneath 이관회's chin) — Seen from the side, with its muzzle angled upward toward the underside of the chin; used as A narrow diagonal connects the officer's hand to the point of pressure; the weapon occupies substantially less space than the human features; 옹기 좌판 (Present behind the confrontation); used as Soft peripheral context preserves the market location without competing with the contact.\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:이관회", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/69254565-1c94-4962-a073-922e40cca9e8.png" ] ], "asset_id": "c6ee6c62-d713-4a4c-bed5-b419c1abb827" }, "S1sh10": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S1sh10.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The open dirt space at the center of a sunlit market, approached from the surrounding stalls.\n\nSHOT TEXT (authoritative, Korean): 양팔을 자연스럽게 내린 빈손의 안규홍이 헌병들을 향해 성큼 걸음을 내디뎌 한쪽 발이 공중에 떠 있는 전신.\n\nCARRIED STATE (persist exactly): The heavy carrying frame now rests on the dirt in the market center; harsh sunlight and stall smoke persist. 안규홍: He advances empty-handed, wearing a dirt-stained jeogori.\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 established waist-height position beside the military police, track backward off 안규홍's approach axis, directly observing his full body in an oblique low-angle view. Place him center-right with clear space beneath his suspended foot and beside both empty, naturally lowered hands; cropped police shoulders occupy the left foreground, their heads turning toward him at slightly different phases while his attention stays on the officer beyond that edge. Make his advancing position the sole emphasis, maintaining the retreating camera's distance, the confrontation side, and the existing daylight.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: police-side end of the market aisle in the lower-left of the frame, foreground; clear ground beneath the approaching man's lifted foot in the lower-right of the frame, midground.\n- KEY BACKGROUND ELEMENTS: 장터 통로의 흙바닥 (Visible beneath 안규홍's approaching feet); used as An uninterrupted ground strip makes the lifted foot and advancing stride unmistakable; 옹기 좌판 (Bordering the confrontation area); used as Peripheral stall shapes maintain the aisle's depth and realistic human scale.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "5f12e311-afbc-4a66-84b1-e7a0a230bef2" }, "S1sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S2sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S2sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L03B02.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The hearth mouth inside a modest home's kitchen at dawn, with a crouching space directly before the rekindling red embers.\n\nSHOT TEXT (authoritative, Korean): 어스름한 새벽, 아궁이 불씨를 향해 입술을 모으고 입김을 뿜어내는 안규홍의 쪼그려 앉은 옆얼굴.\n\nCARRIED STATE (persist exactly): A dying ember glows inside the hearth in the dim dawn; the carrying frame is in a corner. 안규홍: He crouches sleepily before the hearth, with a cold-rice bundle tucked at his waist.\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 beside the hearth at the height of 안규홍's crouching face, directly observing his sleepy profile with a level lens. His head and folded shoulder occupy the left two-thirds, his pursed lips aimed toward the hearth opening at lower right, with the ember positioned naturally below his downward eyeline. Keep a small portion of his bent knee at the bottom edge to explain the crouch, and convey the blowing through his mouth and posture rather than adding visible breath vapor.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 아궁이 입구 (Containing a fading ember that brightens as 안규홍 blows) — The opening is seen obliquely beside his profile, ahead of and below his mouth; used as Occupies less than a third of the frame and supplies the visible destination of his breath.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L03B02.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "d94541fe-9ddd-41d9-8586-47426b75a334" }, "S2sh13": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S2sh13.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L03B01.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The gap in a reopened rustic wicket gate at a modest home's outdoor entrance in the early dawn.\n\nSHOT TEXT (authoritative, Korean): 문틈에 얼굴만 내민 채 능청스럽게 눈웃음을 치는 안규홍의 얼굴 클로즈업.\n\nCARRIED STATE (persist exactly): The gate has reopened; the lidded medicine pot contains all the herbs, and an added log burns in the hearth. 안규홍: He is outside with his carrying frame and the rice bundle tucked back at his waist, leaning his face through the gate.\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 just inside the gate and outside its swing, at 안규홍's returning eye height and oblique to his eyeline toward his mother. His face occupies the center-left while a narrow gate edge remains at right, hiding his body so that only his head projects through the opening; his teasing smile and narrowed eyes address his mother off-screen, never the lens. Emphasize only the last narrowing of camera distance, preserving the established angle and unmediated view through the opening.\n- FRAMING SCALE: close-up\n- FRAME LAYOUT: gate edge beside the protruding face in the middle-right of the frame, foreground.\n- KEY BACKGROUND ELEMENTS: 사립문 (Reopened, with 안규홍's face protruding through the opening) — An oblique inner-facing edge is visible beside his face; the gate conceals his body; used as A narrow lateral boundary makes the playful reappearance legible without letting the gate outweigh the face.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.", "skipped_reason": null, "error": null, "ref_paths": [ [ "plate", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L03B01.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "23016f46-9848-4b3b-ae34-c239ed6abd95" }, "S2sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S3sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S3sh5.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B04.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The sun-beaten dirt work yard of a traditional estate, at the spot where a large straw load is being lifted onto a carrying frame.\n\nSHOT TEXT (authoritative, Korean): 양쪽에서 볏짐을 번쩍 들어 올려 허공에 띄운 채 멈춘, 팔 근육이 팽팽하게 부풀어 오른 안규홍과 장신 조선인 일꾼의 상체.\n\nCARRIED STATE (persist exactly): Blazing sunshine covers the dirt yard and wooden platform; the fallen rice-straw load is now raised. 안규홍: He stands gripping a corner of the load, wearing worn straw shoes.\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 dolly to a stop diagonally outside the line between the lifters, below chest height with a slight upward tilt, directly observing both upper bodies above the suspended rice bundle. 안규홍 occupies the left and 장신 조선인 일꾼 the right, their hands and taut forearms remaining readable as they look down toward their respective grips; synchronized effort retains individual elbow angles and different shoulder compression rather than mirrored poses. Emphasize the final decrease in camera distance, keeping the bundle across the lower third and both bodies as scale references.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 볏짐 (Lifted clear of the ground and held between the two workers) — Opposite gripped edges are visible beneath the men's arms; used as Spans the lower third as a shared load, leaving both sets of hands, forearms, and upper bodies unobstructed; 마당의 흙바닥 (Below the suspended bundle); used as Small lateral glimpses establish clearance beneath the load without adding airborne dust.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B04.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "3e173d0f-3019-472e-bff1-f56a6ba53c08" }, "S3sh18": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S3sh18.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B04.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 estate's guest-wing room beside its open doorway, with morning daylight entering from the yard and a view toward the main gate.\n\nSHOT TEXT (authoritative, Korean): 대문 쪽을 향해 걷는 중인 mid-stride 자세의 안규홍 뒷모습을 노려보며 꼿꼿이 선 박진성의 전신.\n\nCARRIED STATE (persist exactly): The sarangchae door remains open; a drinking table stands inside with a cup set down upon it. 안규홍: He walks toward the gate carrying his frame, with the small jade-colored cloth bundle tucked into it and worn straw shoes on his feet. 박진성: He remains standing after rising abruptly.\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 diagonal position inside the room, behind and to one side of 박진성, with a level lens below his eye height and enough distance to retain his full figure beside the doorway. 박진성 occupies the left midground, his neck angled after 안규홍 and his body rigid from the insult, while 안규홍's full back appears farther away within the opening at center-right, caught mid-stride toward the gate beyond the crop. Observe the shared space directly and emphasize only 안규홍's increasing separation, retaining the static framing and keeping both eyelines away from the lens.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: interior area beside the doorway occupied by 박진성 in the middle-left of the frame, midground; open doorway framing the departing 안규홍 in the middle-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: 사랑채 출입문 (Open onto the yard) — Seen from inside at an oblique angle, with the departing 안규홍 visible through the opening; used as Separates the rigid interior figure from the receding exterior figure without breaking their shared spatial relationship; 안규홍의 지게 (Carried on his back as he leaves) — Its rear is visible above and beside his back; used as Maintains his working silhouette at a natural scale within the distant doorway.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B04.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:박진성", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/71306446-e143-4186-97b6-d91271898082.png" ] ], "asset_id": "f536a455-5400-48c3-b56e-7a44b413639e" }, "S3sh26": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S3sh26.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B04.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 stone step at the main gate inside a traditional estate's outdoor yard.\n\nSHOT TEXT (authoritative, Korean): 달래를 마주보며 참지 못하고 활짝 웃는 안규홍의 흙먼지 묻은 정면.\n\nCARRIED STATE (persist exactly): The sarangchae door remains open with the drinking table inside; strong sunlight continues over the yard. 안규홍: He still wears his loaded carrying frame and worn straw shoes, holding the partly eaten hot 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: Continue the slight inward drift from just behind and outside 달래's shoulder at 안규홍's eye height, retaining the established offset from their eyeline. Her shoulder forms a narrow, soft strip at the left edge while his dusty three-quarter face occupies center-right, turning back into an unrestrained smile directed toward her face just outside the crop. Emphasize his returning gaze rather than a new camera angle, keeping the carrying frame visible only as a small contextual edge behind his shoulder and observing their exchange directly.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 안규홍의 지게 (Still carried on his back) — A small oblique portion is visible behind his shoulder; used as Keeps the intimate smile attached to his ongoing departure and physical workload.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B04.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "8e95141e-5e59-4329-a4a2-daac49ee8836" }, "S4sh17": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S4sh17.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The outdoor frontage of a straw-sandal stall along a densely packed daytime market lane.\n\nSHOT TEXT (authoritative, Korean): 짚신전 앞으로 다가온 배상도와 안규홍의 시선이 공중에서 부딪히는 순간.\n\nCARRIED STATE (persist exactly): The jade-colored delivery bundle rests beside the straw-shoe stall, and the heavy vegetable basket remains on the platform; steam rises from the soup cauldron. 안규홍: He still wears his carrying frame and old straw shoes with a big toe protruding; the potato is fully eaten. 배상도: He carries the tax ledger at the straw-shoe stall.\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 encounter stage from the aisle side and momentarily settle below eye height, directly observing both men in opposing three-quarter views without crossing their confrontation axis. Place 안규홍 on the left with the carrying frame behind his shoulder and 배상도 on the right at the end of his approach, his ledger held low; their faces turn toward one another across the central gap, making the mutual recognition—not the camera—the destination of their attention. Emphasize only that convergence of their eyelines, retaining a balanced upper-body distance and the shoe stall as a quiet lateral anchor before tracking onward.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 짚신전 (Stocked with straw shoes beside the encounter) — The display is seen obliquely from its aisle side; used as A peripheral background strip establishes the location without introducing additional visible people; 배상도의 장부 (In his possession after checking the market accounts) — Held low and obliquely, with no readable page content presented to the camera; used as A small lower-frame element identifies the administrative threat without displacing the faces; 안규홍의 지게 (Carried on his back) — Seen at an angle behind his shoulder; used as Retains his working silhouette and continuity with his arrival at the stall.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:배상도", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/28ee8d7a-14df-4721-bcd8-4af5cab5662a.png" ] ], "asset_id": "47ad740d-fb4b-46a1-8596-baf4ba0db6b0" }, "S4sh24": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S4sh30": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S5sh21": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S5sh28": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S5sh39": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S6sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S6sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S6sh4.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The far end of a crowded outdoor market alley, along the route away from the fight.\n\nSHOT TEXT (authoritative, Korean): 북적이는 사람들 사이로 장터 골목 끝을 향해 뛰어가는 도중, 한쪽 다리를 길게 뻗고 다른 쪽 발은 지면에서 막 떨어진 자세의 안규홍의 작아진 뒷모습.\n\nCARRIED STATE (persist exactly): The sunlit market remains unchanged immediately after the fight. 안규홍: He continues fleeing with his carrying frame, worn straw shoes and injured mouth.\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 alley and offset along one side, hold the track near shoulder height with a level view between nearby people toward 안규홍's small, receding back. Place him in the upper-center opening with one leg stretched forward and the other foot lifting, his head aimed toward the far end; nearby people occupy unequal edge fragments, raising their heads at different moments toward the distant runner. At this stage-ending frame, let only his distance increase before beginning the planned lateral curve toward the rumor-bearers, preserving a direct observation rather than a remembered or imagined escape.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: far end of the market alley in the upper-center of the frame, background.\n- KEY BACKGROUND ELEMENTS: 장터 골목 (Occupied by people, with 안규홍 running toward its far end) — Its length recedes obliquely from the foreground edges toward the upper-center distance; used as Maintains a narrow sightline to the runner through staggered shoulders and uneven gaps.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "87e8fdb7-2c4f-4534-b30e-95287a82fa63" }, "S7sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S7sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/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 main gate of a traditional estate's outdoor courtyard, behind the newly arrived constables in late-afternoon light.\n\nSHOT TEXT (authoritative, Korean): 조선인 순검들 뒤에 서서 턱을 치켜들고 안규홍을 손가락으로 가리키는 배상도의 의기양양한 상체.\n\nCARRIED STATE (persist exactly): The carrying frame stands in the middle of the late-afternoon yard. 배상도: He stands behind the arriving police.\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 inside the gate, offset from the officers' entry line and slightly below 배상도's eye height, observing his upper body through the gap beside their shoulders. Keep 배상도 in the right middle ground, chin raised and pointing left toward 안규홍 off-screen; the officers form unequal, cropped foreground edges rather than a symmetrical escort portrait. Hold this oblique composition and exposure as the pointing hand extends, emphasizing the gesture alone while 배상도 fixes his attention on the man he is identifying.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 대문 (The entry passage is clear as the officers come into the courtyard) — Seen obliquely from its courtyard side behind the entering group; used as Anchors 배상도 behind the officers while their differing shoulder positions leave his face and pointing hand visible.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B01.png" ], [ "char:배상도", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/28ee8d7a-14df-4721-bcd8-4af5cab5662a.png" ], [ "char:조선인 순검(안규홍 체포·옥사 담당)", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/81e55a3b-6888-4f5c-a6cb-43bc0520db51.png" ] ], "asset_id": "84d0c93b-13f3-4025-8095-d54b858c4cd0" }, "S7sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S7sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S8sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S8sh5.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L05B01.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The inner side of a half-open rustic wicket gate leading into a modest home's darkening outdoor yard.\n\nSHOT TEXT (authoritative, Korean): 반쯤 열린 사립문 틈으로 어두운 표정의 달래가 마당에 들어선 전신.\n\nCARRIED STATE (persist exactly): The kitchen is dim; smoke rises from the unlit hearth, and the gate has opened. 달래: She has entered through the gate.\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 courtyard side of the kitchen entrance, hold below eye level with a level optical axis, looking obliquely through the half-open gate as a direct observer. 