{ "S6sh4": { "input_fingerprint": "24bfdcf0e92e2ed1", "geometry": { "entity_placements": [ { "slot": "E1", "subject_en": "jumping young woman", "x": 0.58, "y": 0.73, "anchor_en": "on the approach route ground to the east of the central firing line", "facing": { "x": 0.5, "y": 0.25 }, "facing_anchor_en": "towards the opposite cliff rim where the attack originated", "camera_facing_relation": "unspecified", "camera_facing_evidence": "" }, { "slot": "E2", "subject_en": "jumping young man", "x": 0.42, "y": 0.77, "anchor_en": "on the approach route ground to the west of the central firing line", "facing": { "x": 0.5, "y": 0.25 }, "facing_anchor_en": "towards the opposite cliff rim across the open canyon airspace", "camera_facing_relation": "unspecified", "camera_facing_evidence": "" }, { "slot": "E3", "subject_en": "flaming projectile", "x": 0.5, "y": 0.75, "anchor_en": "in mid-air above the central portion of the canyon approach route", "facing": { "x": 0.5, "y": 0.95 }, "facing_anchor_en": "towards the southern extent of the canyon approach zone", "camera_facing_relation": "unspecified", "camera_facing_evidence": "" } ], "camera": { "origin": { "x": 0.4, "y": 0.65 }, "look_target": { "x": 0.5, "y": 0.75 }, "origin_anchor_en": "on the western edge of the canyon approach route ground", "look_target_anchor_en": "at the center of the canyon approach route in front of the tree", "view_left": { "x": 0.6, "y": 0.7 }, "view_right": { "x": 0.4, "y": 0.8 }, "view_left_anchor_en": "on the eastern ground of the canyon approach zone", "view_right_anchor_en": "on the western ground of the canyon approach zone" }, "rationale_ko": "카메라는 발사선 서쪽의 협곡 접근로 가장자리에서 남동쪽을 비스듬히 바라보며 추적합니다. 북쪽 반대편 절벽에서 날아와 화면 중앙을 가로지르는 탄자를 중심으로, 윌마는 동쪽으로 도약하여 프레임의 왼쪽 가장자리를 향해 몸을 비틀고 토니는 서쪽으로 도약하여 오른쪽 가장자리를 향합니다. 공격의 발원지인 북쪽 절벽은 카메라의 뒤편에 위치하여 완벽히 화면 밖에 머물며, 두 인물의 시선은 자연스럽게 프레임 밖 북쪽을 향하게 됩니다." }, "marker_check": { "markers_ok": false, "details_ko": "카메라 시야각 방향이 잘못되었고, 일부 피사체의 위치와 방향이 일치하지 않으며 방향 화살표가 누락된 피사체가 있습니다.", "violations": [ { "axis": "camera_wedge", "note_ko": "시야각이 지정된 목표점(남동쪽)을 향하지 않고 동쪽을 향하고 있으며, E3 마커가 시야각을 벗어났습니다." }, { "axis": "entity_position", "note_ko": "E3 마커가 지정된 좌표(y=0.75 부근)가 아닌 완전히 다른 위치(협곡 상공)에 배치되었습니다." }, { "axis": "entity_facing", "note_ko": "E1의 방향 화살표가 누락되었으며, E2는 북쪽이 아닌 동쪽을, E3는 남쪽이 아닌 북쪽을 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=0.40, y=0.65 — the center of the plan (landmark, for reference: on the western edge of the canyon approach route ground); its sight line ends at LOOK TARGET: at x=0.50, y=0.75 — the lower middle of the plan (landmark, for reference: at the center of the canyon approach route in front of the tree); the frame's LEFT edge cuts through at x=0.60, y=0.70 — the lower middle of the plan (landmark, for reference: on the eastern ground of the canyon approach zone) and its RIGHT edge through at x=0.40, y=0.80 — the lower middle of the plan (landmark, for reference: on the western ground of the canyon approach zone)\n- E1 (jumping young woman): circle at x=0.58, y=0.73 — the lower middle of the plan (landmark, for reference: on the approach route ground to the east of the central firing line), facing at x=0.50, y=0.25 — the upper middle of the plan (landmark, for reference: towards the opposite cliff rim where the attack originated)\n- E2 (jumping young man): circle at x=0.42, y=0.77 — the lower middle of the plan (landmark, for reference: on the approach route ground to the west of the central firing line), facing at x=0.50, y=0.25 — the upper middle of the plan (landmark, for reference: towards the opposite cliff rim across the open canyon airspace)\n- E3 (flaming projectile): circle at x=0.50, y=0.75 — the lower middle of the plan (landmark, for reference: in mid-air above the central portion of the canyon approach route), facing at x=0.50, y=0.95 — the lower middle of the plan (landmark, for reference: towards the southern extent of the canyon approach zone)", "marker_attempts": 3, "marker_best_effort": true, "marker_pick_index": 2, "marker_pick_count": 3, "marker_pick_why_ko": "후보 2는 카메라 위치가 지정된 좌표(x=0.40, y=0.65)에 근접하게 배치되어 있어, 모든 위치와 방향이 틀린 다른 후보들에 비해 요구사항에서 가장 적게 벗어났습니다.", "marker_model": "nb2", "marker_map_sha256": "a1f8d0bbf41edb9fbd8356541babac46920a0d11b309f8530a760b80018a0c01", "leakage": { "has_marker_leakage": false, "details_ko": "기호나 