{ "S35sh2": { "input_fingerprint": "7211054995c7e93d", "geometry": { "entity_placements": [ { "slot": "E1", "subject_en": "escaping Asian refugee", "x": 0.6, "y": 0.3, "anchor_en": "in the refugee settlement street corridor, above the right-middle section of the central street passage", "facing": { "x": 0.9, "y": 0.1 }, "facing_anchor_en": "toward the upper-right boundary of the refugee settlement street corridor", "camera_facing_relation": "away_from_camera", "camera_facing_evidence": "다급히 등을 돌린 채" }, { "slot": "E2", "subject_en": "second escaping Asian refugee", "x": 0.7, "y": 0.22, "anchor_en": "further right and higher up within the refugee settlement street corridor", "facing": { "x": 0.95, "y": 0.05 }, "facing_anchor_en": "at the far upper-right corner of the refugee settlement street corridor", "camera_facing_relation": "away_from_camera", "camera_facing_evidence": "다급히 등을 돌린 채" }, { "slot": "E3", "subject_en": "third escaping Asian refugee", "x": 0.8, "y": 0.15, "anchor_en": "near the upper-right edge of the refugee settlement street corridor", "facing": { "x": 0.98, "y": 0.02 }, "facing_anchor_en": "at the extreme top-right tip of the refugee settlement street corridor", "camera_facing_relation": "away_from_camera", "camera_facing_evidence": "다급히 등을 돌린 채" } ], "camera": { "origin": { "x": 0.2, "y": 0.65 }, "look_target": { "x": 0.7, "y": 0.22 }, "origin_anchor_en": "in the lower section of the refugee settlement street corridor, near the bottom left", "look_target_anchor_en": "at the second escaping refugee in the upper right corridor", "view_left": { "x": 0.4, "y": 0.1 }, "view_right": { "x": 0.95, "y": 0.5 }, "view_left_anchor_en": "along the top boundary of the refugee settlement street corridor, left of center", "view_right_anchor_en": "on the right side of the central street passage strip" }, "rationale_ko": "카메라는 좌측 하단의 난민촌 거리 하부에서 우측 상단으로 다급히 달아나는 아시아계 난민들의 뒷모습을 넓게 포착합니다. 밀려드는 쓰나미의 방향성과 피사체들의 도주 경로(우상단)를 일치시켰으며, '다급히 등을 돌린 채'라는 지문에 맞추어 인물들이 카메라 반대편인 도주로를 향해 전력 질주하도록 배치했습니다." }, "marker_check": { "markers_ok": false, "details_ko": "모든 캐릭터(E1, E2, E3)의 방향 화살표가 잘못된 방향을 가리키고 있습니다.", "violations": [ { "axis": "entity_facing", "note_ko": "E1, E2, E3의 화살표가 지시된 좌표(우측 상단)가 아닌 우측 하단 방향을 향하고 있습니다." } ] }, "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=0.20, y=0.65 — the left edge area of the plan (landmark, for reference: in the lower section of the refugee settlement street corridor, near the bottom left); its sight line ends at LOOK TARGET: at x=0.70, y=0.22 — the upper-right area of the plan (landmark, for reference: at the second escaping refugee in the upper right corridor); the frame's LEFT edge cuts through at x=0.40, y=0.10 — the upper middle of the plan (landmark, for reference: along the top boundary of the refugee settlement street corridor, left of center) and its RIGHT edge through at x=0.95, y=0.50 — the right edge area of the plan (landmark, for reference: on the right side of the central street passage strip)\n- E1 (escaping Asian refugee): circle at x=0.60, y=0.30 — the upper middle of the plan (landmark, for reference: in the refugee settlement street corridor, above the right-middle section of the central street passage), facing at x=0.90, y=0.10 — the upper-right area of the plan (landmark, for reference: toward the upper-right boundary of the refugee settlement street corridor)\n- E2 (second escaping Asian refugee): circle at x=0.70, y=0.22 — the upper-right area of the plan (landmark, for reference: further right and higher up within the refugee settlement street corridor), facing at x=0.95, y=0.05 — the upper-right area of the plan (landmark, for reference: at the far upper-right corner of the refugee settlement street corridor)\n- E3 (third escaping Asian refugee): circle at x=0.80, y=0.15 — the upper-right area of the plan (landmark, for reference: near the upper-right edge of the refugee settlement street corridor), facing at x=0.98, y=0.02 — the upper-right area of the plan (landmark, for reference: at the extreme top-right tip of the refugee settlement street corridor)", "marker_attempts": 3, "marker_best_effort": true, "marker_pick_index": 