달래's full figure occupies the middle-right opening, caught transferring her weight into the courtyard, her troubled gaze directed toward 이관회 off-screen beside the kitchen. Keep the gate to a narrow framing edge and establish this still entry composition before the track toward the jars begins.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 사립문 (Half-open as 달래 enters) — The gate is seen obliquely from its courtyard side, leaving the entrance opening readable; used as Provides a narrow frame beside her full figure without masking her expression; 마당 (달래 is entering from the gate); used as Open ground ahead of her establishes the route toward the kitchen.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L05B01.png" ], [ "char:달래", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/8a0d2c29-88fb-4d7d-b097-23600d00603e.png" ] ], "asset_id": "3d31da46-a00c-40fc-abe5-d1e93ac679d0" }, "S8sh6": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S8sh6.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L05B02.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Beside the earthenware storage jars in a modest home's outdoor yard at dusk or early night.\n\nSHOT TEXT (authoritative, Korean): 장독대 옆, 이관회를 걱정스레 올려다보는 달래의 흔들리는 눈빛 클로즈업.\n\nCARRIED STATE (persist exactly): Darkness settles around the jars and the open gate; the hearth has not been lit. 달래: She stands beside the jar terrace.\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 established approach nearly settle beside the jars, just above 달래's eyes and beside 이관회's shoulder, looking gently downward without crossing the courtyard-facing side of their conversational axis. Her three-quarter face occupies the center-left, chin raised toward 이관회's face above the right frame edge; his cropped shoulder and rear head remain a thin foreground margin, angled toward her without blocking either eye. Emphasize the closing distance rather than a lighting or eyeline change, using shallow focus to hold her unsettled eyes as she waits for reassurance.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 장독대 (Beside the two characters during their conversation); used as A soft peripheral fragment anchors the close-up to their new position without competing with her eyes.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L05B02.png" ], [ "char:달래", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/8a0d2c29-88fb-4d7d-b097-23600d00603e.png" ] ], "asset_id": "849ed822-4ebd-4e1d-a09a-8e8abf015a41" }, "S8sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S9sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S9sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L11B01.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the police outpost's barred holding cell at night, in the open floor area used to restrain a prisoner; the light source is unspecified.\n\nSHOT TEXT (authoritative, Korean): 일본 순사가 휘두른 굵은 몽둥이가 안규홍의 뺨에 정통으로 격돌한 찰나.\n\nCARRIED STATE (persist exactly): It is night inside the barred jail. 안규홍: He is under restraint with his arms forced behind his back and blood in his mouth.\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 inside the cell on the striking officer's side, close to 안규홍 and above his eye line, looking obliquely downward at his cheek and upper torso as a direct observer. Catch the baton contacting his cheek at center-right as his head turns away and his eyes break toward the lower frame edge; 일본 순사's cropped profile and striking arm enter from the left, his attention fixed on the cheek below him. Minimize camera travel at contact, retain the baton and turning face in one focal plane, and crop below the upper torso so the restraining officers remain outside this frame.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 몽둥이 (In contact with 안규홍's cheek during the strike) — Crosses obliquely from the officer's side toward the visible cheek; used as Forms a narrow action line connecting the striking arm and the impact without exaggerated foreground scale; 감방 벽 (Encloses the interrogation space); used as A subdued background fragment keeps the blow spatially grounded.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L11B01.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "22e137bb-feb9-4afc-9bbf-5052bc519354" }, "S9sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S9sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S10sh6": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S10sh6.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: The damaged outdoor frontage of a straw-sandal stall in the daytime market, beside a ruined woven mat.\n\nSHOT TEXT (authoritative, Korean): 안규홍을 향해 고개를 돌린 채 원망스럽게 노려보는 조선인 청년의 붉어진 두 눈.\n\nCARRIED STATE (persist exactly): Overturned stalls, torn mats and broken bowls litter the dirt; a trampled single straw shoe lies before the damaged shoe stall. 조선인 청년(짚신전): He stands at the damaged shoe stall, handling its ruined mat; his eyes are reddening.\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 approach just behind and outside 안규홍's left shoulder at 조선인 청년(짚신전)'s eye height, keeping the lens slightly lateral to their eyeline. Hold the young man's turned three-quarter face center-right, his reddened eyes directed past the lens toward 안규홍's off-frame face, while 안규홍's cropped rear head and shoulder form a restrained left foreground edge oriented toward him. Tighten distance alone to emphasize the accusation, retaining the young man's mouth and shoulder rather than reducing the image to an extreme eye detail.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 망가진 짚신전 (Damaged after the market violence) — Only an oblique fragment of the stall frontage remains behind the young man; used as Soft background context connects his accusation to the damage without distracting from his eyes.\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": "a9de656a-ac20-4988-b9cb-ecf760c07b21" }, "S10sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S10sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S11sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S11sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L04B02.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The bare bowing space on the floor inside a modest home's room, washed in bluish dawn light.\n\nSHOT TEXT (authoritative, Korean): 안규홍의 이마가 방바닥에 납작하게 닿은 채 엎드려 있는 전신.\n\nCARRIED STATE (persist exactly): Bluish dawn light fills the house; the small travel bundle has been tied. 안규홍: He is fully prostrate with his forehead against the room floor.\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 gentle rise inside the room and hold in an elevated oblique position beside the mother-son axis, directly observing 안규홍's entire bowed body with his forehead touching the floor. Arrange his folded legs and back diagonally through the lower center toward 안규홍의 어머니 beyond him at upper-right, seated against the wall with bedding around her waist and her gaze lowered toward his small bundle beside the bow. Let the camera's increased distance from the floor be the only emphasized adjustment, preserving their positions through the prolonged pause and keeping the doorway transition for the following action.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 방바닥 (안규홍's forehead rests against it during the deep bow); used as The visible contact beneath his head makes the depth and duration of the bow legible; 방 벽 (Supports the seated mother); used as Anchors her position beyond the bowed figure; 어머니의 이불 (Wrapped around her waist); used as A limited shape around her seated body preserves the domestic context; 작은 봇짐 (Packed for 안규홍's departure); used as Remains small beside the bow, connecting the farewell to the imminent journey.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L04B02.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "336d2b17-9092-4c9b-946a-d0463a1330f3" }, "S11sh9": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S11sh9.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L04B01.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: Immediately outside the rustic wicket gate of a modest home, where a farewell takes place at dawn.\n\nSHOT TEXT (authoritative, Korean): 안규홍의 크고 굵은 손바닥 위로 옥가락지를 억지로 꽉 누르고 있는 달래의 두 손 클로즈업.\n\nCARRIED STATE (persist exactly): The room door and the outer gate are closed behind the departure; dawn light remains bluish. 안규홍: He stands outside with his travel bundle and an open palm receiving a small jade ring. 달래: She stands outside the gate with her hands extended in the ring handover.\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 diagonal dolly approach beside their joined hands, slightly above palm height and tilted downward, observing the exchange directly rather than through either character's eyes. 달래's forearms enter from the left and 안규홍's broad open palm from the right; her two hands press the small jade ring firmly into his palm at center, with all three hands readable and the ring only a small accent. Keep their faces outside the crop and their attention concentrated downward on the exchange, emphasizing only the final reduction in camera distance.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 옥가락지 (Being pressed into 안규홍's open palm by 달래's two hands) — Seen obliquely from above between the pressing fingers and receiving palm; used as Small central narrative detail, kept visible without enlarging it beyond its scale relative 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, "ref_paths": [ [ "plate", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L04B01.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:달래", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/8a0d2c29-88fb-4d7d-b097-23600d00603e.png" ] ], "asset_id": "36b911e5-76fa-4c1f-a0a3-4f1a6003cd32" }, "S11sh16": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S12sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S12sh1.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: An exposed earthen footpath along rice paddies, enveloped in dense dawn fog.\n\nSHOT TEXT (authoritative, Korean): 짙은 안개가 자욱하게 깔린 새벽 논둑길, 봇짐을 진 채 앞으로 한 발을 뻗어 성큼 내디딘 미드 액션 찰나의 안규홍 전신.\n\nCARRIED STATE (persist exactly): Dense dawn fog blankets the rice-field embankment path. 안규홍: He walks with a travel bundle on his shoulder and the jade ring concealed inside his 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: Enter the tracking stage with a momentarily settled, low rear-three-quarter view from beside the field path, retaining 안규홍 alone in full figure. Place him left of center with his bundle on his shoulder, one leg reaching forward and the other carrying his weight; his slightly turned rear silhouette differs from the previous back view without changing the established walking direction. Leave generous space beneath his feet and an oblique stretch of empty path behind him, while his attention stays on the route ahead rather than the following sound.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 논둑길 (Fog obscures the farther reaches of the path; no following figure is yet visible) — The path passes diagonally through the frame with a visible section behind 안규홍; used as Establishes the solitary walk while reserving space for the later arrival; 안규홍의 봇짐 (Carried on his shoulder while he walks) — Its rear and outer side are visible beside his upper back; used as A modest silhouette detail anchoring the departure continuity.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "338fb4b6-2ab4-4852-b958-6a51925690f3" }, "S12sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S12sh5.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: Beneath a large village guardian tree at the outdoor fork below the mountain, where the paddy route meets the mountain path.\n\nSHOT TEXT (authoritative, Korean): 거대한 당산나무 아래 쪼그려 앉아 짚신 끈을 잡은 채 고개를 확 쳐든 염재보의 날카로운 눈빛.\n\nCARRIED STATE (persist exactly): Dawn fog surrounds the fork beneath the sacred tree. 염재보: He sits under the tree holding his straw-shoe ties; his confiscated gun is absent.\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 stage-entry position near 염재보's seated height, looking slightly upward from an oblique angle to his line toward the arriving men. Frame his crouched upper body on the right, with his hands still gripping the straw-sandal ties along the lower edge and a limited section of the tree behind him. Catch his head lifting sharply toward 안규홍 and 이관회 off-screen left, keeping the lens outside that eyeline so the sudden change of attention carries the moment.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 당산나무 (염재보 is crouched beneath the tree at the mountain-foot fork) — Only a section behind his crouched body is visible; used as Locates his pause without letting the tree overwhelm his face and hands; 짚신 끈 (Held in his hands during an interrupted adjustment) — The held ends are visible obliquely at the lower frame edge; used as Preserves evidence of the interrupted action beneath the alert 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:염재보", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/04f51624-904e-42ec-9a7b-8d1d8f747f74.png" ] ], "asset_id": "4fd769e1-1085-4232-a26a-c52a6c64d715" }, "S13sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S13sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S13sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S14sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S14sh9": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S14sh9.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_lakeside_camp_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: The exterior entrance of the central rear tent in a temporary lakeside camp, opening toward the communal cooking area.\n\nSHOT TEXT (authoritative, Korean): 중앙의 낡은 천막을 젖힌 채 밖으로 걸음을 내디딘 강용언의 당당한 전신.\n\nCARRIED STATE (persist exactly): Thin potato porridge boils in the large iron pot below the rock; individual earthenware bowls have been distributed on the cleared mat. 강용언: He emerges from the central tent with a sword at his waist and a sun-darkened face.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: Continue the reveal pan from beside the meal area at a low height, tilting gently upward while remaining oblique to 강용언's outward walking axis. Keep his full figure slightly right of center, one hand holding the tent cloth aside and his leading foot clearing the entrance, with his sword visible at his side and the displaced cloth occupying only a limited portion behind him. His face turns toward the cooking-pot area off-screen left rather than toward the lens; let his advancing position drive the frame while the men making way remain outside this selected crop.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 중앙 천막 입구 (Its old cloth is held aside as 강용언 steps out) — The entrance and one adjoining side are seen obliquely behind his body; used as Frames the emergence without enlarging the tent cloth into an overpowering foreground object; 강용언의 칼 (Worn at his side as he exits) — Seen obliquely alongside his moving body; used as A proportionate character detail within the full-body 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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_lakeside_camp_sel.png" ], [ "char:강용언", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/c56aa30c-86d4-404a-a106-39f9dd28d9ec.png" ] ], "asset_id": "eb1859c6-e579-43d9-9942-d45d4fe3b7ba" }, "S14sh15": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S14sh15.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The outdoor eating place on a woven mat beside the large iron pot below a rock in the lakeside camp.\n\nSHOT TEXT (authoritative, Korean): 고개를 가볍게 숙인 채 단단한 눈빛으로 강용언을 마주 보는 안규홍의 정면.\n\nCARRIED STATE (persist exactly): The porridge pot, distributed earthenware bowls and cleared mat remain beside the lakeside shelters; packed supplies stay tied. 안규홍: He sits with a partially eaten bowl of porridge and the jade ring concealed in his 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: Settle the track at seated eye height behind and beside 강용언's outer shoulder, observing 안규홍 directly from slightly off his facial axis. 안규홍's face and bowed upper body occupy the center-right, his firm eyes fixed on 강용언's face just outside the frame, while a narrow, soft shoulder anchors the left foreground. Hold the established distance and lighting, making the slight lowering of 안규홍's head the single emphasized change as he offers his labor rather than accepting charity.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 임시 막사 (Constructed from old cloth and woven mats) — Only a soft, partial exterior is visible behind 안규홍; used as Provides restrained camp context without competing with his 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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "12517b8f-b307-4223-99ed-8ba78794f29b" }, "S15sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S15sh1.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: The outdoor communal eating circle around a large iron pot at the lakeside camp, lit by red campfires after dark.\n\nSHOT TEXT (authoritative, Korean): 붉은 모닥불이 타오르는 어두운 호숫가 옆, 무쇠솥을 둥글게 둘러싸고 앉은 조선인 의병들의 왁자지껄한 전경.\n\nCARRIED STATE (persist exactly): Campfires light the dark lakeshore; the iron pot now boils broth containing two chickens and potatoes rather than porridge.\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 with a stationary high-oblique view from outside the seated circle, looking diagonally down across the pot toward the lakeside before the crane descends. The pot sits below center at less than a fifth of the frame, with 안규홍, 이관회, 염재보 and the other Korean resistance fighters distributed around it, absorbed in their food: some lean toward their portions while others straighten between bites, with unequal elbow angles and naturally varied spacing. Keep the lake across the upper background and the fires beside the gathering; let illumination, rather than a new character arrangement, announce the change from the preceding daytime scene.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 큰 무쇠솥 (Chicken and potato broth is boiling inside) — The open top and near side are visible from the elevated camera; used as Organizes the seated circle without becoming oversized; 모닥불 (Firewood is burning beside the gathering); used as Provides visible points of activity around the circle; 호수 (Visible beyond the lakeside gathering); used as Leaves a broad environmental margin above the clustered diners.