마커가 없음" }, "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 western edge of the canyon approach route ground (coarse estimate x=0.40, y=0.65); its sight line ends at LOOK TARGET: at the center of the canyon approach route in front of the tree (coarse estimate x=0.50, y=0.75); the frame's LEFT edge cuts through on the eastern ground of the canyon approach zone (coarse estimate x=0.60, y=0.70) and its RIGHT edge through on the western ground of the canyon approach zone (coarse estimate x=0.40, y=0.80) — everything between those two edges is in frame, anything outside them is out of frame\n- jumping young woman stands on the approach route ground to the east of the central firing line (coarse estimate x=0.58, y=0.73), facing towards the opposite cliff rim where the attack originated (coarse estimate x=0.50, y=0.25) — from this camera the subject is in the LEFT part of the frame and faces toward the LEFT of the frame and toward the camera, so the camera sees this subject from the front\n- jumping young man stands on the approach route ground to the west of the central firing line (coarse estimate x=0.42, y=0.77), facing towards the opposite cliff rim across the open canyon airspace (coarse estimate x=0.50, y=0.25) — from this camera the subject is in the RIGHT part of the frame and faces toward the LEFT of the frame and toward the camera, so the camera sees this subject from the front\n- flaming projectile stands in mid-air above the central portion of the canyon approach route (coarse estimate x=0.50, y=0.75), facing towards the southern extent of the canyon approach zone (coarse estimate x=0.50, y=0.95) — 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): Tracking laterally at waist height from an oblique position off the firing line, the camera briefly widens to preserve Wilma, Tony, and the flaming projectile within one action plane. Wilma twists airborne toward the left edge and Tony launches toward the right, leaving the projectile crossing the central gap while both keep their attention toward the attack’s off-screen origin.\n\nTHE LOCATION: 산림 협곡 접근로와 절벽 사이 상공\n\nSHOT TEXT (authoritative, Korean): 불을 뿜는 탄자가 지나가는 가운데, 이를 피해 양옆 허공으로 몸을 비틀어 막 날아오른 윌마와 토니의 도약 찰나\n\nCARRIED STATE (persist exactly): Three jumper landing grooves mark the ground, one of them fresh. A rocket projectile passes between the opposing jumps and blasts the intervening rock. 윌마 디어링: She is launching sideways to evade the shot, wearing her moss-smeared belt with one silver weight removed and carrying her moss-smeared gun. 토니(앤서니 로저스): He is launching in the opposite direction, wearing the jumper belt before either silver weight falls away. He carries his rescue rope.\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." }, "S6sh13": { "input_fingerprint": "8b561ec5dd85f3bd", "geometry": { "entity_placements": [ { "slot": "E1", "subject_en": "falling young woman", "x": 0.48, "y": 0.46, "anchor_en": "suspended in the open canyon airspace over the chasm", "facing": { "x": 0.55, "y": 0.3 }, "facing_anchor_en": "on the opposite cliff rim where they intend to land", "camera_facing_relation": "unspecified", "camera_facing_evidence": "" }, { "slot": "E2", "subject_en": "falling young man", "x": 0.5, "y": 0.46, "anchor_en": "suspended in the open canyon airspace over the chasm", "facing": { "x": 0.55, "y": 0.3 }, "facing_anchor_en": "on the opposite cliff rim where they intend to land", "camera_facing_relation": "unspecified", "camera_facing_evidence": "" } ], "camera": { "origin": { "x": 0.38, "y": 0.6 }, "look_target": { "x": 0.55, "y": 0.3 }, "origin_anchor_en": "in the open canyon airspace diagonally behind the falling pair", "look_target_anchor_en": "on the opposite cliff rim", "view_left": { "x": 0.45, "y": 0.25 }, "view_right": { "x": 0.65, "y": 0.32 }, "view_left_anchor_en": "along the leftward portion of the opposite cliff rim", "view_right_anchor_en": "along the rightward portion of the opposite cliff rim" }, "rationale_ko": "윌마와 토니가 서로를 붙잡고 협곡 상공(C1)을 가로질러 반대편 절벽(O1)으로 비스듬히 하강하는 순간입니다. 