3, "marker_pick_count": 3, "marker_pick_why_ko": "후보 3은 카메라 및 피사체들의 위치와 시야각이 모두 정확하게 배치되어 있으며, 오직 피사체들의 바라보는 방향(화살표)만 잘못되었기 때문에 지시사항과 가장 가깝습니다.", "marker_model": "nb2", "marker_map_sha256": "2ea8188a683fe234ec9902f47ffb904f2157a67959912c8dc0337f7cb5c6853b", "leakage": { "has_marker_leakage": false, "details_ko": "도해용 기호나 글자, 평면도 등의 유출 없이 지시된 카메라 앵글과 씬의 내용만을 표현한 깨끗한 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 in the lower section of the refugee settlement street corridor, near the bottom left (coarse estimate x=0.20, y=0.65); its sight line ends at LOOK TARGET: at the second escaping refugee in the upper right corridor (coarse estimate x=0.70, y=0.22); the frame's LEFT edge cuts through along the top boundary of the refugee settlement street corridor, left of center (coarse estimate x=0.40, y=0.10) and its RIGHT edge through on the right side of the central street passage strip (coarse estimate x=0.95, y=0.50) — everything between those two edges is in frame, anything outside them is out of frame\n- escaping Asian refugee stands in the refugee settlement street corridor, above the right-middle section of the central street passage (coarse estimate x=0.60, y=0.30), facing toward the upper-right boundary of the refugee settlement street corridor (coarse estimate x=0.90, 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- second escaping Asian refugee stands further right and higher up within the refugee settlement street corridor (coarse estimate x=0.70, y=0.22), facing at the far upper-right corner of the refugee settlement street corridor (coarse estimate x=0.95, 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- third escaping Asian refugee stands near the upper-right edge of the refugee settlement street corridor (coarse estimate x=0.80, y=0.15), facing at the extreme top-right tip of the refugee settlement street corridor (coarse estimate x=0.98, y=0.02) — 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\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): Finish the parallel tracking stage from a low, laterally offset position behind the runners, looking diagonally across their backs while preserving a broad view of the street behind them. Place the escaping Asian refugees across the center and right, moving toward the upper-right depth, with the advancing black seawater entering from the lower-left rear; their full bodies remain readable without exaggerated foreground scale. This direct observer view emphasizes the shrinking positional gap: raised feet occur at different stride phases, shoulders pitch at different angles, and each runner remains absorbed in the escape route ahead rather than turning toward the water or lens.\n\nTHE LOCATION: 해일이 밀려드는 인천 난민촌 거리\n\nSHOT TEXT (authoritative, Korean): 난민촌 거리에 거대하게 밀려든 검은 바닷물이, 다급히 등을 돌린 채 한 발을 공중에 띄운 질주 자세인 아시아계 난민들의 뒤를 집어삼키기 직전의 맹렬한 찰나.\n\nCARRIED STATE (persist exactly): Seawater is pouring into the settlement through the breached seawall, with a rapidly advancing surge filling the streets. The ground is shaking.\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." }, "S48sh5": { "input_fingerprint": "904085ac795d029d", "geometry": { "entity_placements": [ { "slot": "E1", "subject_en": "turning camper van", "x": 0.32, "y": 0.7, "anchor_en": "on the mountain track entrance curving off the main road", "facing": { "x": 0.38, "y": 0.5 }, "facing_anchor_en": "uphill along the mountain access track to the north", "camera_facing_relation": "unspecified", "camera_facing_evidence": "" } ], "camera": { "origin": { "x": 0.5, "y": 0.88 }, "look_target": { "x": 0.32, "y": 0.7 }, "origin_anchor_en": "on the main road southeast of the mountain track junction", "look_target_anchor_en": "at the turning camper on the track entrance", "view_left": { "x": 0.15, "y": 0.65 }, "view_right": { "x": 0.45, "y": 0.55 }, "view_left_anchor_en": "on the grassy verge west of the track entrance", "view_right_anchor_en": "on the open ground north of the main road" }, "rationale_ko": "캠핑카는 멀리 있는 검문소(A4)를 피하기 위해 메인 도로(A1)를 주행하다 산길(A2)로 급격히 좌회전하며 진입합니다. 카메라는 회전 반경 바깥인 캠핑카의 우측 후방(남동쪽 도로 위)에 낮게 위치하여 북서쪽을 바라봅니다. 