原始文档
GPT Image 2 · en
{
"type": "image_generation_prompt",
"style": "photorealistic cinematic street photography, documentary aesthetic",
"resolution": "ultra-high resolution",
"identity_preservation": {
"use_reference_image": true,
"alter_face": false,
"strict_identity_lock": true,
"notes": "Use the uploaded reference image as the compositional base. Replace the central character with the woman from the reference image, preserving exact facial structure, skin texture, lighting direction, shadows, depth of field, angle, and emotional expression. No distortions, no artifacts, no skin tone mismatch."
},
"subject": {
"gender": "female",
"appearance": {
"hair": "bald (as in the original composition)",
"age": "adult",
"expression": "calm, introspective, emotionally neutral",
"skin": "realistic texture with natural pores and tones"
},
"pose": {
"position": "standing still in the center of a busy urban crosswalk",
"action": "gently smelling a flower held near the face",
"posture": "upright, relaxed, perfectly static"
},
"wardrobe": {
"outerwear": "dark minimalist blazer",
"top": "black shirt"
}
},
"environment": {
"location": "busy urban pedestrian crosswalk",
"atmosphere": "metropolitan street scene",
"crowd": {
"behavior": "people moving rapidly around the subject",
"effect": "motion blur from long exposure"
}
},
"lighting": {
"type": "natural daylight",
"conditions": "overcast sky",
"quality": "soft, diffused light",
"effects": [
"realistic skin tones",
"no artificial highlights",
"natural shadows"
]
},
"cinematic_effects": {
"long_exposure": true,
"subject_clarity": "central subject perfectly sharp",
"surroundings": "crowd blurred with motion",
"mood": "isolation and stillness amid chaos"
},
"color_grading": {
"palette": [
"cool grays",
"muted browns",
"soft blacks"
],
"saturation": "desaturated",
"style": "professional cinematic grading"
},
"camera": {
"lens_look": "85mm",
"depth_of_field": "shallow",
"grain": "realistic film grain",
"perspective": "identical to original reference image"
},
"quality_constraints": [
"no facial deformation",
"no AI artifacts",
"no artificial lighting effects",
"perfect facial integration",
"consistent shadows and perspective"
],
"output_goal": "Create a photorealistic, cinematic street photograph featuring a woman standing still in a busy crosswalk, smelling a flower, with long-exposure motion blur around her, preserving the exact realism, lighting, depth, and emotional tone of the original reference image."
}使用方法
- 复制完整原始提示词，并保留其中的参数。
- 按需求替换主体、文字和构图要求。
- 在兼容的外部工具中使用，核对当前使用条件并检查结果。
开始前需了解
- 先确认是否需要参考图。标注兼容模型，不代表该示例由这个模型生成。
- 核对名称、数字与画面文字；不同模型版本的结果可能不同。
