{ "S3sh1": { "input_fingerprint": "6f499413d5ca5220", "geometry": { "camera": { "look_target": { "x": 0.5, "y": 0.48 }, "look_target_anchor_en": "In the open north-central portion of the Outdoor Campus Ground.", "origin": { "x": 0.5, "y": 0.875 }, "origin_anchor_en": "At the southern entrance edge of the Outdoor Campus Ground.", "view_left": { "x": 0.2, "y": 0.43 }, "view_left_anchor_en": "At the western boundary of the Outdoor Campus Ground beside the long planted strip.", "view_right": { "x": 0.79, "y": 0.43 }, "view_right_anchor_en": "At the eastern boundary of the Outdoor Campus Ground where the Campus Approach joins it." }, "entity_placements": [ { "anchor_en": "On the southwestern side of the Outdoor Campus Ground, north of its southern entrance.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.45, "y": 0.58 }, "facing_anchor_en": "In the open left-center portion of the Outdoor Campus Ground.", "slot": "E1", "subject_en": "university student holding a raised sign", "x": 0.405, "y": 0.72 }, { "anchor_en": "On the southeastern side of the Outdoor Campus Ground, north of its southern entrance.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.55, "y": 0.58 }, "facing_anchor_en": "In the open right-center portion of the Outdoor Campus Ground.", "slot": "E2", "subject_en": "university student carrying a placard", "x": 0.595, "y": 0.71 }, { "anchor_en": "On the west side of the Outdoor Campus Ground beside the open central corridor.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.49, "y": 0.59 }, "facing_anchor_en": "In the open central corridor of the Outdoor Campus Ground.", "slot": "E3", "subject_en": "university student calling through a megaphone", "x": 0.35, "y": 0.59 }, { "anchor_en": "On the east side of the Outdoor Campus Ground, south of the Campus Approach junction.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.51, "y": 0.59 }, "facing_anchor_en": "In the open central corridor of the Outdoor Campus Ground.", "slot": "E4", "subject_en": "university student holding a raised sign", "x": 0.65, "y": 0.57 }, { "anchor_en": "On the left side of the north-central gathering area of the Outdoor Campus Ground.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.49, "y": 0.65 }, "facing_anchor_en": "In the open central corridor leading from the southern entrance of the Outdoor Campus Ground.", "slot": "E5", "subject_en": "university student speaking into a megaphone", "x": 0.43, "y": 0.49 }, { "anchor_en": "On the right side of the north-central gathering area of the Outdoor Campus Ground.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.51, "y": 0.64 }, "facing_anchor_en": "In the open central corridor leading from the southern entrance of the Outdoor Campus Ground.", "slot": "E6", "subject_en": "university student displaying a placard", "x": 0.57, "y": 0.47 } ], "rationale_ko": "카메라는 광장 남쪽 입구 가장자리에서 북쪽 군중을 향하도록 배치했다. 전경 학생들은 좌우에서 프레임에 들어오며, 중앙에는 전진 트래킹이 통과할 수 있는 열린 통로를 남겼다. 확성기와 팻말을 든 학생들을 좌우와 북쪽에 분산해 붐비는 와이드 샷의 깊이와 밀도를 만들었다." }, "marker_check": { "markers_ok": true, "details_ko": "정상" }, "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 places its marker relative\nto a fixed feature, zone or boundary VISIBLE on the attached plan —\nthat landmark-relative description is the placement authority. The\nnormalized fractions in parentheses are coarse estimates of the same\nspot (x runs left→right 0..1, y runs top→bottom 0..1 of the full\ncanvas) — use them only to confirm the rough region; when in doubt,\nthe landmark description wins. Do NOT relocate a marker onto a\ndifferent salient line or feature than the one its description names.\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 the southern entrance edge of the Outdoor Campus Ground. (coarse estimate x=0.50, y=0.88); its sight line ends at LOOK TARGET: In the open north-central portion of the Outdoor Campus Ground. (coarse estimate x=0.50, y=0.48); the frame's LEFT edge cuts through At the western boundary of the Outdoor Campus Ground beside the long planted strip. (coarse estimate x=0.20, y=0.43) and its RIGHT edge through At the eastern boundary of the Outdoor Campus Ground where the Campus Approach joins it. (coarse estimate x=0.79, y=0.43)\n- E1 (university student holding a raised sign): circle On the southwestern side of the Outdoor Campus Ground, north of its southern entrance. (coarse estimate x=0.41, y=0.72), facing