이 구도는 차량이 화면 우측 상단의 산길을 향해 코를 트는 역동적인 움직임을 포착하며, 후측면에서 흙먼지를 일으키며 도주하는 긴박한 액션을 서사의 맥락에 맞게 강조합니다." }, "marker_check": { "markers_ok": false, "details_ko": "카메라와 피사체(E1)의 위치가 잘못되었으며 시야각의 방향도 일치하지 않습니다.", "violations": [ { "axis": "camera_position", "note_ko": "카메라(CAM) 마커가 지정된 좌표(x=0.50, y=0.88)가 아닌 잘못된 위치에 배치되었습니다." }, { "axis": "camera_wedge", "note_ko": "카메라 시야각이 지정된 룩 타겟(x=0.32, y=0.70)을 향하지 않고 다른 방향으로 열려 있습니다." }, { "axis": "entity_position", "note_ko": "E1 마커가 지정된 좌표(x=0.32, y=0.70)가 아닌 산길 위쪽의 다른 위치에 배치되었습니다." } ] }, "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=0.50, y=0.88 — the lower middle of the plan (landmark, for reference: on the main road southeast of the mountain track junction); its sight line ends at LOOK TARGET: at x=0.32, y=0.70 — the lower-left area of the plan (landmark, for reference: at the turning camper on the track entrance); the frame's LEFT edge cuts through at x=0.15, y=0.65 — the left edge area of the plan (landmark, for reference: on the grassy verge west of the track entrance) and its RIGHT edge through at x=0.45, y=0.55 — the center of the plan (landmark, for reference: on the open ground north of the main road)\n- E1 (turning camper van): circle at x=0.32, y=0.70 — the lower-left area of the plan (landmark, for reference: on the mountain track entrance curving off the main road), facing at x=0.38, y=0.50 — the center of the plan (landmark, for reference: uphill along the mountain access track to the north)", "marker_attempts": 3, "marker_best_effort": true, "marker_pick_index": 2, "marker_pick_count": 3, "marker_pick_why_ko": "후보 1은 5개의 위반 사항(카메라 위치, 시야각, 피사체 위치, 피사체 방향, 불필요한 추가 기호)이 있고 후보 3은 4개의 위반 사항(카메라 위치, 시야각, 피사체 위치, 피사체 방향)이 있는 반면, 후보 2는 피사체의 방향이 요구사항(우측 상단)과 일치하여 3개의 위반 사항(카메라 위치, 시야각, 피사체 위치)만 가지므로 제시된 연출 지시와 가장 가깝습니다.", "marker_model": "nb2", "marker_map_sha256": "c74ef2514d708a2e072c02bce0ace84047dfd0ecc6028462efae16df3c8e47f6", "leakage": { "has_marker_leakage": false, "details_ko": "다이어그램 기호나 텍스트 누출 없이 자연스러운 투시도로 그려짐." }, "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 main road southeast of the mountain track junction (coarse estimate x=0.50, y=0.88); its sight line ends at LOOK TARGET: at the turning camper on the track entrance (coarse estimate x=0.32, y=0.70); the frame's LEFT edge cuts through on the grassy verge west of the track entrance (coarse estimate x=0.15, y=0.65) and its RIGHT edge through on the open ground north of the main road (coarse estimate x=0.45, y=0.55) — everything between those two edges is in frame, anything outside them is out of frame\n- turning camper van stands on the mountain track entrance curving off the main road (coarse estimate x=0.32, y=0.70), facing uphill along the mountain access track to the north (coarse estimate x=0.38, y=0.50) — from this camera the subject is near the CENTER of the frame and faces toward the RIGHT of the frame and away from the camera, into the depth of the shot, so the camera sees this subject from behind\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): Track outside the turning arc at axle height, looking diagonally forward from the camper's rear quarter toward the mountain-road entrance in a direct exterior observation. Place the complete vehicle across the lower-middle frame at no more than roughly one third of the image, its nose swinging toward the upper-right entrance while both the turning body and wheels remain readable and earth dust bursts from the tires. Keep the distant checkpoint on the original road at upper-left and the occupants out of view, emphasizing the vehicle's change of position against a steady low viewing angle.\n\nTHE LOCATION: 화성 검문소를 우회하는 산길\n\nSHOT TEXT (authoritative, Korean): 캠핑카가 검문소를 앞두고 산길 쪽으로 차체가 급격히 꺾인 채 타이어에서 흙먼지가 뿜어져 나오는 mid-action 역동적인 순간.\n\nCARRIED STATE (persist exactly): The old camper carries the collected supplies and has unresolved roof and window-frame leaks from the previous rainstorm. A checkpoint lies ahead amid barren fields, dead trees and abandoned houses; Charlie occupies the rear seating area.\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." } }