\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": "aa28beca-dd5c-4a15-a739-4a4397077ace" }, "S15sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S15sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S16sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S16sh4.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The dirt yard immediately outside a rural home's storehouse entrance, where a seed-grain sack has been dragged out.\n\nSHOT TEXT (authoritative, Korean): 흙바닥에 주저앉은 채 씨나락 자루를 양팔로 필사적으로 끌어안고 오열하는 조선인 노파의 애처로운 웅크림.\n\nCARRIED STATE (persist exactly): A small, tightly tied seed-rice sack has been dragged out of the storehouse onto the dirt yard. 조선인 노파(씨나락 주인): She sits on the dirt clutching the tied seed-rice sack.\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 restrained dolly from the stage's three-quarter side position, looking downward at 조선인 노파(씨나락 주인) without yet following her later displacement. Her folded torso occupies the left-center and both arms close around the small, tightly tied sack at lower right, which takes less than a quarter of the frame; her lowered face remains directed toward the grain she is trying to protect. Keep the dirt ground and a partial granary entrance visible around her, using the approach in distance—not a lighting or gaze change—to intensify her desperate grip.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 씨나락 자루 (Small, tightly tied, and held with both arms by the elderly woman) — Its side and tied upper portion are visible beneath her embrace; used as Connects her curled body to the threatened seed grain while retaining realistic scale; 흙바닥 (The woman is seated directly on it); used as Surrounds the body with unprotected ground; 광 입구 (The seed-grain sack has been dragged out from inside) — A partial oblique view of the entrance remains behind the woman; used as Locates the seizure without introducing additional action into the frame.\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:조선인 노파(씨나락 주인)", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/718d534d-07e6-4a7d-867b-e752b603bb50.png" ] ], "asset_id": "480fe76d-33b7-4385-8934-4a59175b9569" }, "S16sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S16sh16": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S17sh8": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S17sh8.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The open assembly ground beside the lake in a temporary camp, ringed by onlookers under slanting afternoon sunlight.\n\nSHOT TEXT (authoritative, Korean): 안규홍의 코앞까지 성큼 바짝 다가선 강용언의 위협적인 상체.\n\nCARRIED STATE (persist exactly): Two tied seed-rice sacks lie in the camp clearing under slanting red afternoon light. 안규홍: He stands with the blood wiped from his head wound, wearing a carrying frame and concealing the jade ring. 강용언: He stands close in confrontation, with his sword still at his waist.\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 beside 안규홍, below the men's eye line and tilted slightly upward toward 강용언 in three-quarter view, never substituting 안규홍's literal eyesight. 강용언's upper body occupies the center-right as his weight arrives over the forward foot, his attention fixed on 안규홍's face beyond the narrow head-and-shoulder fragment at the left foreground; 안규홍 holds his ground and attends to him. Settle before the next lateral travel, making the collapse of interpersonal space the single emphasized change.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 호수 (Gray beyond the lakeside clearing); used as A narrow, soft background interval preserves the established lakeside location.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:강용언", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/c56aa30c-86d4-404a-a106-39f9dd28d9ec.png" ] ], "asset_id": "1fe19e6c-d8b6-47dc-859d-698afc7389dc" }, "S17sh18": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S17sh21": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S18sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S18sh1.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: The gravel eating area around an empty iron pot in the outdoor lakeside camp, with two untouched seed-grain sacks nearby.\n\nSHOT TEXT (authoritative, Korean): 빈 무쇠솥 주변 자갈밭에 축 늘어져 웅크린 조선인 의병들의 퀭한 전신.\n\nCARRIED STATE (persist exactly): The iron pot is empty; two untouched, tightly tied seed-rice sacks remain beside it in the red evening light.\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 opening crane position at the clearing's outer edge, looking obliquely down in a wide, direct observational view that retains the exhausted Korean militia members from head to foot. Arrange their depleted bodies unevenly across the lower and middle frame around the small empty pot: one curls over his knees, another sags sideways, and another sits with his legs extended, their lowered attention remaining on the ground and empty cooking space rather than the lens. Keep the two untouched, tied seed-grain sacks together beside the group, establishing the spatial arrangement before the camera begins its descent toward the grove.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 빈 무쇠솥 (Empty, with exhausted militia members gathered around it) — The oblique elevated view exposes the empty interior; used as A modest central reference that makes the men's hunger legible without overpowering their bodies; 씨나락 자루 두 개 (Both tied and untouched beside the group) — Both sacks and their tied closures remain visible beside the men; used as A secondary visual counterpoint to the empty pot; 자갈밭 (Beneath the resting men and cooking area); used as Connects the separate resting poses within a continuous ground 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, "no_plate": true, "ref_paths": [], "asset_id": "0ead871c-d53e-42a7-a406-a8613400bae4" }, "S18sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S18sh4.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The narrow bamboo approach opening into the temporary lakeside camp in reddish late-afternoon light.\n\nSHOT TEXT (authoritative, Korean): 빽빽한 대나무 숲길 사이로 무거운 짐을 진 안규홍과 이관회가 한쪽 발을 앞으로 내디딘 미드액션 전신.\n\nCARRIED STATE (persist exactly): The empty pot and two unopened seed-rice sacks remain on the gravel in red late-afternoon light. 안규홍: He enters with a loaded carrying frame, dirt-covered hands and the jade ring concealed in his clothing. 이관회: He arrives sweaty and tired from building a wall and chopping wood.\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 clearing side of the bamboo entrance, hold a below-eye-level, oblique wide view beside the men's route, capturing the start of the accompanying track without entering their frontal axis. 안규홍 occupies the center-left and 이관회 the center-right, both visible from their loads to their feet as they advance diagonally into the clearing; 안규홍 plants his forward foot while 이관회 is still transferring weight, their attention directed along the route toward the off-screen cooking area. Emphasize their changing position within the established space, keeping the loads at believable scale and leaving room ahead of their steps.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 대나무 숲길 입구 (The men are emerging through the dense bamboo into the clearing) — The entrance recedes obliquely behind the men; used as Frames the arrival along the sides without concealing either man's feet or load; 지게와 운반 중인 식량 짐 (Carried toward the cooking area before unloading) — The carrying frames and loads are seen obliquely behind the men's shoulders; used as Makes the burden visible while retaining the carriers as the primary subjects.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:이관회", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/69254565-1c94-4962-a073-922e40cca9e8.png" ] ], "asset_id": "7f934b4a-3c6a-4635-bdbb-61ec165cbeb3" }, "S18sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S19sh17": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S19sh17.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The dirt space beside the communal campfire in the lakeside camp, where a wooden carrying frame lies within the fighting area.\n\nSHOT TEXT (authoritative, Korean): 안규홍의 굵은 주먹이 강용언의 턱을 무자비하게 강타한 찰나.\n\nCARRIED STATE (persist exactly): A sword strike has damaged the carrying frame beside the campfire; the two seed-rice sacks remain unopened. 안규홍: His lip is freshly split and bleeding; the jade ring remains concealed in his clothing. 강용언: He is unsteady and red-eyed from drink, still in the armed struggle.\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 close-observation stage's endpoint, remain just below the men's eye line on the established three-quarter side, looking slightly upward in a direct handheld close two-shot. 안규홍's split-lipped face and driving shoulder occupy the left side while his fist meets 강용언's unobstructed chin at center-right; 안규홍 looks down along the striking line toward the chin, and 강용언's eyes are displaced off-screen by the recoil. Briefly arrest lateral drift at contact, preserving the established light and screen positions while the fist's arrival supplies the sole emphatic positional change before the downward follow.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 임시거점 공터 (The confrontation remains within the camp clearing); used as A narrow, unfocused spatial margin keeps the bodily impact grounded in the existing location.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:강용언", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/c56aa30c-86d4-404a-a106-39f9dd28d9ec.png" ] ], "asset_id": "5aac126f-7b05-4f78-b00f-cfa59765f394" }, "S19sh25": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S19sh31": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S20sh2": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S20sh6": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S20sh6.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L09B02.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: Inside the traditional estate's dim guest-wing meeting room at night, in the floor-seating area with no drinking table.\n\nSHOT TEXT (authoritative, Korean): 박제현과 시선을 마주한 채 눈빛이 파르르 흔들리는 순간의 박상현의 얼굴 클로즈업.\n\nCARRIED STATE (persist exactly): The red seizure seal remains on the grain-store door; no drinking table is set, and the frame's usual yard corner is empty. 박상현: He remains seated, his expression losing its composure.\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 inward beside 박제현's shoulder at 박상현's seated eye height, maintaining the established slight three-quarter view rather than moving onto their eyeline. 박상현's face occupies the center-right while a narrow, soft edge of 박제현's shoulder and rear head anchors the left foreground; 박상현's wavering eyes remain fixed on 박제현's face just outside the crop, and 박제현 holds his attention on his brother. Let the reduced distance reveal the failure of 박상현's composure while preserving the existing body arrangement and dim exposure, then hold before the camera withdraws toward the yard.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 사랑채 실내 (The seated conversation continues without the customary drinking table); used as A minimal, defocused interior margin keeps the reaction in the shared room 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, "ref_paths": [ [ "plate", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L09B02.png" ], [ "char:박상현", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/4db16aea-d0e1-45c2-acc8-6e8efbda159d.png" ] ], "asset_id": "278fc18d-344d-447a-8a88-b10740614a49" }, "S20sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S21sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S21sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L18B03.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The open floor inside an isolated hillside barn, dim despite the daytime outside.\n\nSHOT TEXT (authoritative, Korean): 어두운 헛간 바닥에 지친 기색으로 널브러진 안규홍, 이관회, 염재보, 복만과 세 명의 조선인 남성들의 전경.\n\nCARRIED STATE (persist exactly): The isolated barn is dim. 안규홍: He sprawls exhausted with one eye badly swollen and his lip split; the jade ring remains concealed in his clothing. 이관회: He sprawls exhausted on the barn floor. 염재보: He sprawls exhausted on the barn floor. 복만: He sprawls exhausted in his worn durumagi, retaining his matchlock.\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 opening static view from high inside the barn, looking diagonally down across all seven exhausted men with the doorway at the right edge, before 달래 enters. Place 안규홍 near center-left with his swollen eye and split lip visible obliquely, 이관회 and 염재보 at differing depths across the center, 복만 toward the rear-left, and the three other Korean men irregularly across the remaining floor; vary bent knees, supporting elbows, and torso angles without making their exhaustion a repeated pose. Keep their attention lowered toward the floor immediately around them, preserving full-body visibility and an unobstructed spatial route for the later approach rather than drawing their eyes toward an arrival that has not happened yet.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 헛간 바닥 (Occupied by seven exhausted men resting in irregular positions); used as A continuous ground plane reveals different resting postures and unequal intervals between bodies; 헛간 문 (Not yet opened for 달래's entrance) — Seen from inside at an oblique angle along the right edge; used as Establishes the entrance for the subsequent movement without prematurely showing 달래.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L18B03.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:이관회", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/69254565-1c94-4962-a073-922e40cca9e8.png" ] ], "asset_id": "f7c5032e-6432-4695-86f3-7827a0cdf745" }, "S21sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S21sh16": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S22sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S22sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L20B01.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 private home's grain storehouse at night, with pine-torch light falling over stored sacks and valuables.\n\nSHOT TEXT (authoritative, Korean): 활짝 열린 곳간 문 안으로 성큼 발을 내디딘 복면 쓴 안규홍의 전신.\n\nCARRIED STATE (persist exactly): A broken iron padlock lies on the floor; pine-resin light reveals rice bales, seed sacks, silver hairpins and brass bowls, including sacks marked '최 서방 종자' and '이 씨 볍씨'. 안규홍: He enters masked, with the swollen eye, split lip and concealed jade ring retained.\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 inside the storehouse, below eye level and diagonally beside the entry path, holding a direct observational full-body view before the backward track develops. Place masked 안규홍 in the central midground as he takes a long step through the fully open doorway, his body angled into the room and his attention directed toward the stored sacks beyond the frame. Keep 이관회, 염재보, and 복만 behind him within the doorway at unequal depths and different stride phases, leaving the camera-side path open for the retreat.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Open storehouse doorway behind the entering group in the upper-left of the frame, background.\n- KEY BACKGROUND ELEMENTS: Storehouse doorway (Fully open during the group's entry) — Seen obliquely from inside, with the entry passage visible behind 안규홍; used as Background threshold establishing movement from outside into the storehouse; Rice bales and seed sacks (Piled inside the storehouse) — Partial sides of the piles appear beside the entry path; used as Side framing and scale references without blocking the full-body action.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.", "skipped_reason": null, "error": null, "ref_paths": [ [ "plate", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L20B01.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "44af9002-9e8c-42e1-a3a9-c56745c9477f" }, "S22sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S22sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S23sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S23sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_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: A dark outdoor dirt alley between thatched village homes.\n\nSHOT TEXT (authoritative, Korean): 어두운 초가집 골목, 무거운 자루를 멘 채 은밀한 자세로 걸음을 내딛어 한쪽 발이 허공에 뜬 복면 쓴 안규홍, 이관회, 염재보, 복만의 전경.\n\nCARRIED STATE (persist exactly): The thatched-house lane is dark. 안규홍: He walks masked with a seed-rice sack shouldered, retaining his facial injuries and concealed jade ring. 이관회: He walks masked with a travel bundle. 염재보: He walks masked carrying a rice sack and retaining his gun. 복만: He walks masked, retaining his matchlock.\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: Establish the following path from behind and to one side at approximately head height, looking diagonally along the alley in a direct observational wide view. Arrange masked 안규홍 ahead near the upper center, with 이관회, 염재보, and 복만 staggered toward the lower-right midground, their full bodies and carried sacks readable against the alley's depth. All attend to the route ahead, but their quiet strides are asynchronous: 안규홍's advancing foot hangs briefly above the ground, another man transfers weight, and the others carry their loads with different shoulder angles.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Alley continuation ahead of the group in the upper-center of the frame, background.\n- KEY BACKGROUND ELEMENTS: Thatched-house alley (The group is moving quietly through it) — The alley recedes diagonally from the lower right toward the upper center; used as Defines the shared direction of travel and the rear-oblique tracking route; Carried sacks (Borne by the masked group) — Seen mainly from behind and from the camera-side edges; used as Distinct load shapes reinforce individual silhouettes without obscuring the walkers.\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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:이관회", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/69254565-1c94-4962-a073-922e40cca9e8.png" ] ], "asset_id": "37dd0a26-f584-4c3d-b385-c565ed3d6c52" }, "S23sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S23sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S24sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S24sh2.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The raised wooden dining platform beside a corner seat in a busy daytime market soup eatery; enclosure is not specified.