{
 "S8sh1": {
  "input_fingerprint": "31e06aeb7ba8906d",
  "geometry": {
   "camera": {
    "look_target": {
     "x": 0.344,
     "y": 0.515
    },
    "origin": {
     "x": 0.344,
     "y": 0.655
    }
   },
   "entity_placements": [
    {
     "slot": "E1",
     "subject_en": "young woman riding a bicycle",
     "x": 0.344,
     "y": 0.515
    }
   ],
   "rationale_ko": "대형 마트로 이어지는 Commercial District Approach(A1) 도로 중앙에 자전거를 탄 여성을 배치했다. 카메라는 진행 방향인 화면 아래쪽에서 같은 도로 중심선을 따라 뒤로 이동하며 여성을 정면으로 바라보게 했고, 양옆의 상업지구 네온사인(A2)이 외곽 배경에 걸리도록 구성했다."
  },
  "leakage": {
   "has_marker_leakage": false,
   "details_ko": "기호, 텍스트, 화살표 등의 마커 유출 요소가 없는 3차원 투시 스케치입니다."
  },
  "prompt": "Draw a single CAMERA-VIEW storyboard frame (16:9) of the scene staged\non the attached TOP-DOWN SITE PLAN, seen from the camera position\ngiven in the STAGING GEOMETRY data below.\n\nJurisdiction of sources — follow all three, they do not conflict:\n- The attached SITE PLAN is the SOT for what exists on the site and\n  how its zones and landmarks are arranged relative to each other.\n- The STAGING GEOMETRY data below is the SOT for XY POSITIONS and\n  horizontal heading ONLY: where each subject stands on that plan,\n  where the camera stands, and which way it looks. Distances,\n  directions and relative depths between subjects come from these\n  coordinates. Subjects outside the camera's horizontal field of\n  view are out of frame.\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.\n\nSTYLE — LIGHT STORYBOARD FRAME: thin uniform dark outlines on plain\npaper. No shading, no hatching, no texture, no facial features beyond\na minimal head shape, no costume detail. Human figures are correctly\nproportioned full-body outlines in their canonical poses. Environment\nis reduced to a few placement lines (ground line, key landmark\nsilhouettes) — just enough to read positions and depth.\n\nSTAGING GEOMETRY — PLANNING DATA ONLY, NEVER RENDER IT: the lines\nbelow are normalized map coordinates on the attached site plan\n(x runs left→right 0..1, y runs top→bottom 0..1). Use them solely to\nplace the camera and subjects. Do NOT draw any of this data in the\nimage — no numbers, no coordinates, no labels, no arrows, no cones,\nno dots, no diagram symbols of any kind.\n- the camera stands at (x=0.34, y=0.66) and looks toward (x=0.34, y=0.52); subjects outside the camera's horizontal field of view are out of frame\n- young woman riding a bicycle stands at (x=0.34, y=0.52)\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): The camera tracks backward from the center of the road at upper-torso height, holding 수리영 frontally as she rides directly toward it. Her bicycle and body remain centered while taxis, solicitation activity, stalls, and neon signage pass along both outer thirds, preserving her forward travel and the busy street depth.\n\nTHE LOCATION: 대형 마트 외부와 출입구\n\nSHOT TEXT (authoritative, Korean): 붉은 네온사인이 번지는 어두운 번화가 도로 한가운데, 수리영이 자전거 안장에 앉아 한쪽 무릎을 굽혀 페달을 밟고 옷자락이 뒤로 휘날리는 정면 구도.\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."
 },
 "S25sh6": {
  "input_fingerprint": "d47296555bdf7a73",
  "geometry": {
   "camera": {
    "look_target": {
     "x": 0.444,
     "y": 0.787
    },
    "origin": {
     "x": 0.482,
     "y": 0.823
    }
   },
   "entity_placements": [
    {
     "slot": "E1",
     "subject_en": "young man beside mooring rope",
     "x": 0.421,
     "y": 0.775
    },
    {
     "slot": "E2",
     "subject_en": "young woman looking up imploringly",
     "x": 0.458,
     "y": 0.796
    }
   ],
   "rationale_ko": "M2 고정 계류점 바로 옆에 밧줄을 다루는 남성을 두고, 여성은 Harbor Mooring Edge의 열린 접근 방향에서 그에게 바짝 다가선 위치에 배치했다. 카메라는 두 사람의 접근축을 따라 가까이 잡아 여성이 전경 왼쪽, 남성이 밧줄과 함께 후경에 놓이는 미디엄 투 플레인 구도가 되며, 같은 축 너머의 항구 수면과 계류된 배 방향도 읽히게 했다."
  },
  "leakage": {
   "has_marker_leakage": false,
   "details_ko": "마커나 기호 등 계획 데이터 유출이 없는 자연스러운 투시도입니다."
  },
  "prompt": "Draw a single CAMERA-VIEW storyboard frame (16:9) of the scene staged\non the attached TOP-DOWN SITE PLAN, seen from the camera position\ngiven in the STAGING GEOMETRY data below.\n\nJurisdiction of sources — follow all three, they do not conflict:\n- The attached SITE PLAN is the SOT for what exists on the site and\n  how its zones and landmarks are arranged relative to each other.\n- The STAGING GEOMETRY data below is the SOT for XY POSITIONS and\n  horizontal heading ONLY: where each subject stands on that plan,\n  where the camera stands, and which way it looks. Distances,\n  directions and relative depths between subjects come from these\n  coordinates. Subjects outside the camera's horizontal field of\n  view are out of frame.\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.\n\nSTYLE — LIGHT STORYBOARD FRAME: thin uniform dark outlines on plain\npaper. No shading, no hatching, no texture, no facial features beyond\na minimal head shape, no costume detail. Human figures are correctly\nproportioned full-body outlines in their canonical poses. Environment\nis reduced to a few placement lines (ground line, key landmark\nsilhouettes) — just enough to read positions and depth.\n\nSTAGING GEOMETRY — PLANNING DATA ONLY, NEVER RENDER IT: the lines\nbelow are normalized map coordinates on the attached site plan\n(x runs left→right 0..1, y runs top→bottom 0..1). Use them solely to\nplace the camera and subjects. Do NOT draw any of this data in the\nimage — no numbers, no coordinates, no labels, no arrows, no cones,\nno dots, no diagram symbols of any kind.\n- the camera stands at (x=0.48, y=0.82) and looks toward (x=0.44, y=0.79); subjects outside the camera's horizontal field of view are out of frame\n- young man beside mooring rope stands at (x=0.42, y=0.78)\n- young woman looking up imploringly stands at (x=0.46, y=0.80)\n\nCAMERA DIRECTION (vertical angle / elevation / framing SOT): Settle at 수리영's upper-body height just ahead and slightly beside her, holding a medium two-plane composition with her in the near left and 인우 beyond her beside the rope. Her raised face becomes the focus while 인우 and the moored boat remain legible in the same axis, preserving the endpoint of the tracking approach.\n\nTHE LOCATION: 안개 낀 포구\n\nSHOT TEXT (authoritative, Korean): 밧줄 앞 인우에게 다가선 수리영이 고개를 들어 서늘하고 간절한 눈빛으로 그를 올려다보는 구도.\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."
 }
}