迷你模型場景重建

A structured JSON prompt for GPT Image 2 to reconstruct any input image as a clean, collectible-scale miniature diorama.

{
 "reference_images": {
  "scene_reference": "ATTACHED_IMAGE",
  "usage_rule": "使用此圖像作為場景佈局、物體放置和構圖的精確來源。不要重新詮釋或替換場景。"
 },
 "concept": {
  "type": "微縮模型重建",
  "intent": "將附加的場景重建為一個乾淨的、可收藏規模的模型，同時保留原始的空間關係"
 },
 "environment": {
  "scale": "桌面微縮模型",
  "ground": {
   "type": "雕塑底座",
   "behavior": "自然地支撐所有物體，無需封裝",
   "edges": "乾淨、簡約、略微倒角"
  },
  "background": {
   "type": "無縫攝影棚背景",
   "color": "純白色",
   "constraint": "除模型底座外無其他環境"
  }
 },
 "objects_and_elements": {
  "layout_rule": "所有物體必須保持與參照圖片相同的相對位置",
  "primary_elements": "參照中可見的精確車輛、結構、道具和地形",
  "detail_handling": "簡化但忠實的微縮比例",
  "characters": {
   "presence": "僅在參照中存在時",
   "style": "微縮人偶，無面部寫實感"
  }
 },
 "composition": {
  "view": "等距或略微抬高的3/4視角",
  "framing": "整個模型可見，居中",
  "cropping": "無縮放，無電影式裁切"
 },
 "camera": {
  "lens_equivalent": "35mm-50mm",
  "perspective": "微縮真實感",
  "distortion": "無"
 },
 "lighting": {
  "type": "柔和的攝影棚燈光",
  "direction": "頂部並略微傾斜",
  "shadows": "僅物體下方有細微接觸陰影",
  "avoid": ["戲劇性燈光", "聚光燈", "電影對比度"]
 },
 "materials_and_style": {
  "surface_finish": "光滑、啞光或輕微緞面",
  "material_quality": "高品質比例模型材料",
  "aesthetic": "乾淨、現代、高級的模型"
 },
 "quality_controls": {
  "image_clarity": "極度清晰",
  "grain": "無",
  "noise": "無",
  "motion_blur": "無"
 },
 "negative_prompts": [
  "玻璃罩", "展示盒", "博物館展櫃",
  "透明方塊", "保護外殼",
  "玻璃反光", "標籤或銘牌",
  "文字覆蓋", "雜亂背景", "電影模糊"
 ]
}

機器翻譯 — 實際產出作品的是原文 prompt。

✨ 生成 收藏 複製 Prompt 分享 原始貼文 在 Hitboard 開啟