\n\nSHOT TEXT (authoritative, Korean): 나무 평상에 앉아 탁주잔을 공중으로 쨍 부딪치는 대장장이와 백정의 즐거운 상체.\n\nCARRIED STATE (persist exactly): White steam rises from the soup cauldron in the crowded daytime restaurant; rice-soup bowls and rice-wine cups are set out. 대장장이: He sits on the side platform holding a rice-wine cup. 백정: He sits on the side platform holding a rice-wine cup.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At seated face height, enter the lateral route beside the platform without crossing the men's mutual facing axis, observing their upper bodies directly from an oblique angle. Place 대장장이 on the left leaning into his raised cup and 백정 on the right lifting his cup from a slightly more settled seat, the rims meeting near the center below their faces. Both look down toward the cup contact rather than toward the lens; keep lateral movement slight and their elbows at different heights so the shared pleasure does not become a mirrored pose.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: Wooden seating platform (Occupied by the two men within this crop) — The front edge and a portion of the upper seating surface are visible beneath them; used as Shared physical anchor for the oblique seated two-shot; Takju cups (Raised with their rims touching) — Seen from the side with both rims visible between the men; used as Small central action point linked to two distinct arm gestures.\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:대장장이", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/928f3f98-0c2d-4018-81e4-affb931a7cb3.png" ], [ "char:백정", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a302b0bd-7ebf-4bf6-ba26-063943f87df3.png" ] ], "asset_id": "7acb567e-8915-4455-aca7-3659da9414bb" }, "S24sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S25sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S25sh3.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L22B03.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The visitor's standing space opposite a tidy desk inside a police outpost office at night, with enough light for ledger work.\n\nSHOT TEXT (authoritative, Korean): 책상 맞은편에 두 손을 모은 채 뻣뻣하게 서서 책상 쪽을 내려다보는 배상도의 상체.\n\nCARRIED STATE (persist exactly): Tax ledgers, an abacus and red seal paste are arranged on the neat desk at night. 배상도: He stands on the opposite side of the 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: Settle the crane above the established lateral desk edge, slightly above 배상도's eyes, looking gently downward at his upper body in three-quarter view. Place him just right of center with his joined hands inside the lower frame and a narrow strip of the tidy desktop in the foreground; his rigid shoulders and lowered gaze toward the desk convey the strain of making his report. Finish the rise without reframing his hands, retaining the same side of the dialogue axis for the subsequent approach to 토미이시.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 책상 (Tidy, separating 배상도 from 토미이시) — The lateral edge runs obliquely across the lower foreground; used as A restrained foreground boundary makes his joined hands and subordinate position 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, "ref_paths": [ [ "plate", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L22B03.png" ], [ "char:배상도", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/28ee8d7a-14df-4721-bcd8-4af5cab5662a.png" ] ], "asset_id": "85e61bf4-394e-42e3-a697-240357916b83" }, "S25sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S25sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S26sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S26sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_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: The newcomers' side of an open mountain-camp clearing, opposite the established members in daylight.\n\nSHOT TEXT (authoritative, Korean): 공터 맞은편, 낡은 봇짐과 농기구를 손에 쥔 채 주뼛거리며 서 있는 대여섯 명의 새로 온 조선인 남성들 전경.\n\nCARRIED STATE (persist exactly): Daylight fills the mountain-camp clearing. 오주일: He stands among the newcomers in rough clothes with the removal mark on his worn collar. 임정현: He stands at the very back of the newcomers. 대장장이: He stands among the newcomers with visibly callused hands. 목수: He stands among the newcomers. 백정: He stands among the newcomers with tense shoulders.\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 with the crane held at the clearing's elevated lateral edge, looking diagonally downward across the empty gap toward five newly arrived Korean men, with their full bodies grouped across the middle and right of frame. 대장장이, 목수 and 백정 occupy the nearer part of the group while 오주일 and 임정현 remain behind; their attention stays on the established men beyond the left frame edge, with unequal weight distribution, differently angled shoulders and naturally uneven spacing rather than a posed line. Keep their bundles and worn farming tools readable beside their bodies, leaving the lower-left clearing open for the later descent and approach.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 산채 공터 (An open gap separates the newcomers from the established men); used as The unoccupied lower-left area makes the awkward social distance visible; 봇짐 (Held by the newly arrived men); used as Small, separately positioned belongings distinguish the arrivals without creating repeated silhouettes; 낡은 농기구 (Worn farming tools carried by the newcomers) — The tools follow different natural carrying angles beside their holders; used as Readable within the full-body composition as evidence of the men's civilian lives.\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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png" ], [ "char:오주일", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/31c9e7b0-be1d-40c4-934d-85ba6ad649bf.png" ], [ "char:임정현", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/451b6f0a-c1b4-4b5d-9fbd-fbb3c744bf3f.png" ] ], "asset_id": "829edf95-8348-46f0-9c37-4fcfa7339808" }, "S26sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S26sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S27sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S27sh21": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S27sh21.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The outdoor serving area beside the mountain camp's large cooking pot after training.\n\nSHOT TEXT (authoritative, Korean): 자신의 토기 사발에 담긴 멀건 국물 같은 죽을 허탈하게 내려다보는 백정의 퀭한 시선.\n\nCARRIED STATE (persist exactly): The cauldron lid is open, exposing watery porridge; serving bowls are filled with the same thin food. 백정: He holds his bowl and looks down into the watery porridge.\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 meal-stage camera at the gathering's outer edge, slightly above 백정's eyes and looking down from his three-quarter left side. His lowered face occupies the upper center, with his hands and earthenware bowl below it; keep the bowl within the lower fifth so his exhausted gaze and the thin porridge remain readable together at natural scale. His shoulders fold subtly toward the bowl as he examines its contents, with no other diners entering this narrow composition and no movement until the subsequent retreat begins.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 토기 사발 (Held below 백정's face and containing thin porridge) — Its open interior tilts into the camera's downward view; used as A small lower-frame counterpoint to his eyes makes the cause of his disappointment visible; 멀건 죽 (Watery porridge inside the bowl); used as The visible contents ground his reaction in the inadequate meal.\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:백정", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a302b0bd-7ebf-4bf6-ba26-063943f87df3.png" ] ], "asset_id": "6b43ab3c-f77b-46d3-9765-83ffa19fa20f" }, "S27sh26": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S28sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S28sh18": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S28sh21": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S29sh2": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S29sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S29sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S30sh21": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S30sh38": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S30sh50": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S31sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S31sh1.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The sandy refuge immediately behind large coastal rocks, beside rough breaking surf.\n\nSHOT TEXT (authoritative, Korean): 거친 파도가 치는 해안가 거대한 바위 뒤로 한쪽 발을 딛고 뒷발로 모래를 차올리며 달려 들어오는 미드 액션, 앞을 향해 상체를 기울인 안규홍, 이관회, 염재보, 의병 포로1, 의병 포로2, 의병 포로3의 역동적인 전경.\n\nCARRIED STATE (persist exactly): Rough surf breaks beside the coastal rocks and sand. 안규홍: He arrives without his carrying frame, with split, bleeding knuckles and the jade ring concealed. 이관회: He arrives breathless, retaining the sickle used in the rescue. 염재보: He arrives carrying a rescued prisoner piggyback, with his matchlock retained. 의병 포로1: He is freed from his binding rope and arrives exhausted. 의병 포로2: He is freed from his binding rope and arrives exhausted. 의병 포로3: He cannot walk unaided and arrives being carried.\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 tracking stage from the low lateral three-quarter position beside the route behind the rocks, looking slightly upward across the group's left-to-right arrival with full bodies visible. 안규홍 leads near center-right, 이관회 and the first two prisoners follow at differing stride phases, and 염재보 arrives to the left carrying 의병 포로3, preserving the preceding scene's inability to walk rather than making all six run independently. Their attention stays on the shelter ahead beyond the right edge; planted feet and trailing feet disturb the sand asynchronously, while the sheltering rock remains a peripheral mass smaller than two fifths of the image.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Sheltered arrival space behind the coastal rock in the middle-right of the frame, midground.\n- KEY BACKGROUND ELEMENTS: 해안 바위 (Sheltering the arriving group) — The shelter-facing side appears at the right edge, with the arrival route visible beside it; used as Defines the destination without hiding the runners or overwhelming their scale; 모래 바닥 (Disturbed beneath the arriving feet); used as Separates planted and airborne feet and makes the staggered stride phases readable; 해안 파도 (Breaking behind the rocks); used as A limited background opening establishes the coast without competing with the arrival.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:이관회", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/69254565-1c94-4962-a073-922e40cca9e8.png" ] ], "asset_id": "34d329c4-6159-44b7-bf3f-98f6943cb851" }, "S31sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S31sh17": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S32sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S32sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S32sh22": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S33sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S33sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S33sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S34sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S34sh16": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S34sh24": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S35sh8": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S35sh8.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_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: The outdoor edge of a village lane lined with opening household gates, where supplies are passed toward a cart at night.\n\nSHOT TEXT (authoritative, Korean): 어둠 속 열린 문틈들 사이로 짚신과 옥수수를 쥔 채 문밖을 향해 불쑥 뻗어 나와 정지된 여러 조선인 손들의 겹친 모습.\n\nCARRIED STATE (persist exactly): The cart holds the donated rice bales plus a barley sack and potato basket; village gates are opening as straw shoes and corn are added.\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 doorway side of the cart's route, track at the height of the extended hands, looking obliquely along successive open entrances rather than into the houses. Nearer hands enter from the right edge while farther hands overlap toward the upper left, offering straw shoes and corn toward the cart outside the frame; vary wrist angles, grips, and extension so the gestures remain individual. Settle on this layered endpoint without crossing the travel axis, excluding faces and keeping each offering smaller than the surrounding human-and-doorway context.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Successive village doorways (Open as offerings are extended outside) — Seen obliquely along their exterior edges, with interiors largely excluded; used as Create successive narrow frames and depth separations around the hands; Straw shoes and corn (Held out in several villagers' hands) — Presented at differing angles along the line of extended arms; used as Provide distinct offering details without allowing any single object to exceed a small portion of the frame.\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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png" ] ], "asset_id": "55aaf43a-c73c-4965-89dd-f589f5a02422" }, "S35sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S35sh13": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S35sh13.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_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: The dark end of a village alley, with a view toward the departing cart and the estate's closing main gate.\n\nSHOT TEXT (authoritative, Korean): 골목 끝 어둠 속, 저만치 떨어진 수레를 향해 시선을 고정한 채 뚫어져라 응시하는 박진성과 박상현의 굳은 전신.\n\nCARRIED STATE (persist exactly): The cart retains its enlarged load of grain, potatoes, straw shoes and corn; the house's main gate is closing. 박진성: He stands at the dark lane end. 박상현: He stands at the lane end looking toward the closing gate.\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: Make the prescribed spatial cut to the alley end and hold a stationary, near-eye-level wide view diagonally behind 박진성 and 박상현, retaining both figures head to foot. Place 박진성 at the left and 박상현 just right of him, with the small departing cart in the upper-right distance along their shared sightline; its load conceals the pullers from this angle. Their fixed attention belongs to the cart, not the lens: 박진성 holds his neck slightly forward while 박상현 sets his shoulders, and the camera waits before the later pan toward the gate.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Distant departing cart beyond the observers in the upper-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: Alley end (Occupied by the two observers) — Opens onto the departing cart's route beyond their shoulders; used as Establish their separate observation position without reversing the departure direction; Distant loaded cart (Moving away with the accumulated provisions) — Rear load visible beyond the observers; the men pulling it are occluded; used as Supply the small, distant endpoint of both men's 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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png" ], [ "char:박진성", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/71306446-e143-4186-97b6-d91271898082.png" ], [ "char:박상현", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/4db16aea-d0e1-45c2-acc8-6e8efbda159d.png" ] ], "asset_id": "d29e1c04-90d1-4ba7-a4b5-8d8c01f4b6de" }, "S36sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S36sh1.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The lower stretch of the uphill forest approach to the mountain camp, where a loaded cart is being hauled upward at night.\n\nSHOT TEXT (authoritative, Korean): 산길 아래, 무거운 수레 끈을 어깨에 걸고 한 발을 내디딘 mid-stride 자세의 안규홍, 이관회, 염재보의 땀 맺힌 전신.\n\nCARRIED STATE (persist exactly): The cart arrives loaded with rice bales, barley, potatoes, straw shoes and corn on the dark mountain approach. 안규홍: He strains uphill with the loaded cart, retaining his sword and concealed jade ring. 이관회: He strains uphill with the loaded cart. 염재보: He strains uphill with the loaded cart and retains his gun.\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: Establish the uphill-side tracking position at a low torso height, offset toward the approaching men's front flank, with a gentle upward tilt and all three visible head to foot. Hold the entry composition before retreating: 안규홍 occupies center-left, 이관회 the left edge and 염재보 center-right, while the loaded cart follows in the right background and occupies less than a third of the image. Their attention stays on the uphill path outside the frame as shoulder-borne ropes draw tight, with different footfalls and degrees of forward lean expressing the same heavy ascent rather than synchronized marching.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Uphill mountain path (Being climbed by the three men pulling the cart) — Runs from behind the cart toward the camera's uphill position; used as Make the incline readable beneath the full-body action; Loaded cart (Piled with rice sacks, barley, potatoes and straw shoes) — Near side and forward end visible behind the men; used as Provide a proportional background measure of the burden; Cart ropes (Across the men's shoulders during the uphill pull) — Extend backward from the men's shoulders to the cart; used as Visually transmit the load through each man's posture.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:이관회", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/69254565-1c94-4962-a073-922e40cca9e8.png" ] ], "asset_id": "dd27a023-9a40-4cbd-8596-a4c9b0d59e93" }, "S36sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S36sh17": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S37sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S37sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_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: Directly before an outdoor market wall bearing a posted bounty notice, beside the passing daytime crowd.\n\nSHOT TEXT (authoritative, Korean): 소금과 약재 꾸러미를 손에 쥔 채 벽보를 멍하니 올려다보는 복만의 뒷모습.\n\nCARRIED STATE (persist exactly): A wanted notice on the market wall bears the name '안규홍', a bounty amount and a conspicuous red official seal. 