In the open left-center portion of the Outdoor Campus Ground. (coarse estimate x=0.45, y=0.58)\n- E2 (university student carrying a placard): circle On the southeastern side of the Outdoor Campus Ground, north of its southern entrance. (coarse estimate x=0.59, y=0.71), facing In the open right-center portion of the Outdoor Campus Ground. (coarse estimate x=0.55, y=0.58)\n- E3 (university student calling through a megaphone): circle On the west side of the Outdoor Campus Ground beside the open central corridor. (coarse estimate x=0.35, y=0.59), facing In the open central corridor of the Outdoor Campus Ground. (coarse estimate x=0.49, y=0.59)\n- E4 (university student holding a raised sign): circle On the east side of the Outdoor Campus Ground, south of the Campus Approach junction. (coarse estimate x=0.65, y=0.57), facing In the open central corridor of the Outdoor Campus Ground. (coarse estimate x=0.51, y=0.59)\n- E5 (university student speaking into a megaphone): circle On the left side of the north-central gathering area of the Outdoor Campus Ground. (coarse estimate x=0.43, y=0.49), facing In the open central corridor leading from the southern entrance of the Outdoor Campus Ground. (coarse estimate x=0.49, y=0.65)\n- E6 (university student displaying a placard): circle On the right side of the north-central gathering area of the Outdoor Campus Ground. (coarse estimate x=0.57, y=0.47), facing In the open central corridor leading from the southern entrance of the Outdoor Campus Ground. (coarse estimate x=0.51, y=0.64)", "marker_attempts": 1, "marker_map_sha256": "323007ce9ae3fa9a5b102770fd4a1818b73681a1548e82a61ff328fdc3d574e6", "leakage": { "has_marker_leakage": false, "details_ko": "도면 마커나 텍스트 같은 유출 흔적이 없는 투시도 렌더링입니다." }, "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: thin uniform dark outlines on plain\npaper, nothing else. Draw every person as a PLAIN ARTIST'S MANNEQUIN:\na featureless oval head with NO face, NO hair, NO clothing and no\ncostume detail — simple tapered limbs and torso, like a wooden posing\nfigure. Because the head has no face and no hair, the ONLY thing that\nshows 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 At the southern entrance edge of the Outdoor Campus Ground. (coarse estimate x=0.50, y=0.88); its sight line ends at LOOK TARGET: In the open north-central portion of the Outdoor Campus Ground. (coarse estimate x=0.50, y=0.48); the frame's LEFT edge cuts through At the western boundary of the Outdoor Campus Ground beside the long planted strip. (coarse estimate x=0.20, y=0.43) and its RIGHT edge through At the eastern boundary of the Outdoor Campus Ground where the Campus Approach joins it. (coarse estimate x=0.79, y=0.43) — everything between those two edges is in frame, anything outside them is out of frame\n- university student holding a raised sign stands On the southwestern side of the Outdoor Campus Ground, north of its southern entrance. (coarse estimate x=0.41, y=0.72), facing In the open left-center portion of the Outdoor Campus Ground. (coarse estimate x=0.45, y=0.58) — from this camera the subject is in the LEFT part of the frame and faces toward the RIGHT of the frame and away from the camera, into the depth of the shot, so the camera sees this subject from behind\n- university student carrying a placard stands On the southeastern side of the Outdoor Campus Ground, north of its southern entrance. (coarse estimate x=0.59, y=0.71), facing In the open right-center portion of the Outdoor Campus Ground. (coarse estimate x=0.55, y=0.58) — from this camera the subject is in the RIGHT part of the frame and faces toward the LEFT of the frame and away from the camera, into the depth of the shot, so the camera sees this subject from behind\n- university student calling through a megaphone stands On the west side of the Outdoor Campus Ground beside the open central corridor. (coarse estimate x=0.35, y=0.59), facing In the open central corridor of the Outdoor Campus Ground. (coarse estimate x=0.49, y=0.59) — from this camera the subject is in the LEFT part of the frame and faces toward the RIGHT of the frame\n- university student holding a raised sign stands On the east side of the Outdoor Campus Ground, south of the Campus Approach junction. (coarse estimate x=0.65, y=0.57), facing In the open central corridor of the Outdoor Campus Ground. (coarse estimate x=0.51, y=0.59) — from