카메라는 이들의 하강 궤적과 속도를 맞추며 약간 뒤쪽 측면 허공에 위치하고, 프레임 중앙에 두 사람을 담아 맞은편 착지 지점을 대각선으로 바라보도록 배치했습니다." }, "marker_check": { "markers_ok": false, "details_ko": "카메라 위치가 잘못된 구역에 있고, 피사체의 방향 화살표가 반대이며, 불필요한 텍스트가 포함되었습니다.", "violations": [ { "axis": "camera_position", "note_ko": "CAM 마커가 지정된 협곡 상공(Open Canyon Airspace)이 아닌 아래쪽 절벽/지상 구역에 잘못 배치되었습니다." }, { "axis": "entity_facing", "note_ko": "E1과 E2의 방향 화살표가 시선 목표 지점(Look Target)을 향하지 않고 반대 방향(피사체 쪽)을 가리키고 있습니다." }, { "axis": "extra_content", "note_ko": "지정되지 않은 'LOOK TARGET'이라는 텍스트가 도면에 임의로 추가되었습니다." } ] }, "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=0.38, y=0.60 — the center of the plan (landmark, for reference: in the open canyon airspace diagonally behind the falling pair); its sight line ends at LOOK TARGET: at x=0.55, y=0.30 — the upper middle of the plan (landmark, for reference: on the opposite cliff rim); the frame's LEFT edge cuts through at x=0.45, y=0.25 — the upper middle of the plan (landmark, for reference: along the leftward portion of the opposite cliff rim) and its RIGHT edge through at x=0.65, y=0.32 — the upper middle of the plan (landmark, for reference: along the rightward portion of the opposite cliff rim)\n- E1 (falling young woman): circle at x=0.48, y=0.46 — the center of the plan (landmark, for reference: suspended in the open canyon airspace over the chasm), facing at x=0.55, y=0.30 — the upper middle of the plan (landmark, for reference: on the opposite cliff rim where they intend to land)\n- E2 (falling young man): circle at x=0.50, y=0.46 — the center of the plan (landmark, for reference: suspended in the open canyon airspace over the chasm), facing at x=0.55, y=0.30 — the upper middle of the plan (landmark, for reference: on the opposite cliff rim where they intend to land)", "marker_attempts": 3, "marker_best_effort": true, "marker_pick_index": 3, "marker_pick_count": 3, "marker_pick_why_ko": "후보 3은 시야각(카메라 웨지)이 지정된 방향과 일치하게 그려졌으며 피사체의 위치도 요구사항에 부합하여, 카메라 위치와 화살표 방향, 불필요한 텍스트가 추가된 점을 제외하면 가장 지시사항에 근접합니다.", "marker_model": "nb2", "marker_map_sha256": "cfad7429d9e5881ce8b6af692d073e693102e6cdceb1c80c57edbc76b1d2f01d", "leakage": { "has_marker_leakage": false, "details_ko": "기호나 텍스트 누출 없이 3D 뷰로 무난하게 그려졌습니다." }, "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 open canyon airspace diagonally behind the falling pair (coarse estimate x=0.38, y=0.60); its sight line ends at LOOK TARGET: on the opposite cliff rim (coarse estimate x=0.55, y=0.30); the frame's LEFT edge cuts through along the leftward portion of the opposite cliff rim (coarse estimate x=0.45, y=0.25) and its RIGHT edge through along the rightward portion of the opposite cliff rim (coarse estimate x=0.65, y=0.32) — everything between those two edges is in frame, anything outside them is out of frame\n- falling young woman stands suspended in the open canyon airspace over the chasm (coarse estimate x=0.48, y=0.46), facing on the opposite cliff rim where they intend to land (coarse estimate x=0.55, y=0.30) — 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- falling young man stands suspended in the open canyon airspace over the chasm (coarse estimate x=0.50, y=0.46), facing on the opposite cliff rim where they intend to land (coarse estimate x=0.55, y=0.30) — from this camera the subject is in the RIGHT part of the frame and faces away from the camera, into the depth of the shot, so the camera sees this subject from behind\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): Several meters beside and slightly above the pair, the tracking camera matches their downward speed and looks diagonally along their shared trajectory toward the opposite side of the canyon. Wilma and Tony remain clasped in the middle third with their bodies pitched along the same descending diagonal, their attention held on the approaching landing direction rather than the lens.\n\nTHE LOCATION: 산림 협곡 접근로와 절벽 사이 상공\n\nSHOT TEXT (authoritative, Korean): 서로를 단단히 붙잡은 두 사람의 몸이 협곡 반대편 아래쪽을 향해 사선으로 기울어진 채 허공에 떠 있는 순간\n\nCARRIED STATE (persist exactly): The struck rock remains blasted apart. Two silver weights have fallen free from Tony's belt toward the gorge. 윌마 디어링: She is airborne on a descending diagonal toward the far side, gripping a jumper harness. Her moss-smeared belt remains missing the previously transferred weight, and she carries her moss-smeared gun. 토니(앤서니 로저스): He is airborne on the same descending diagonal, suspended by his harness after losing two silver weights. He still carries his rescue rope.\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." } }