복만: He stands carrying purchased salt and medicinal herbs, in his worn durumagi.\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 rear approach behind and slightly right of 복만 at a low torso height, tilting gently upward while retaining his back, lowered hands and both purchased bundles in a medium composition. Place him lower-right and the notice upper-left, leaving enough separation from the wall for a comfortable upward look at 안규홍's name rather than a sharply bent neck. The wall and his body bound the shot so the other onlookers stay outside it; pause here before the prescribed curve around his right side.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: Written face of the reward notice above and ahead of 복만 in the upper-left of the frame, background.\n- KEY BACKGROUND ELEMENTS: Reward notice (Posted on the wall with 안규홍's name, a reward amount and a red official seal) — The written face is visible obliquely to the camera, including the name and the seal beneath it; used as Occupy less than a third of the upper-left image as the endpoint of 복만's upward attention; Market wall (Bearing the notice) — Seen obliquely beyond 복만's back; used as Form a simple background that separates the notice from his silhouette; Salt and medicinal ingredient bundles (Purchased and held in 복만's hands); used as Keep the ordinary errand visible at the lower edge beneath his arrested 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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png" ], [ "char:복만", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/aa6b9475-1e62-48e3-8a8b-25bd2e70202a.png" ] ], "asset_id": "e51f1080-c121-43ef-bdb2-c111ecfb3183" }, "S37sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S37sh17": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S38sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S38sh3.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The entrance edge of the mountain camp's dirt meeting clearing, crossed by red sunset light through the palisade.\n\nSHOT TEXT (authoritative, Korean): 이마에 땀방울이 맺힌 채 한쪽 발을 공터 흙바닥에 막 디딘 복만의 역동적인 찰나.\n\nCARRIED STATE (persist exactly): Long red sunset light falls through the camp palisade. 복만: He arrives breathless with sweat on his forehead, retaining the purchased salt and herbs.\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 lateral track's endpoint at the outside of the seated circle, keeping the camera low at torso height and oblique to 복만's approach, with his forehead and planting foot both inside the wide frame. Place 복만 center-right with space to the left toward 안규홍 and the seated listeners just outside the image, and catch his weight landing on the forward foot while his chest remains pitched from the hurried climb. His attention is fixed on 안규홍 off-screen; retain the same side of their axis and let the footfall, not an additional camera move, finish the arrival.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Clearing's earth ground (복만's forward foot has just made contact); used as Leave clear space beneath the whole figure so the arrival's weight transfer reads in one frame; Camp palisade (Present around the camp with gaps between its uprights) — Seen across the background beyond 복만; used as Provide the camp boundary behind the arrival without crowding the listener-facing 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, "no_plate": true, "ref_paths": [ [ "char:복만", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/aa6b9475-1e62-48e3-8a8b-25bd2e70202a.png" ] ], "asset_id": "925c2002-e6b7-484f-b9c1-767408a0c3fb" }, "S38sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S38sh17": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S39sh14": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S39sh14.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: The wooded ridges on both sides of a mountain-pass cart track, overlooking the exposed ambush site.\n\nSHOT TEXT (authoritative, Korean): 나무 틈새로 일제히 모습을 드러낸 채 총을 겨누고 선 수많은 일본인 군인들의 전신.\n\nCARRIED STATE (persist exactly): The bait supply cart is stopped on the mountain path; gunfire comes from both wooded ridges.\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 ridge-reveal pan from a low position at the path's edge, looking obliquely uphill through the trees and remaining clearly offset from the soldiers' firing axes. Distribute the Japanese soldiers' full figures across the middle and upper frame, their rifles and attention directed downhill toward the militia outside the lower side of the image. Their collective emergence remains simultaneous, but vary planted feet, bent knees, shoulder heights, and partial tree occlusion so the ambush reads as coordinated people rather than identical copies.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 능선의 나무 (Japanese soldiers have appeared in the gaps between them) — Trunks cross the oblique uphill view at different depths; used as Divide the force into irregular visible intervals while preserving full-body readings through selected gaps; 산길과 능선 (The soldiers occupy the higher ground above the path) — The path edge lies low in the image and the slope recedes upward; used as Establishes the attackers' height advantage without adopting a combatant's subjective viewpoint; 일본군의 총 (Raised and aimed toward the militia below) — Seen from the side at oblique angles, with barrels directed away from the camera's axis; used as Connects the dispersed figures through a common downhill threat direction.\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": "464a7862-b636-4a03-82eb-b0aabb506b77" }, "S39sh18": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S39sh18.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The exposed mountain track beside the seized supply cart, between the wooded slopes firing down on it.\n\nSHOT TEXT (authoritative, Korean): 대장장이의 등 한가운데 찢겨진 옷감 사이로 붉은 피가 확 번져나가는 찰나.\n\nCARRIED STATE (persist exactly): The supply cart remains abandoned under fire on the wooded path. 대장장이: He has just been shot in the back, with blood spreading through his 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: At the closest point of the inherited track, hold the lens level with 대장장이's middle back and look across it from the established rear three-quarter axis, tightening distance without rotating around him. His arrested forward lean and back occupy most of the image, with blood spreading through the torn clothing at center and a narrow margin of the forest retained for context. Keep his head and the wounded man outside the crop; the shoulder and upper-arm line still carries his interrupted effort to push the man forward.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 숲의 나무 (Partially visible beyond the wounded figure) — Only narrow, oblique background portions remain visible; used as Provides a soft spatial reference around the bodily detail without distracting from the interrupted rescue.\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:대장장이", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/928f3f98-0c2d-4018-81e4-affb931a7cb3.png" ] ], "asset_id": "674fc9be-f179-475f-aebc-486d89cffdc6" }, "S39sh25": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S40sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S40sh4.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/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: The outdoor courtyard of a traditional estate, between the opened main gate and the guest wing in daylight.\n\nSHOT TEXT (authoritative, Korean): 박제현을 향해 턱을 치켜들고 거만한 눈빛으로 내려다보는 배상도의 측면.\n\nCARRIED STATE (persist exactly): The main gate stands open after being forced wide. 배상도: He stands in the yard with his chin raised.\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 almost to a stop on the confrontation's flank, holding a slightly low near-profile view of 배상도 with 박제현 along his address line. Place 배상도 on the right and 박제현 at the left margin, keeping both upper bodies readable as 배상도 lifts his chin and lets his eyes escape upward rather than meeting 박제현's appeal. 박제현 angles his face up toward him without turning toward the lens; the lifted gaze, not a new distance or lighting effect, carries the change.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 사랑채 (박제현 has just emerged from it) — An oblique portion of its courtyard-facing side remains behind 박제현; used as Anchors his position within his own household during the 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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B01.png" ], [ "char:배상도", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/28ee8d7a-14df-4721-bcd8-4af5cab5662a.png" ] ], "asset_id": "0a7af2d1-5155-4265-b928-6ff03a1c5af0" }, "S40sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S40sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S41sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S41sh1.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: The outdoor gathering circle around a low, dying campfire in the mountain camp at night.\n\nSHOT TEXT (authoritative, Korean): 죽어가는 모닥불 주변에 무거운 표정으로 흩어져 앉은 조선인 의병들 전경.\n\nCARRIED STATE (persist exactly): A low campfire burns beside an unoccupied place marked only by a hammer.\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 from the crane's high, stationary entrance position outside the seated group, looking diagonally down before the planned descent. Arrange the scattered militia around the low-burning fire with differing torso inclinations, head angles, and intervals: 임정현 attends to his writing, 안규홍 watches that work from across the fire, and the others lower their attention toward the ground or fire. Keep the unoccupied place and its small hammer clearly visible to one side of the lower frame, with no one seated beside it and no person posed toward the camera.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Unoccupied place beside the blacksmith's hammer in the lower-right of the frame, midground.\n- KEY BACKGROUND ELEMENTS: 모닥불 (A single fire burning unusually low); used as Serves as a small spatial center around which the seated intervals are readable; 대장장이의 빈 자리와 망치 (The place is unoccupied; his hammer lies there and nobody sits beside it) — The hammer lies obliquely within the empty place, at a modest scale relative to the seated people; used as Creates a visible break in the group that gives the loss a physical location.\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": "ba41a792-d2b2-4f36-98c5-72e5dbd65f1a" }, "S41sh8": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S41sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S42sh4": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S42sh4.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The dim outdoor alley directly along the rear wall of a government compound at night.\n\nSHOT TEXT (authoritative, Korean): 박상현을 향해 시선을 고정한 채 비웃듯 한쪽 입꼬리를 비틀어 올린 배상도의 얼굴.\n\nCARRIED STATE (persist exactly): The alley beneath the government-office wall is dim at night. 배상도: He has stopped in the alley.\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 inward move from just behind 박상현's shoulder on the open-alley side, using an upper-chest-height camera tilted slightly upward toward 배상도. Place 배상도's three-quarter face in the right half and only a narrow, soft portion of 박상현's shoulder at the left edge, keeping the raised mouth corner unobstructed. 배상도 fixes his attention on 박상현's face just beyond that edge, while 박상현 remains pitched toward him with his own face outside the crop.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Government-office boundary wall (Present behind the encounter) — Its alley-facing side recedes obliquely behind 배상도; used as A softly resolved background plane maintains the established side of the conversation.\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:배상도", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/28ee8d7a-14df-4721-bcd8-4af5cab5662a.png" ] ], "asset_id": "adbe5aa6-eb3b-4267-94b9-472eeb2efec2" }, "S42sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S42sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S43sh8": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S43sh8.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The outdoor forecourt just beyond the government compound's main doorway in morning light.\n\nSHOT TEXT (authoritative, Korean): 박제현의 손이 박상현의 어깨 위에 툭 얹어진 순간의 손 클로즈업.\n\nCARRIED STATE (persist exactly): The government-office entrance is open in morning light. 박제현: He is gaunt and unsteady, with a trembling hand extended at shoulder height. 박상현: He stands nearby, avoiding eye contact.\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 beside the brothers just above shoulder height, angling slightly downward across 박상현's near shoulder at the instant 박제현's trembling hand makes contact. Place the hand near center and the receiving shoulder across the lower-right portion, retaining enough of both upper bodies for scale while excluding both faces. 박제현's attention remains on his brother outside the upper crop, while 박상현 keeps his eyes lowered rather than meeting him; the inward camera distance isolates the incomplete reassurance.\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, "no_plate": true, "ref_paths": [ [ "char:박제현", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/f662d945-0d12-48ba-8296-cf6d42dcd1f0.png" ], [ "char:박상현", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/4db16aea-d0e1-45c2-acc8-6e8efbda159d.png" ] ], "asset_id": "58ede9ba-47c8-4b35-8c1a-2368a6f071b4" }, "S43sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S43sh16": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S44sh6": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S44sh6.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L33B02.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The table area inside a dim prison interrogation room at night, with a deep shadowed standing space behind the detainee.\n\nSHOT TEXT (authoritative, Korean): 토미이시의 손에 든 지휘봉 끝이 그림자 속 배상도 쪽을 비스듬히 가리킨 찰나.\n\nCARRIED STATE (persist exactly): A table divides the dim interrogation room; cigarette smoke hangs in the cold darkness. 토미이시: He sits with a cigarette and a command baton 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: From the established side of the table just above its surface, catch the pan as 토미이시's hand directs the baton diagonally from the lower-left toward 배상도 in the upper-right rear. Keep the hand and baton together below a third of the image, with 토미이시's cropped seated torso providing scale and 배상도 visibly farther away along the pointing line. 토미이시 remains engaged with 달래 beyond the near crop, while 배상도 holds his weight still in the rear shadow and looks down toward the seated interrogation outside the lower edge.\n- FRAMING SCALE: medium shot\n- FRAME LAYOUT: Rear position behind the seated pair toward which the baton points in the upper-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: Interrogation table (Between the seated interrogator and prisoner) — Its top and near edge are viewed obliquely at a shallow downward angle; used as The lower edge establishes hand height and connects the near gesture to the room beyond; Command baton (Held by 토미이시 and pointing toward 배상도) — The tip angles from the lower-left foreground toward the upper-right rear; used as A directional bridge rather than an oversized isolated object.\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/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L33B02.png" ], [ "char:토미이시", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/c8296eb1-5a7c-4601-a9e9-81f9fdf60bcb.png" ] ], "asset_id": "a89cc4ee-711d-445b-972e-49369d870a7c" }, "S44sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S44sh17": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S44sh17.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L33B01.png", "prompt": "The FIRST attached image is the LOCATION PHOTOGRAPH (loose spatial reference only). Every following attached image is a CHARACTER REFERENCE for proportion.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nThe attached photograph is the LOCATION where this shot happens.\nUse it ONLY as a LOOSE spatial reference — the rough set masses\nand where things sit relative to each other. You do NOT need to\nfollow it exactly: do not copy its camera, its lighting or its\ndetails. Choose the camera and framing the SHOT TEXT needs, and\ndraw only the few set masses that matter as plain outline shapes.\n\nTHE LOCATION: The top of a large rock beside the mountain camp's forest approach, overlooking a trail covered in dense dawn mist.\n\nSHOT TEXT (authoritative, Korean): 거대한 바위 위에 우뚝 서서 산길 아래쪽을 뚫어져라 내려다보는 안규홍의 굳은 전신.\n\nCARRIED STATE (persist exactly): Dense dawn fog covers the mountain path; a cart approaches through the forest. 안규홍: He stands on a rock waiting, with his half jade ring hanging at his neck.\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 the mountain insert already separated from the interrogation room by a temporal and spatial cut, complete the upward tilt from the path below and beside the rock, holding a low three-quarter side view outside 안규홍's downward sightline. Place his complete figure in the upper-right, neck extended and weight braced as he searches the lower path continuing beyond the lower-left edge, with no glance toward the lens. Retain the rock beneath his feet within the lower-right third and open path space to the left, keeping his figure and the surrounding terrain as scale references rather than exaggerating the foreground rock.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Lower mountain path continuing beyond the frame in the lower-left of the frame, foreground; Rock supporting the waiting figure in the lower-right of the frame, midground.\n- KEY BACKGROUND ELEMENTS: Large rock beneath 안규홍 (Supports his full figure) — Its upper surface and path-facing side are visible from below and to one side; used as An elevated support confined to the lower-right third, establishing his lookout position; Lower mountain path (Extends through the forest beneath the lookout) — Recedes from the lower-left toward the terrain below the rock; used as Provides look room and a plausible downward viewing direction; Forest bordering the path (Present along the mountain route); used as Surrounding terrain gives scale and depth to the isolated waiting figure.