this camera the subject is in the RIGHT part of the frame and faces toward the LEFT of the frame\n- university student speaking into a megaphone stands On the left side of the north-central gathering area of the Outdoor Campus Ground. (coarse estimate x=0.43, y=0.49), facing In the open central corridor leading from the southern entrance of the Outdoor Campus Ground. (coarse estimate x=0.49, y=0.65) — from this camera the subject is in the LEFT part of the frame and faces toward the RIGHT of the frame and toward the camera, so the camera sees this subject from the front\n- university student displaying a placard stands On the right side of the north-central gathering area of the Outdoor Campus Ground. (coarse estimate x=0.57, y=0.47), facing In the open central corridor leading from the southern entrance of the Outdoor Campus Ground. (coarse estimate x=0.51, y=0.64) — from this camera the subject is near the CENTER 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\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): At eye level along one edge of the plaza, the camera begins a broad forward track into the dense campus gathering. Foreground students enter from both sides while a central corridor remains open into the crowd; raised signs and megaphones punctuate the upper half without overwhelming the human scale.\n\nTHE LOCATION: 명지대 캠퍼스 광장\n\nSHOT TEXT (authoritative, Korean): 햇살이 내리쬐는 캠퍼스 광장에서 확성기를 들거나 팻말을 든 한국인 대학생들이 붐비는 와이드 샷\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." }, "S32sh2": { "input_fingerprint": "91e404016ebb84b7", "geometry": { "camera": { "look_target": { "x": 0.42, "y": 0.61 }, "look_target_anchor_en": "On the grass directly in front of the inscribed grave marker beside the inter-row cemetery path.", "origin": { "x": 0.35, "y": 0.76 }, "origin_anchor_en": "On the grass between the second and third grave-marker rows south of the inter-row cemetery path.", "view_left": { "x": 0.2, "y": 0.53 }, "view_left_anchor_en": "On the grass along the south edge of the inter-row cemetery path.", "view_right": { "x": 0.7, "y": 0.58 }, "view_right_anchor_en": "On the grass between neighboring markers in the first grave-marker row south of the inter-row cemetery path." }, "entity_placements": [ { "anchor_en": "On the grass immediately in front and slightly left of the inscribed grave marker beside the inter-row cemetery path.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.421, "y": 0.592 }, "facing_anchor_en": "At the inscribed grave marker beside the inter-row cemetery path.", "slot": "E1", "subject_en": "standing young man", "x": 0.39, "y": 0.65 }, { "anchor_en": "On the grass immediately in front and slightly right of the inscribed grave marker beside the inter-row cemetery path.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.421, "y": 0.592 }, "facing_anchor_en": "At the inscribed grave marker beside the inter-row cemetery path.", "slot": "E2", "subject_en": "standing young woman", "x": 0.45, "y": 0.65 } ], "rationale_ko": "두 사람을 김광동 비석 바로 앞 잔디에 함께 멈춰 세우고 모두 비석을 바라보게 했다. 남성을 화면 중심에 가깝게, 여성을 옆으로 치우쳐 배치했으며, 전방 좌측 사분면의 카메라에서 비석이 두 사람 사이에 보이도록 구성했다. 넓은 화각에는 뒤로 이어지는 묘비 행과 묘지 통로가 함께 들어온다." }, "marker_check": { "markers_ok": true, "details_ko": "정상" }, "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 places its marker relative\nto a fixed feature, zone or boundary VISIBLE on the attached plan —\nthat landmark-relative description is the placement authority. The\nnormalized fractions in parentheses are coarse estimates of the same\nspot (x runs left→right 0..1, y runs top→bottom 0..1 of the full\ncanvas) — use them only to confirm the rough region; when in doubt,\nthe landmark description wins. Do NOT relocate a marker onto a\ndifferent salient line or feature than the one its description names.