返回 Prompt 库





印度婚礼庭院回眸人像
{ "prompt": { "scene": "Traditional Indian wedding celebration in a decorated courtyard with marigold garlands, floral archways, and guests in festive ethnic attire blurred in the






Prompt
{
"prompt": {
"scene": "Traditional Indian wedding celebration in a decorated courtyard with marigold garlands, floral archways, and guests in festive ethnic attire blurred in the background.",
"subject": {
"gender": "adult woman",
"pose": "sitting slightly turned away from the camera while looking back over her shoulder with a confident expression",
"hair": "dark black hair tied in a loose messy bun with soft strands framing the face",
"expression": "calm, confident, subtle gaze",
"body_details": {
"visible_back": true,
"tattoo": "small tattoo on forearm"
}
},
"clothing": {
"bottom": "orange embroidered lehenga skirt with intricate gold zari work",
"top": "backless traditional blouse styling",
"jewelry": [
"gold maang tikka",
"heavy jhumka earrings",
"gold bangles",
"armlets"
]
},
"lighting": {
"type": "natural golden hour sunlight",
"style": "warm cinematic tones"
},
"camera": {
"angle": "rear three-quarter portrait angle",
"depth_of_field": "shallow depth of field with blurred wedding crowd",
"focus": "sharp focus on subject"
},
"style": [
"ultra realistic",
"editorial fashion photography",
"cinematic Indian wedding aesthetic",
"high detail",
"warm festive atmosphere"
],
"composition": {
"orientation": "vertical",
"aspect_ratio": "2:3"
}
},
"negative_prompt": [
"low quality",
"blurry face",
"extra limbs",
"deformed hands",
"cropped body",
"bad anatomy",
"oversaturated skin",
"duplicate jewelry",
"distorted background",
"watermark",
"text"
],
"generation_settings": {
"resolution": "1024x1536",
"steps": 35,
"cfg_scale": 7.5,
"sampler": "DPM++ 2M Karras"
}
}
PhotoTypographyCinematicHero PortraitFashion LookGroup SceneGolden HourLow KeyPortrait OrientationSocial Media Post
如何使用这个 Prompt
- 用上方的复制按钮复制完整提示词。
- 把方括号 [ ] 里的占位内容替换成你自己的主体、场景或细节。
- 粘贴到 Gemini / Nano Banana Pro 生成,或直接点上面的「试试这个 Prompt」在本站免费生成,再对照示例图微调用词。
风格说明
- Photo
- 要求模型输出照片级真实感:自然光线、可信的皮肤与材质、类似相机的景深,而不是插画或 3D 质感。
- Typography
- 文字本身是画面的一部分。Nano Banana Pro 这类新模型能渲染清晰的美术字,但提示词里要把具体文字写短、并用引号标出。
- Cinematic
- 电影感渲染:宽画幅构图、强烈的光比、调色(常见青橙对比),画面自带叙事氛围。
- Hero Portrait
- 把单一主体拍成主视觉:紧凑构图、有力的眼神或姿态,背景简化,让人物撑起整张画面。
- Fashion Look
- 时尚大片式造型:突出服装细节与面料质感,模特姿态和布光借鉴杂志拍摄。
- Group Scene
- 多人同框:AI 一致性最难的场景,提示词通常要明确给每个人物分配位置和角色。
- Golden Hour
- 日出后/日落前的低角度暖阳:影子长而柔、色调金黄,几乎适合一切主体。
- Low Key
- 整体偏暗、局部高光的画面:情绪浓烈,且对提示词里光源位置的描述非常敏感。
- Portrait Orientation
- 竖版画幅(如 3:4、9:16):手机屏幕、Stories、应用商店截图的原生格式。
- Social Media Post
- 为社交信息流(Instagram、X、小红书)优化的构图与画幅:主体突出、预留文案位置、配色在小屏幕上依然醒目。
常见问题
这个 Prompt 怎么在 Gemini(Nano Banana Pro)里使用?
点击上方的复制按钮拿到完整提示词,粘贴到 Gemini 或任何支持 Nano Banana Pro 的工具里,再对照本页示例图检查效果。也可以直接点「试试这个 Prompt」在本站生成——每天有免费次数,无需注册。
可以修改「印度婚礼庭院回眸人像」这个提示词吗?
可以。方括号 [ ] 里的内容是占位参数,本来就应该替换成你自己的主体或细节;主体、光线、风格关键词也都可以自由调整,措辞上的小改动往往带来明显不同的结果。
这个提示词适用于哪些 AI 模型?
它最初是为 Google 的 Gemini 图像模型(含 Nano Banana Pro)分享的。大多数文生图模型也能理解,但构图和文字渲染质量会因模型而异。