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.", "skipped_reason": null, "error": null, "ref_paths": [ [ "plate", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L33B01.png" ], [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "e1be15bd-1561-470f-8e86-af3cd0283875" }, "S45sh5": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S45sh5.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The outdoor mourning place around a straw mat laid in the mountain camp's clearing at night.\n\nSHOT TEXT (authoritative, Korean): 달래의 시신 옆에 무릎을 꿇고 앉아 피 묻은 달래의 손을 들어 올린 안규홍의 상체.\n\nIMMOBILE CHARACTER POSE — CANONICAL (identical wherever this character appears in ANY panel; on any conflict THIS POSE WINS): Her dead body is laid out on a straw mat while An Gyuhong lifts and supports one of her blood- and dirt-stained hands, raising that forearm from the mat. The screenplay does not specify which hand he holds, her face direction, or the arrangement of her other arm and legs.\n\nCARRIED STATE (persist exactly): A straw mat lies laid out in the camp at night. 달래: She lies dead on the mat with blood and dirt on her face, skirt and hands, disheveled hair, and a half jade ring on a finger. 안규홍: He kneels with one hand carefully raised; the other half jade ring hangs at his neck.\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 open side of 달래's body, maintaining the approach's low camera position and oblique view of 안규홍 with a slight downward tilt. Pause the downward reframing as he kneels at frame right and lifts her blood- and earth-marked hand into the lower center, keeping his upper body and her partially visible body together. His lowered gaze rests on her fingers, while the restrained inward movement emphasizes proximity rather than changing their screen positions.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 짚멍석 (달래의 시신이 위에 뉘어져 있다) — Only a narrow portion of its upper surface appears beneath her body; used as Grounds the lower edge without competing with the lifted hand; 달래의 반쪽 옥가락지 (달래의 손가락에 걸려 있다) — Seen obliquely on her supported finger; used as A small narrative detail within the joined-hand area; 안규홍의 반쪽 가락지 (안규홍의 목에 걸려 있다) — Visible against his upper body from the established side angle; used as Quietly establishes the second half without isolating 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, "no_plate": true, "ref_paths": [ [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:달래", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/8a0d2c29-88fb-4d7d-b097-23600d00603e.png" ] ], "asset_id": "f9e33123-9dd2-43a4-8218-3df03202a68f" }, "S45sh20": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S45sh33": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S46sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S46sh3.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The central outdoor assembly circle of the mountain camp, with morning sunlight slanting through cypress trees.\n\nSHOT TEXT (authoritative, Korean): 산채 한가운데 둥글게 둘러앉은 백정, 목수, 염재보, 임정현, 오주일, 복만, 이관회를 훑어보는 안규홍의 정면.\n\nCARRIED STATE (persist exactly): Morning sunlight slants through the cypress trees into the camp. 안규홍: His eyes are swollen, dried dirt remains on his unwashed face, his hair is firmly retied and his neck is bare.\n\nPROPS FACE THE RIGHT WAY (also in this sketch): every handheld or used\nobject must be oriented as its real-world use requires. A person\nreading, watching or operating something (a phone, a photograph, a\npaper, any device) has its functional side — screen, front, page —\nfacing THEIR OWN eyes; the camera then sees whatever side the staging\ngeometry implies (often its back). Show the functional side to the\ncamera ONLY when the shot text itself stages it toward the viewer.\nNever flip, mirror or reverse an object's front and back.\n\nNATURAL PERFORMANCE (default only — every explicit direction above\nwins): when no pose contract or shot-text direction says otherwise,\nsketched figures read as alive in mid-moment — believable weight\nshift, hands engaged, gaze on the target the SHOT TEXT implies; avoid\na stiff attention stance (feet together, arms hanging straight down)\nand a blank stare into the lens. If the SHOT TEXT or any POSE contract\nabove stages stillness, death, sleep, unconsciousness, restraint,\ndrill or an explicit direct-to-camera look, draw THAT exactly — this\nclause never overrides it.\n\nKEYSHOT LAYOUT VALUE: this storyboard frame is a KEY FRAME extracted\nfrom a finished film — its layout alone must convey why this moment\nmatters in the scene. Compose the frame so the subject's pose, gaze\ntarget and spatial relationships read clearly. Do not fill the frame\nwith a single face and do not draw a subject standing square to the\ncamera in a passport-photo composition unless the SHOT TEXT itself\nexplicitly stages that framing for a narrative reason. Even in an\nextreme close-up, keep at least one meaning-bearing element (the gaze\ntarget, the object reacted to, the relevant surroundings) inside or\nat the edge of the frame.\n\nABSOLUTELY NO TEXT anywhere: no captions, no numbers, no labels of any kind.\n\nCAMERA & FRAME (follow exactly — this is the composition authority for this still; the reference images supply identity and place, never the framing):\n- CAMERA: At seated eye height, enter the approach through the space beside 이관회's shoulder, observing 안규홍 directly in an off-axis three-quarter medium view rather than a frontal portrait. Place 안규홍 just right of center with his upper body and empty neck visible, and confine 이관회's rear shoulder to the lower-left edge, leaving the other seated men outside this selected crop. Hold the entry composition as 안규홍 inclines toward the circle and scans listeners beyond frame left, while 이관회 listens with his head slightly lowered toward the ground inside the circle.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 편백 (산채 둘레에 서 있다) — Partial trunks occupy the distant margins behind the seated figure; used as Provides restrained vertical context beyond the intimate shoulder 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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "27ce28a9-6143-468b-9182-2c27d802d80d" }, "S46sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S46sh16": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S47sh3": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S47sh3.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The uphill forest approach immediately below the mountain camp, along the porters' morning arrival route.\n\nSHOT TEXT (authoritative, Korean): 쌀자루와 반찬이 실린 지게를 멘 조선인 짐꾼들과 함께 숲길을 오르는 mid-stride 자세의 박상현의 전신.\n\nCARRIED STATE (persist exactly): Morning light fills the camp approach. 박상현: He walks into the camp from the mountain path.\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 directly beside the uphill path from the arrival stage's elevated oblique position, looking slightly downward and retaining 박상현 and both Korean porters from head to foot. Let their route rise from lower left toward upper right, with 박상현 farther along the path and the porters staggered behind him, each looking toward the uphill route beyond the right edge. Catch 박상현 transferring weight forward while one porter plants a foot and the other lifts a heel; keep the loaded pack frames proportional to their wearers and the supply bottle a minor detail.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: uphill continuation toward the camp in the upper-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: 숲속 산길 (박상현과 짐꾼 둘이 산채 쪽으로 올라오고 있다) — The visible route runs diagonally uphill from lower left to upper right; used as Establishes the direction and effort of the arrival; 짐꾼들의 지게 (쌀자루와 반찬 꾸러미, 술 한 병을 나누어 싣고 있다) — Seen from the side and rear, with the loads visible above and behind the porters' shoulders; used as Explains the visitors' apparent purpose while preserving full-body scale.\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:박상현", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/4db16aea-d0e1-45c2-acc8-6e8efbda159d.png" ] ], "asset_id": "4e1e988e-f16d-4e34-a0ee-4d33e37f1724" }, "S47sh13": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S47sh18": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S48sh10": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S48sh10.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_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: The rear approach alley to the straw-sandal stall in the outdoor market, now blocked across its width.\n\nSHOT TEXT (authoritative, Korean): 다급히 뒤를 돌아본 이관회의 시선 너머로, 뒤쪽 골목을 꽉 채우며 나타난 조선인 일진회원들의 전신.\n\nCARRIED STATE (persist exactly): The familiar daytime market lanes are blocked at both ends.\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 just forward and left of 이관회 at shoulder-to-eye height, observing the rear alley directly past his turned shoulder rather than adopting his literal POV. Confine his shoulder and partial rear profile to the left foreground edge, his attention directed down the alley, and preserve the blocking Korean Iljinhoe members' full bodies and visible feet across the middle and background. Hold the completed reveal before the next spatial cut: their swords remain sheathed at this moment, their arriving steps and shoulder angles differ naturally, and their gazes angle toward the trapped men beyond the near frame edges rather than toward the lens.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: rear alley blocked by the arriving Iljinhoe members in the middle-center of the frame, background.\n- KEY BACKGROUND ELEMENTS: 뒤쪽 골목 (나타난 일진회원들에 의해 통로가 막혔다) — The alley extends away from 이관회's near shoulder into the center of the image, with ground visible beneath the blocking group; used as Makes the loss of the retreat route unambiguous; 일진회원들이 찬 칼 (아직 뽑지 않은 채 몸에 차고 있다) — Visible at differing side angles beside individual bodies; used as Establishes the armed threat without advancing to the later sword-drawing beat.\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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png" ] ], "asset_id": "57a75fcf-991e-4505-a6b3-6fa21b051189" }, "S48sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S48sh23": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S49sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S49sh2.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The damp, leaf-covered floor of the cypress forest below the mountain camp, between closely spaced trunks.\n\nSHOT TEXT (authoritative, Korean): 소총을 가슴 높이로 든 채 빽빽한 편백나무 틈새로 한 발 내딛은 자세의 일본인 군인들의 전신.\n\nCARRIED STATE (persist exactly): Dew wets the fallen leaves beneath the cypress trees. 선두 일본인 군인: He advances with his rifle at chest height at the front of the silent formation. A thin plume of camp smoke rises beyond the trees.\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 lateral track from a low observer position ahead and to one side of the formation, looking gently upward while retaining the Japanese soldiers' full figures between the cypresses. Distribute the two branches through separate gaps across the middle of the frame, rifles held at chest height and attention directed along their respective off-screen approaches. Preserve their silent common advance without synchronized poses: one boot receives weight as another soldier lifts a heel, with small differences in shoulder angle, head direction, and spacing.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Cypress trees (Dense trees separate the emerging soldiers into two visible branches) — Successive trunks overlap at the frame edges and between figures; used as Create layered partial occlusions while leaving enough gaps to read complete bodies; Fallen leaves (Wet with dew beneath the soldiers' boots); used as Keep the lower frame grounded in the careful placement of each step; Soldiers' rifles (Held at chest height during the advance) — Seen obliquely across individual torsos, with slight differences in carrying angle; used as Repeat the armed threat across the formation without enlarging any single weapon.\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:선두 일본인 군인", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/b372d112-53db-456c-873a-1a0ce0e613ee.png" ] ], "asset_id": "c27b30b3-1418-418d-b990-faa3668679a4" }, "S49sh5": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S49sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S50sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S50sh1.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: The outdoor communal eating ground on the mountain camp's dirt clearing, near the cooking area.\n\nSHOT TEXT (authoritative, Korean): 산채 흙바닥에 삼삼오오 둥글게 둘러앉아 사기그릇의 밥을 숟가락으로 뜬 채 입가로 가져가는 낡은 옷차림의 조선인 의병들 전경.\n\nCARRIED STATE (persist exactly): Bowls contain white rice from the delivered provisions; the cooking pot remains upright, and ammunition bundles are hidden beneath stones near trees.\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 crane passage in a settled high oblique observer view outside the seated groups, looking diagonally down across complete figures and the spaces between their small circles. Place the nearest Korean resistance fighters across the lower half, with further groups receding above them; their worn clothing, bowls, and inward-facing bodies establish a shared meal rather than a posed gathering. Keep their attention down toward the rice, catching different phases of the same eating action—spoons lifting, nearing mouths, or lowering—before the descending approach begins.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Camp earth floor (The fighters sit directly on the ground in small circles); used as Visible intervals of ground separate the groups and clarify the gathering's layout; Rice bowls (Ceramic bowls contain rice being eaten) — Their open tops are visible from the oblique elevated angle; used as Provide small repeated centers of attention within the seated circles; Spoons (Held at different stages of bringing rice toward mouths) — Angles vary naturally with each fighter's eating motion; used as Supply asynchronous gestures that make the meal feel lived rather than choreographed.\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": "2d101188-50be-410c-b655-e8647d121794" }, "S50sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S50sh7": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S50sh7.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: The sentry position just outside the mountain camp's eating area, facing downhill into the surrounding forest.\n\nSHOT TEXT (authoritative, Korean): 조금 떨어진 곳, 총을 든 채 숲 아래를 뚫어져라 지켜보는 보초 의병의 꼿꼿한 전신.\n\nCARRIED STATE (persist exactly): The white-rice meal remains laid out, with the pot upright and ammunition bundles concealed at the prepared tree-and-stone positions. 보초 의병: He stands at his post with a gun, watching the forest.\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 track between the meal gathering and 보초 의병, slightly below his eye level and well off his forward-facing axis, keeping his complete figure visible. Place him in the left third in an oblique side view, gun held close and posture erect from sustained vigilance, with open viewing space toward the forest at right. His head and eyes angle naturally toward the lower forest beyond the right edge, making the watch—not an address to the camera—the reason for his stillness.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Forest (Being watched by the sentry from a position apart from the meal gathering) — Visible at the right and continuing beyond the right edge along his viewing direction; used as Provides meaningful look room and the unseen approach that holds his attention; Sentry's gun (Held while he keeps watch) — Seen obliquely alongside his torso without obscuring his face; used as Connects the still full-body pose to active guard duty.\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": "c1e82e04-4ee4-4c86-bc7e-b1b98e10c920" }, "S51sh2": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S51sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S51sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S52sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S52sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_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: An exposed wooded ridge above the mountain camp, offering a clear downhill view into its clearing.\n\nSHOT TEXT (authoritative, Korean): 산채가 내려다보이는 높은 능선 위, 토미이시와 배상도가 나란히 서서 아래를 굽어보는 전신.\n\nCARRIED STATE (persist exactly): A wooded ridge overlooks the camp in daylight. 토미이시: He stands on the ridge looking down, carrying the sword used in the later fight. 배상도: He stands on the ridge.\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 with the crane held high behind and to one side of 토미이시 and 배상도, looking diagonally downward across their full figures toward the camp below. Place 토미이시 left of center and 배상도 beside him to the right, their backs forming a small foreground pair against the downhill view; 토미이시 inclines his head toward the camp while 배상도 leans slightly forward to look down at the same place. Hold this entry composition before descending toward their shared flank, making the broader viewing distance the establishing emphasis.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: Ridge (Overlooks the camp) — Its downhill slope recedes away from the figures; used as Establishes the commanders' elevated position and the direction of the impending advance; Camp below (Visible beneath the ridge) — Seen from above beyond the two figures; used as Provides the shared destination of their downward attention without introducing unsupported architectural details.\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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png" ], [ "char:배상도", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/28ee8d7a-14df-4721-bcd8-4af5cab5662a.png" ], [ "char:토미이시", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/c8296eb1-5a7c-4601-a9e9-81f9fdf60bcb.png" ] ], "asset_id": "0091b78d-fbc2-42ab-a5cc-2957683bf011" }, "S52sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S53sh2": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S53sh6": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S53sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S54sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S54sh7": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S55sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S55sh34": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S55sh40": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S56sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S56sh31": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S56sh31.