\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 On the grass between the second and third grave-marker rows south of the inter-row cemetery path. (coarse estimate x=0.35, y=0.76); its sight line ends at LOOK TARGET: On the grass directly in front of the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.42, y=0.61); the frame's LEFT edge cuts through On the grass along the south edge of the inter-row cemetery path. (coarse estimate x=0.20, y=0.53) and its RIGHT edge through On the grass between neighboring markers in the first grave-marker row south of the inter-row cemetery path. (coarse estimate x=0.70, y=0.58)\n- E1 (standing young man): circle On the grass immediately in front and slightly left of the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.39, y=0.65), facing At the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.42, y=0.59)\n- E2 (standing young woman): circle On the grass immediately in front and slightly right of the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.45, y=0.65), facing At the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.42, y=0.59)", "marker_attempts": 1, "marker_map_sha256": "b4c9aed1805aa92f0d9e7b23029ca8c161f2d270a9a30830349abadf70660908", "leakage": { "has_marker_leakage": false, "details_ko": "스케치에 마커나 다이어그램 기호가 보이지 않음." }, "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: thin uniform dark outlines on plain\npaper, nothing else. Draw every person as a PLAIN ARTIST'S MANNEQUIN:\na featureless oval head with NO face, NO hair, NO clothing and no\ncostume detail — simple tapered limbs and torso, like a wooden posing\nfigure. Because the head has no face and no hair, the ONLY thing that\nshows 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 grass between the second and third grave-marker rows south of the inter-row cemetery path. (coarse estimate x=0.35, y=0.76); its sight line ends at LOOK TARGET: On the grass directly in front of the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.42, y=0.61); the frame's LEFT edge cuts through On the grass along the south edge of the inter-row cemetery path. (coarse estimate x=0.20, y=0.53) and its RIGHT edge through On the grass between neighboring markers in the first grave-marker row south of the inter-row cemetery path. (coarse estimate x=0.70, y=0.58) — everything between those two edges is in frame, anything outside them is out of frame\n- standing young man stands On the grass immediately in front and slightly left of the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.39, y=0.65), facing At the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.42, y=0.59) — 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- standing young woman stands On the grass immediately in front and slightly right of the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.45, y=0.65), facing At the inscribed grave marker beside the inter-row cemetery path. (coarse estimate x=0.42, y=0.59) — from this camera the subject is in the RIGHT part of the frame and faces toward the LEFT of the frame and away from the camera, into the depth of the shot, so the camera sees this subject from behind\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): From standing eye level on the grave marker's front quarter, hold a static wide composition with 김광석 and 송영숙 stopped together in the midground. Place the inscribed marker between and slightly below their sightlines, with 김광석 nearer the center and 송영숙 offset beside him; surrounding grave markers recede behind them to establish the cemetery layout.\n\nTHE LOCATION: 국립묘지\n\nSHOT TEXT (authoritative, Korean): '육군 대위 김광동'이라 적힌 비석 앞에 우두커니 멈춰 선 김광석(광석·광돌·김광돌)과 송영숙(영숙)\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." }, "S75sh7": { "input_fingerprint": "225593e9b9a60162", "geometry": { "camera": { "look_target": { "x": 0.4, "y": 0.57 }, "look_target_anchor_en": "At the roadway edge just left of the center of the boarding area.", "origin": { "x": 0.86, "y": 0.32 }, "origin_anchor_en": "In the upper-right portion of the bus-stop boarding area.", "view_left": { "x": 0.3, "y": 0.79 }, "view_left_anchor_en": "On the bus travel roadway below the left half of the boarding area.", "view_right": { "x": 0.18, "y": 0.51 }, "view_right_anchor_en": "At the curved left edge of the bus-stop boarding area beside the roadway corner." }, "entity_placements": [ { "anchor_en": "At the roadway edge near the middle of the bus-stop boarding area.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.22, "y": 0.64 }, "facing_anchor_en": "In the bus travel roadway below the left half of the boarding area.", "slot": "E1", "subject_en": "motionless young man", "x": 0.5, "y": 0.54 }, { "anchor_en": "In the bus travel roadway below the left half of the boarding area.", "camera_facing_evidence": "", "camera_facing_relation": "unspecified", "facing": { "x": 0.07, "y": 0.64 }, "facing_anchor_en": "Along the bus travel roadway near the left site boundary.", "slot": "E2", "subject_en": "departing city bus", "x": 0.22, "y": 0.64 } ], "rationale_ko": "남자는 승차 구역의 도로 가장자리에 멈춰 서서 이미 왼쪽 출발 방향으로 멀어진 버스를 바라본다. 