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_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 the exterior wall of a mountain-camp hut, beside rock cover and the exposed firing lanes across the clearing.\n\nSHOT TEXT (authoritative, Korean): 가슴에 피가 번진 채 두 눈을 부릅뜨고 몸이 뻣뻣하게 굳어버린 임정현의 충격받은 정면.\n\nCARRIED STATE (persist exactly): The cauldron is overturned, rice bowls are shattered and rice is scattered in the dirt; a stone has been lifted to expose a cloth-wrapped ammunition bundle. 임정현: He is against the hut with dirt on his face and a fresh bleeding chest gunshot wound.\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 shelter-side track close to 임정현, slightly above his crouched eye height, maintaining the oblique downward view past him toward the rock gap. Frame his wide eyes and blood-spreading chest together in the central-left area, with a narrow hut edge behind his shoulder and the pointing arm exiting toward frame right. His gaze remains on the other ammunition location beyond that edge, not the lens; the bodily arrest is the sole emphasized change before the camera follows his collapse.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: 산채 움막 (Immediately behind 임정현 as his wounded body stops) — Its rear exterior is seen obliquely beside his shoulder; used as A narrow edge identifies his shelter and anticipates the surface against which he will sink; 바위 틈 (Open gap beyond his position) — The gap is viewed obliquely past 임정현; used as A small background opening preserves the established observation axis without competing with his face and chest.\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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png" ], [ "char:임정현", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/451b6f0a-c1b4-4b5d-9fbd-fbb3c744bf3f.png" ] ], "asset_id": "bc76a30b-f151-4a0a-a91e-af39885e2129" }, "S56sh40": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S57sh7": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S57sh7.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_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: The outdoor market alley beside an exterior wall, along the fleeing man's route away from the central fighting area.\n\nSHOT TEXT (authoritative, Korean): 허공을 날아온 낫이 도망치는 박상현의 등 한가운데 깊숙이 푹 박혀 상체가 충격으로 앞으로 쏠린 미드임팩트 순간.\n\nCARRIED STATE (persist exactly): Broken stalls, fallen weapons and blood remain along the emptied market lane. 박상현: A thrown sickle is embedded in his back as he strikes the 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: Track directly behind and to one side of 박상현 at lower-chest height, matching his speed briefly and preserving the pursuit axis toward the wall ahead. Frame him from upper legs to head with his back centered, catching the sickle lodged at its middle as his torso pitches forward while the wall remains a separate, narrow destination at frame right. His partly turned head retains the last backward glance toward 안규홍 outside the frame; emphasize the torso's impact-driven displacement rather than changing angle or exposure.\n- FRAMING SCALE: medium shot\n- KEY BACKGROUND ELEMENTS: 벽 (Ahead of 박상현, before his body strikes it) — Seen obliquely along the direction of pursuit; used as A narrow right-side plane makes the imminent collision legible without blocking the back wound; 등에 박힌 낫 (Embedded in the middle of 박상현's back) — The exposed portion is viewed from behind at an oblique angle; used as A realistically scaled detail against his back establishes the cause of the forward pitch.\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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png" ], [ "char:박상현", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/4db16aea-d0e1-45c2-acc8-6e8efbda159d.png" ] ], "asset_id": "32ba9ee3-5ee8-4bf5-b51d-628359c1bf61" }, "S57sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S57sh19": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S58sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S58sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S58sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S59sh2": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S59sh2.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The steep wooded uphill path leading from the market side toward the mountain camp.\n\nSHOT TEXT (authoritative, Korean): 안규홍의 등 한가운데 난 깊은 상처에서 붉은 피가 흘러 저고리를 짙게 적신 클로즈업.\n\nCARRIED STATE (persist exactly): The steep wooded approach rises above the distant market. 안규홍: He climbs alone carrying two bloodied sickles; blood from his deep back slash soaks his jeogori, and his hands remain blood-covered.\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 close behind 안규홍, offset slightly left at mid-back height, looking obliquely across his back in a direct observational view. His climbing torso occupies most of the frame, with the central wound and blood-soaked jeogori clearly readable and a narrow margin of uphill forest path retained for context; his head remains outside the crop, oriented toward the climb. Hold this entry composition before the tracking movement develops, making camera distance the principal framing emphasis.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Uphill forest path (Visible only at the margins of the climbing torso) — The path continues uphill beyond the subject; used as Provides a restrained spatial reference without competing with the wound.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "2e08c992-7e18-41ad-8a14-57af8366804d" }, "S59sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S59sh11": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S59sh11.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The separate forest descent on the opposite side of the mountain camp, away from the approaching lone climber.\n\nSHOT TEXT (authoritative, Korean): 반대편 숲길 비탈, 토미이시와 일본인 군인들이 총을 멘 채 아래로 발을 내디딘 mid-stride 순간의 뒷모습.\n\nCARRIED STATE (persist exactly): Separate wooded paths carry the ascent and descent without intersecting. 토미이시: He walks downhill retaining his sword.\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: Cut explicitly to the opposite path, beginning behind and left of 토미이시 and the Japanese soldiers on its uphill side, with an elevated lens tilted down along their descent. In a direct rear observation, place 토미이시 near center-left and the soldiers at differing depths toward the lower right, retaining their full descending strides and slung rifles as their attention follows the path ahead. Hold the stage-entry framing before tracking, emphasizing the reversal of travel direction through unsynchronized steps, differing shoulder angles, and naturally uneven gaps rather than a matching row of backs.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Downhill continuation of the opposite forest path in the lower-right of the frame, midground.\n- KEY BACKGROUND ELEMENTS: Opposite descending forest path (Occupied by the descending party) — Runs from the upper-left depth toward the lower-right frame edge; used as Establishes a separate route and a clearly descending movement; Slung rifles (Carried by the soldiers) — Seen obliquely beside their backs, at ordinary body-relative scale; used as Clarify the armed party without enlarging any single weapon.\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:토미이시", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/c8296eb1-5a7c-4601-a9e9-81f9fdf60bcb.png" ] ], "asset_id": "a9955fc4-6842-40a5-a557-ac83ab7a0d93" }, "S60sh2": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S60sh11": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S60sh12": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S60sh12.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: Behind a tree at the edge of the devastated mountain camp, adjoining the forest cover outside the clearing.\n\nSHOT TEXT (authoritative, Korean): 피 묻은 쌍낫의 자루를 꽉 움켜쥐어 손가락 마디가 하얘진 안규홍의 주먹 클로즈업.\n\nCARRIED STATE (persist exactly): Smoke, broken bowls, overturned cookware, fallen timber and bloodied rice persist throughout the camp. 안규홍: He grips both bloodied sickles and moves into the forest; his face and hands are smeared with blood and dirt, and his back wound remains open.\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 behind the same tree and stop the crane at 안규홍's hand height, observing his near flank from an oblique side angle. His tightening fingers and whitening knuckles occupy the central close view, with the bloodstained paired sickle handles crossing the lower portion and enough torso and tree edge retained to keep the weapons at believable scale. Make the reduction in camera distance the principal accent, keeping his head outside the frame and his attention directed toward the camp off-screen rather than implying that he looks at his hands.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Bloodstained paired sickles (Held tightly in 안규홍's hands) — Handles lie obliquely across the lower frame, with only portions of the blades visible; used as Give the tightening grip its narrative object while leaving the hands as the primary subject; Concealing tree trunk (Still beside 안규홍's hidden position) — A partial edge remains behind his near flank; used as Maintains continuity with the concealed observation.\nCompose the frame exactly as specified above — camera angle, subject scale and screen placement. Keep true physical scale between people and background elements: fixtures and distant objects occupy only the small screen area their real size and distance dictate; never enlarge a background object into a foreground presence.\n\nPERSPECTIVE & SCALE GUIDES (draw these as part of the sketch — they are the whole point of this layout):\n- Draw the HORIZON LINE at the camera's eye height, and 2-3 thin PERSPECTIVE GUIDE LINES converging toward the vanishing point, so the depth of the space is explicit.\n- TRUE RELATIVE SIZE: draw every person and every set mass at the exact screen size that its real-world size and its distance from the camera dictate. A high wall-mounted device or any distant object stays SMALL against the architecture; people scale with their depth along the guide lines. NEVER enlarge a background object beyond its true perspective size.\n- For EVERY person draw one thin EYELINE ARROW from the eyes to the exact thing they look at; if something moves, one thin MOTION ARROW along its path.\n- All guides are simple thin pencil lines — layout language only, never objects in the scene, and still NO text, numbers or letters anywhere.", "skipped_reason": null, "error": null, "no_plate": true, "ref_paths": [ [ "char:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "46742370-5b9f-4d7a-808e-0ece1e4b21c2" }, "S61sh4": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S61sh15": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S61sh32": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S62sh12": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S62sh19": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S62sh22": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S63sh18": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S63sh18.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The dirt slope at the wooded edge of the mountain camp, below the spot where the fighters lost their weapons.\n\nSHOT TEXT (authoritative, Korean): 엎어진 안규홍의 등 위에 올라탄 자세로 양손으로 목을 꽉 조르고 있는 토미이시의 핏대 선 얼굴.\n\nCARRIED STATE (persist exactly): A dislodged sickle and the dropped sword lie on the dirt near the slope; the camp ruins and battle debris persist. 안규홍: He is pinned in a choking struggle, with blood spreading afresh through his jeogori from the reopened back wound; his face remains blood- and dirt-covered. 토미이시: He straddles in a choking posture, using both hands and no longer holding his sword.\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 stage-entry camera beside 안규홍's shoulder, close to the ground and tilted obliquely upward toward 토미이시, observing the struggle directly rather than reproducing 안규홍's failing vision. 토미이시's strained three-quarter face occupies the upper center as he looks down at the neck he is gripping, with both forearms descending into the lower third and his weight visibly pitched over 안규홍's prone back. Keep 안규홍's near shoulder, turned-down head and hands resisting the wrists at the lower edge, so the facial emphasis remains physically connected to the strangling action.\n- FRAMING SCALE: close-up\n- KEY BACKGROUND ELEMENTS: Earth beneath the struggle (The men have fallen onto the ground after rolling down the slope); used as A narrow lower-edge strip establishes how little space remains beneath 안규홍.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ], [ "char:토미이시", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/c8296eb1-5a7c-4601-a9e9-81f9fdf60bcb.png" ] ], "asset_id": "2e0c93ad-afb4-454a-b9da-50dde103a91c" }, "S63sh53": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S63sh61": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S64sh3": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "bgonly", "error": null }, "S64sh10": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S64sh18": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S65sh1": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S65sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_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: The steep cypress-lined approach road below the mountain camp, broad enough for horses and military supply carts.\n\nSHOT TEXT (authoritative, Korean): 빽빽한 편백나무 사이로 가파른 산길을 오르기 위해 일제히 한쪽 발을 내디딘 거대한 수의 일본인 군인 대열 전경.\n\nCARRIED STATE (persist exactly): A military-supply cart carries a machine gun along the steep forest path; horses accompany the column.\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 crane descent from the elevated position beside the uphill path, observing directly and diagonally downhill through the dense cypress trees while retaining a wide view of the approaching column. Let the route run from upper-right background toward lower-left foreground: 배상도 leads beside the horse, the mounted 헌병 장교 looks uphill beyond the lower-left edge, and roughly fifty Japanese soldiers extend behind them with loaded carts and the cart-mounted machine gun. Make the advancing footfalls legible as a collective beat without cloning the men: forward feet are caught at slightly different points of planting, with individual knee bends, shoulder angles and natural spacing variations, while 배상도 and the soldiers attend to the uphill route.\n- FRAMING SCALE: wide shot\n- FRAME LAYOUT: Approaching column on the mountain path in the middle-center of the frame, midground, moves toward uphill continuation beyond the lower-left frame edge; Rear of the column and supply carts in the upper-right of the frame, background.\n- KEY BACKGROUND ELEMENTS: Dense cypress trees (The column emerges between them); used as Create irregular foreground and background openings without concealing all the footfalls; Steep mountain path (Filled by the advancing military column) — Ascends from upper-right background toward lower-left foreground; used as Organizes the soldiers, lead horse and carts into a single readable approach; Japanese soldiers behind the lead group (Advancing with bayonet-fitted rifles; planting feet in slightly different phases with varied knee bends, shoulder angles and spacing) — Seen obliquely from above, following the uphill direction rather than facing the lens; used as Convey the column's numerical weight without duplicated poses or a posed group arrangement; Supply carts and cart-mounted machine gun (Loaded carts follow the lead group, with a machine gun on a cart) — Oblique upper and side views follow the path's diagonal; used as Remain small within the rear column, establishing military equipment at realistic scale.\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/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png" ] ], "asset_id": "052a900c-9848-4657-a468-c7a3d9bbcd1c" }, "S65sh14": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S65sh19": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S66sh1": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S66sh9": { "image_path": null, "plate_path": null, "prompt": null, "skipped_reason": "prev", "error": null }, "S66sh22": { "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S66sh22.png", "plate_path": null, "prompt": "Every attached image is a CHARACTER REFERENCE for proportion only. There is no location photograph — stage the location purely from THE LOCATION and SHOT TEXT below.\n\nDraw ONE storyboard layout frame, 16:9, filling the entire image edge-to-edge.\n\nSTYLE — LAYOUT-ONLY THUMBNAIL SKETCH: the lightest possible\ndirector's layout drawing. THIN, CLEAN, UNIFORM PENCIL CONTOUR\nLINES ONLY on pure white paper. Absolutely NO shading, NO tone, NO\nhatching, NO texture, NO grayscale fill, NO light-and-shadow, NO\nfacial features beyond a bare head outline, NO clothing detail, NO\nmaterial rendering. The frame contains ONLY: the camera framing,\neach figure as a simple correct-proportion human contour in its\nexact pose and screen position/size, and the few major set masses\nas plain outline shapes. It must read as a quick layout guide,\nnever as a finished drawing.\n\nTHE LOCATION: The shaded forest path leading onward between cypress trees from the ruined mountain camp, with its far end darkened by tree cover.\n\nSHOT TEXT (authoritative, Korean): 어둠이 깔린 숲길 끝을 향해 한쪽 발을 내디딘 mid-stride 자세인 안규홍의 굳건한 뒷모습.\n\nCARRIED STATE (persist exactly): It remains daytime among the cypress trees; the devastated camp and its scattered cookware and bloodied food are left behind. 안규홍: He walks at the front with a limp, the bloodied sickle hanging low in his hand; his face is blood- and dirt-covered, his back wound remains open and his neck is bare.\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 established rear-left follow at 안규홍's lower-chest height, using a restrained downward tilt to include his full figure while keeping the distant route above the frame boundary. Place his back slightly right of center, catch one foot advancing through his uneven stride, and leave the bloodied sickle hanging at his side as his attention stays on the route ahead, unseen beyond the upper edge. Maintain the preceding rear-follow distance and daylight, emphasizing only the advancing body position before cutting to black rather than darkening the forest.\n- FRAMING SCALE: wide shot\n- KEY BACKGROUND ELEMENTS: 피 묻은 낫 (Bloodied and carried in 안규홍's lowered hand) — Hangs beside his body, seen obliquely from behind; used as A small, legible continuation of his resolve beside the walking figure; 편백 (The walking route passes between the trees); used as Trunks at the lateral edges contain the rear view without exposing the destination; 발밑의 이동 경로 (Only the nearby ground traversed by 안규홍 is visible; the route's endpoint is outside the frame); used as Provides space to read the advancing foot while withholding where the group is going.\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:안규홍", "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/reference/a9f0fe87-d8fb-4e1c-beb4-4ff2050200e2.png" ] ], "asset_id": "0b420f52-818e-4a0b-9031-18736e4cd7ee" } }, "map_conti": {}, "conti_pack": "5.202607222353", "lane_conti": { "S3sh18": { "lane": "structure_plate", "group_id": "bg_tiled_house", "segment_id": "seg_porch", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_tiled_house_sel.png", "seed_asset_id": "0d12e89a-d0a7-4e88-a172-83d7a9b982f6", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B04.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S3sh18.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B04.png" }, "S7sh10": { "lane": "structure_plate", "group_id": "bg_tiled_house", "segment_id": "seg_gate", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_tiled_house_sel.png", "seed_asset_id": "0d12e89a-d0a7-4e88-a172-83d7a9b982f6", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B01.png", "bg_reason": "", "bypass_reason": "prev" }, "S8sh5": { "lane": "structure_plate", "group_id": "bg_thatched_house", "segment_id": "gate_threshold", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_thatched_house_sel.png", "seed_asset_id": "2dc88acf-a75f-4d7e-973d-10ab234660a8", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L05B01.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S8sh5.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L05B01.png" }, "S10sh15": { "lane": "structure_plate", "group_id": "bg_market", "segment_id": "seg_02", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "seed_asset_id": "32b543ac-1086-4282-b907-3fcd465b580a", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S12sh10": { "lane": "map_marker", "group_id": "bg_paddy_path", "segment_id": "seg_03", "marker_attempts": 3, "marker_best_effort": true, "marker_pick_index": 2, "marker_pick_count": 3, "marker_pick_why_ko": "후보 2와 3 모두 여러 오류를 포함하고 있으나, 후보 2는 카메라 마커가 예상 위치에 비교적 정확히 배치되어 있고 마커의 중복이 없어 후보 3보다 원래의 기획 의도에 더 가깝습니다.", "marker_model": "nb2", "marker_check": { "markers_ok": false, "details_ko": "다수의 피사체 마커 위치와 방향이 잘못되었고, 일부가 시야각을 벗어났으며, 불필요한 텍스트와 선이 추가되었습니다.", "violations": [ { "axis": "camera_wedge", "note_ko": "E1 마커가 카메라 시야각(웨지) 영역 바깥에 위치해 있습니다." }, { "axis": "entity_position", "note_ko": "E2와 E3 마커가 지정된 산길 위가 아닌 완전히 다른 구역에 잘못 배치되었습니다." }, { "axis": "entity_facing", "note_ko": "모든 피사체(E1, E2, E3)의 방향 화살표가 지정된 북쪽 좌표가 아닌 카메라를 향하고 있습니다." }, { "axis": "extra_content", "note_ko": "도면에 'Look target'이라는 텍스트와 피사체를 가리키는 불필요한 지시선들이 임의로 추가되었습니다." } ] }, "marker_models_tried": [ "nb2" ], "sketch_attempts": 1, "status": "ok", "image_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/lane_sketch_S12sh10.png", "base_map_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/canon_bg_paddy_path_map.png", "base_map_asset_id": "92364ebb-3bf9-4328-b506-0cef621ca433", "marker_map_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/lane_marker_map_S12sh10.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=0.86, y=0.55 — the right edge area of the plan (landmark, for reference: on the right side of the mountain path, slightly above the mountain-foot junction); its sight line ends at LOOK TARGET: at x=0.84, y=0.15 — the upper-right area of the plan (landmark, for reference: the left side of the mountain path near its upper end); the frame's LEFT edge cuts through at x=0.70, y=0.15 — the upper-right area of the plan (landmark, for reference: the terrain slightly above the guardian tree foliage) and its RIGHT edge through at x=0.98, y=0.15 — the upper-right area of the plan (landmark, for reference: the empty space to the right of the mountain path near the top edge)\n- E1 (man stepping forward): circle at x=0.87, y=0.40 — the right edge area of the plan (landmark, for reference: on the right side of the mountain path, a short distance above the junction), facing at x=0.87, y=0.10 — the upper-right area of the plan (landmark, for reference: farther up the right side of the mountain path)\n- E2 (man walking uphill): circle at x=0.83, y=0.15 — the upper-right area of the plan (landmark, for reference: on the left edge of the mountain path, near the top boundary of the map), facing at x=0.83, y=0.05 — the upper-right area of the plan (landmark, for reference: the top edge of the mountain path)\n- E3 (man walking uphill): circle at x=0.84, y=0.20 — the upper-right area of the plan (landmark, for reference: on the left side of the mountain path, between the middle and top sections), facing at x=0.84, y=0.10 — the upper-right area of the plan (landmark, for reference: farther up the center of the mountain path)", "geometry": { "entity_placements": [ { "slot": "E1", "subject_en": "man stepping forward", "x": 0.87, "y": 0.4, "anchor_en": "on the right side of the mountain path, a short distance above the junction", "facing": { "x": 0.87, "y": 0.1 }, "facing_anchor_en": "farther up the right side of the mountain path", "camera_facing_relation": "away_from_camera", "camera_facing_evidence": "염재보의 뒷모습." }, { "slot": "E2", "subject_en": "man walking uphill", "x": 0.83, "y": 0.15, "anchor_en": "on the left edge of the mountain path, near the top boundary of the map", "facing": { "x": 0.83, "y": 0.05 }, "facing_anchor_en": "the top edge of the mountain path", "camera_facing_relation": "away_from_camera", "camera_facing_evidence": "멀어지는 두 사람의 등 뒤로" }, { "slot": "E3", "subject_en": "man walking uphill", "x": 0.84, "y": 0.2, "anchor_en": "on the left side of the mountain path, between the middle and top sections", "facing": { "x": 0.84, "y": 0.1 }, "facing_anchor_en": "farther up the center of the mountain path", "camera_facing_relation": "away_from_camera", "camera_facing_evidence": "멀어지는 두 사람의 등 뒤로" } ], "camera": { "origin": { "x": 0.86, "y": 0.55 }, "look_target": { "x": 0.84, "y": 0.15 }, "origin_anchor_en": "on the right side of the mountain path, slightly above the mountain-foot junction", "look_target_anchor_en": "the left side of the mountain path near its upper end", "view_left": { "x": 0.7, "y": 0.15 }, "view_right": { "x": 0.98, "y": 0.15 }, "view_left_anchor_en": "the terrain slightly above the guardian tree foliage", "view_right_anchor_en": "the empty space to the right of the mountain path near the top edge" }, "rationale_ko": "카메라는 산길(M1) 우측 하단부에 위치하여 오르막을 향해 촬영합니다. 방금 전 나무 밑에서 일어난 염재보(E1)는 산길 우측(프레임 우하단)에서 걷기 시작하며, 안규홍(E2)과 이관회(E3)는 화면 좌상단 쪽에 위치하도록 산길 좌측 상단에 거리를 두고 배치했습니다. 이를 통해 세 사람이 모두 산길을 오르고 있지만, 염재보가 약간의 거리를 두고 뒤따르는 '미드 액션 상태'와 세 사람 간의 공간적 간격이 잘 드러나도록 프레이밍했습니다." }, "geometry_attempts": 1, "leakage": { "has_marker_leakage": false, "details_ko": "기호, 텍스트 등 마커 유출이 없으며 자연스러운 원근감이 표현된 스케치입니다." }, "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 right side of the mountain path, slightly above the mountain-foot junction (coarse estimate x=0.86, y=0.55); its sight line ends at LOOK TARGET: the left side of the mountain path near its upper end (coarse estimate x=0.84, y=0.15); the frame's LEFT edge cuts through the terrain slightly above the guardian tree foliage (coarse estimate x=0.70, y=0.15) and its RIGHT edge through the empty space to the right of the mountain path near the top edge (coarse estimate x=0.98, y=0.15) — everything between those two edges is in frame, anything outside them is out of frame\n- man stepping forward stands on the right side of the mountain path, a short distance above the junction (coarse estimate x=0.87, y=0.40), facing farther up the right side of the mountain path (coarse estimate x=0.87, y=0.10) — from this camera the subject is near the CENTER of the frame and faces away from the camera, into the depth of the shot, so the camera sees this subject from behind\n- man walking uphill stands on the left edge of the mountain path, near the top boundary of the map (coarse estimate x=0.83, y=0.15), facing the top edge of the mountain path (coarse estimate x=0.83, y=0.05) — from this camera the subject is near the CENTER of the frame and faces away from the camera, into the depth of the shot, so the camera sees this subject from behind\n- man walking uphill stands on the left side of the mountain path, between the middle and top sections (coarse estimate x=0.84, y=0.20), facing farther up the center of the mountain path (coarse estimate x=0.84, y=0.10) — from this camera the subject is near the CENTER of the frame and faces away from the camera, into the depth of the shot, so the camera sees this subject from behind; this subject is turned toward the man walking uphill\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): From behind 염재보 at a below-eye-level height, settle just off the uphill axis before beginning the follow, with his entire rear figure in the lower-right midground. Keep 안규홍 and 이관회 separately readable farther uphill toward the upper left, exposing an uninterrupted interval of path between them and 염재보 as he extends his first following step. All three attend to the route ahead, but their walking phases differ—염재보 just committing, 안규홍 transferring weight, and 이관회 lifting a trailing heel—so spacing, rather than a new lighting or distance effect, expresses his decision to join.\n\nTHE LOCATION: 논둑길\n\nSHOT TEXT (authoritative, Korean): 멀어지는 두 사람의 등 뒤로 거리를 둔 채 산길을 향해 한 발을 뻗은 미드 액션 상태인 염재보의 뒷모습.\n\nCARRIED STATE (persist exactly): Dawn fog persists along the mountain path beyond the tree fork. 염재보: He has tightened his straw-shoe ties and now follows on foot without a gun. 안규홍: He ascends with his shoulder bundle and concealed jade ring. 이관회: He ascends carrying his travel bundle.\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": "d286f973-862c-4243-8f09-c550226664ee" }, "S14sh1": { "lane": "structure_plate", "group_id": "bg_lakeside_camp", "segment_id": "seg_01", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_lakeside_camp_sel.png", "seed_asset_id": "4d7542af-9887-40c1-ad92-e627c929288c", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_lakeside_camp_sel.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S14sh9": { "lane": "structure_plate", "group_id": "bg_lakeside_camp", "segment_id": "seg_01", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_lakeside_camp_sel.png", "seed_asset_id": "4d7542af-9887-40c1-ad92-e627c929288c", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_lakeside_camp_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S14sh9.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_lakeside_camp_sel.png" }, "S16sh7": { "lane": "structure_plate", "group_id": "bg_farmhouse_yard", "segment_id": "granary_frontage", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_farmhouse_yard_sel.png", "seed_asset_id": "ed5a274a-bbcb-4fb2-91e7-cea7dadafbaf", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_farmhouse_yard_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S18sh14": { "lane": "structure_plate", "group_id": "bg_lakeside_camp", "segment_id": "seg_01", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_lakeside_camp_sel.png", "seed_asset_id": "4d7542af-9887-40c1-ad92-e627c929288c", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_lakeside_camp_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S23sh1": { "lane": "structure_plate", "group_id": "bg_village_lanes", "segment_id": "seg_01", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png", "seed_asset_id": "aeaa845f-49c4-45b0-8a1f-1c8f50c6daed", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S23sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png" }, "S26sh2": { "lane": "structure_plate", "group_id": "bg_mountain_camp", "segment_id": "clearing", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "seed_asset_id": "8c17c7ae-efff-4bb5-b88c-7c5528f00716", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S26sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png" }, "S28sh4": { "lane": "structure_plate", "group_id": "bg_tiled_house", "segment_id": "seg_porch", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_tiled_house_sel.png", "seed_asset_id": "0d12e89a-d0a7-4e88-a172-83d7a9b982f6", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B07.png", "bg_reason": "", "bypass_reason": "prev" }, "S28sh18": { "lane": "structure_plate", "group_id": "bg_tiled_house", "segment_id": "seg_storehouse", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_tiled_house_sel.png", "seed_asset_id": "0d12e89a-d0a7-4e88-a172-83d7a9b982f6", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B05.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S30sh50": { "lane": "structure_plate", "group_id": "bg_market", "segment_id": "seg_01", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "seed_asset_id": "32b543ac-1086-4282-b907-3fcd465b580a", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S35sh8": { "lane": "structure_plate", "group_id": "bg_village_lanes", "segment_id": "seg_01", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png", "seed_asset_id": "aeaa845f-49c4-45b0-8a1f-1c8f50c6daed", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S35sh8.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png" }, "S35sh13": { "lane": "structure_plate", "group_id": "bg_village_lanes", "segment_id": "seg_04", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png", "seed_asset_id": "aeaa845f-49c4-45b0-8a1f-1c8f50c6daed", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S35sh13.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_village_lanes_sel.png" }, "S37sh2": { "lane": "structure_plate", "group_id": "bg_market", "segment_id": "seg_05", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "seed_asset_id": "32b543ac-1086-4282-b907-3fcd465b580a", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S37sh2.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png" }, "S40sh13": { "lane": "structure_plate", "group_id": "bg_tiled_house", "segment_id": "seg_gate", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_tiled_house_sel.png", "seed_asset_id": "0d12e89a-d0a7-4e88-a172-83d7a9b982f6", "seed_status": "ok", "bg_source": "plate", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/episodes/272bd7af-9294-4490-98c6-88a40e9deacc/images/background_chain/L08B01.png", "bg_reason": "", "bypass_reason": "prev" }, "S43sh12": { "lane": "structure_plate", "group_id": "bg_government_office_exterior", "segment_id": "front_entrance_approach", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_government_office_exterior_sel.png", "seed_asset_id": "a1aa7312-aa5c-4e06-8470-b67bfdce1854", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_government_office_exterior_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S48sh10": { "lane": "structure_plate", "group_id": "bg_market", "segment_id": "seg_04", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "seed_asset_id": "32b543ac-1086-4282-b907-3fcd465b580a", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S48sh10.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png" }, "S52sh1": { "lane": "structure_plate", "group_id": "bg_mountain_camp", "segment_id": "ridge", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "seed_asset_id": "8c17c7ae-efff-4bb5-b88c-7c5528f00716", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S52sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png" }, "S56sh31": { "lane": "structure_plate", "group_id": "bg_mountain_camp", "segment_id": "hut_margin", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "seed_asset_id": "8c17c7ae-efff-4bb5-b88c-7c5528f00716", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S56sh31.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png" }, "S57sh7": { "lane": "structure_plate", "group_id": "bg_market", "segment_id": "seg_05", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "seed_asset_id": "32b543ac-1086-4282-b907-3fcd465b580a", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S57sh7.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png" }, "S57sh12": { "lane": "structure_plate", "group_id": "bg_market", "segment_id": "seg_01", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "seed_asset_id": "32b543ac-1086-4282-b907-3fcd465b580a", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_market_sel.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S60sh2": { "lane": "structure_plate", "group_id": "bg_mountain_camp", "segment_id": "ridge", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "seed_asset_id": "8c17c7ae-efff-4bb5-b88c-7c5528f00716", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "bg_reason": "", "bypass_reason": "bg_only" }, "S61sh4": { "lane": "structure_plate", "group_id": "bg_mountain_camp", "segment_id": "hut_margin", "status": "ab_select_bypass", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "seed_asset_id": "8c17c7ae-efff-4bb5-b88c-7c5528f00716", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "bg_reason": "", "bypass_reason": "prev" }, "S65sh1": { "lane": "structure_plate", "group_id": "bg_mountain_camp", "segment_id": "main_approach", "status": "ab_select_ready", "seed_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "seed_asset_id": "8c17c7ae-efff-4bb5-b88c-7c5528f00716", "seed_status": "ok", "bg_source": "seed", "bg_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png", "bg_reason": "", "conti_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/272bd7af-9294-4490-98c6-88a40e9deacc/conti/conti_S65sh1.png", "plate_path": "/Users/manta/Documents/Projects/TheRoad-I1/projects/db00517b-165b-4005-a287-f28936b59b95/images/background_chain/seed_bg_mountain_camp_sel.png" } } }, "step_id": "shot_conti_light", "run_id": "51ca49aa-a95c-4a9e-b9c7-7a07d43ded5f", "resolved_model": "gpt-image-2", "updated_at": "2026-09-09T00:24:23.812664+00:00", "project_config_snapshot": {} }