카메라는 승차 구역 우측에서 남자와 버스의 승객문 쪽을 비스듬히 보며, 화면상 남자를 왼쪽에 두고 버스를 오른쪽 원경에 겹치지 않게 배치한다." }, "marker_check": { "markers_ok": true, "details_ko": "정상" }, "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 places its marker relative\nto a fixed feature, zone or boundary VISIBLE on the attached plan —\nthat landmark-relative description is the placement authority. The\nnormalized fractions in parentheses are coarse estimates of the same\nspot (x runs left→right 0..1, y runs top→bottom 0..1 of the full\ncanvas) — use them only to confirm the rough region; when in doubt,\nthe landmark description wins. Do NOT relocate a marker onto a\ndifferent salient line or feature than the one its description names.\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 In the upper-right portion of the bus-stop boarding area. (coarse estimate x=0.86, y=0.32); its sight line ends at LOOK TARGET: At the roadway edge just left of the center of the boarding area. (coarse estimate x=0.40, y=0.57); the frame's LEFT edge cuts through On the bus travel roadway below the left half of the boarding area. (coarse estimate x=0.30, y=0.79) and its RIGHT edge through At the curved left edge of the bus-stop boarding area beside the roadway corner. (coarse estimate x=0.18, y=0.51)\n- E1 (motionless young man): circle At the roadway edge near the middle of the bus-stop boarding area. (coarse estimate x=0.50, y=0.54), facing In the bus travel roadway below the left half of the boarding area. (coarse estimate x=0.22, y=0.64)\n- E2 (departing city bus): circle In the bus travel roadway below the left half of the boarding area. (coarse estimate x=0.22, y=0.64), facing Along the bus travel roadway near the left site boundary. (coarse estimate x=0.07, y=0.64)\n\n[REGENERATE — the previous attempt failed the marker check: 카메라(CAM) 마커에서 우측 상단 방향으로 뻗어나가는 불필요한 선이 그려져 있습니다.. Draw exactly the specified markers and change nothing else on the plan.]", "marker_attempts": 2, "marker_map_sha256": "b07b26902f99d5e1cd17826db02407dc502afdf3cd3f41284a045add2093fd66", "leakage": { "has_marker_leakage": false, "details_ko": "마커, 화살표, 문자 등의 기호나 평면도 유출 없이 입체적인 장면으로 잘 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: thin uniform dark outlines on plain\npaper, nothing else. Draw every person as a PLAIN ARTIST'S MANNEQUIN:\na featureless oval head with NO face, NO hair, NO clothing and no\ncostume detail — simple tapered limbs and torso, like a wooden posing\nfigure. Because the head has no face and no hair, the ONLY thing that\nshows 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 upper-right portion of the bus-stop boarding area. (coarse estimate x=0.86, y=0.32); its sight line ends at LOOK TARGET: At the roadway edge just left of the center of the boarding area. (coarse estimate x=0.40, y=0.57); the frame's LEFT edge cuts through On the bus travel roadway below the left half of the boarding area. (coarse estimate x=0.30, y=0.79) and its RIGHT edge through At the curved left edge of the bus-stop boarding area beside the roadway corner. (coarse estimate x=0.18, y=0.51) — everything between those two edges is in frame, anything outside them is out of frame\n- motionless young man stands At the roadway edge near the middle of the bus-stop boarding area. (coarse estimate x=0.50, y=0.54), facing In the bus travel roadway below the left half of the boarding area. (coarse estimate x=0.22, y=0.64) — 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 departing city bus\n- departing city bus stands In the bus travel roadway below the left half of the boarding area. (coarse estimate x=0.22, y=0.64), facing Along the bus travel roadway near the left site boundary. (coarse estimate x=0.07, y=0.64) — 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): At eye level several meters away, let the pan finish with Gwangseok’s full body held on the left third while the departing bus recedes toward the right background along his gaze line. The closed passenger door remains legible on the bus’s near side, and Gwangseok’s motionless figure is separated from it by widening roadway space.\n\nTHE LOCATION: 버스 정류장\n\nSHOT TEXT (authoritative, Korean): 닫힌 버스 문 너머로 멀어지는 버스를 하염없이 쳐다보는 김광석(광석·광돌·김광돌)의 멍한 전신\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." } }