GoodCase.aiAI News · Radar↗AI Map↗Course · LearnPrompt↗
ProjectsGoodCase.aiAI News Radar ↗AI Map ↗LearnPrompt ↗
GoodCase.aiGoodCase.aiAI Prompt Case Collection
GoodCase.ai
RankingsCasesSkillsFavoritesSubmitDailyJoin us
中文EN
Agent Access →

Projects

AI News · Radar ↗AI Map ↗Course · LearnPrompt ↗
GoodCase.aiGoodCase.aiAI Prompt Case Collection
RankingsCasesSkillsFavoritesSubmitDailyJoin us
中文EN
Agent Access →

Loading…

GoodCase.ai · AI Prompt Case Collection
DSH PluginsChangelogFeedback
ModelsCreatorsSeedance 2.5Seedance 2.0GPT Image 2GeminiNano Banana ProClaudeClaude Opus 5.5Grok ImagineVeoKlingQwen ImageGPT Image 1.5MiniMax H3
写实东亚女性网红人像全量中文提示词

写实东亚女性网红人像全量中文提示词

Creator · jackzhang123vip

AI ImageX2026-11-07Added 11/09/2026Source verified#prompt-in-post
More tags (3)
#goodcase-bot-search#grok-gate-passGPT Image 2.6
View original source ↗
Source ♥ 362

Prompt

主体: 一位明确成年的25岁东亚女性,清秀自然的鹅蛋脸,柔和下颌线,偏大的深棕色杏眼,眼神安静、略带倦意,鼻梁自然挺直,鼻头小巧,双唇自然丰满,淡玫瑰豆沙色唇妆,带轻微湿润反光。面颊有柔和的蜜桃粉晕染,保留真实肤质、细微毛孔和自然面部阴影,不使用夸张美颜。

发型: 深棕黑色长直发,发量自然丰厚,顶部略微蓬松,额前有细碎空气刘海和几缕自然垂落的发丝。一侧头发向后收拢成松散的小发髻,另一侧长发自然披落胸前。画面右侧发际附近固定一枚非常醒目的酒红色细长椭圆形磨砂发夹,发夹不能缺失、变色或替换。

服装: 浅燕麦米色、薄款修身长袖针织上衣,圆领略宽,细密横向罗纹和柔软棉质纹理清晰可见,袖口自然堆积在手腕附近。无图案、无Logo、无夸张首饰。

动作: 坐在昏暗卧室中,上半身微微向前倾,一只手自然托住脸颊与下巴,手掌贴合下颌,手指轻触太阳穴附近,手腕弯曲自然,另一只手不必入镜。头部轻微侧倾,眼睛平静地望向手机镜头,嘴唇自然闭合,表情不刻意微笑。

场景: 普通居家卧室,背景为灰褐色墙面,侧后方可隐约看到深色门框、床沿或家具轮廓。室内没有复杂装饰,背景暗且安静,带轻微生活杂乱感。

光线: 夜间近距离暖色手机补光或小型台灯照明,光线主要落在面部、手背和胸前针织衫上。鼻梁一侧形成明显但柔和的阴影,脸颊保留暖橙色亮部,背景比主体暗约2档。光线不均匀,不使用商业影棚的均匀柔光。

镜头: 9:16竖版,手机前置自拍质感,约26–35mm等效焦距,镜头与眼睛接近平齐,略微高于面部。近距离头肩到胸部构图,脸部占据画面上半部分,保留头顶发丝和双肩。轻微手机广角透视,真实手部比例。

风格: 真实生活自拍、暖色低照度摄影、细微高ISO噪点、轻微JPEG压缩质感、克制锐化、自然曝光、暗部保留颗粒。拒绝塑料皮肤、过度磨皮、假睫毛夸张化、过度锐利的虹膜、AI对称脸、影棚布光、电影级过度调色。
≡Provenance · verifiedPublished prompts are human-checked against the original post; platform-reconstructed prompts are not accepted.Compare with source ↗

Models & stability

Recommended models

GPT Image 2.6
Stability
Cost
Medium
Related SkillsEditorial portrait composition ↗

Input assets

Input images used to produce this case; copy any prompt that comes with one.

input asset 1
input asset 2

Keep exploring

Explore related cases.

View all AI Image Case →
Woman in a glossy black bunny costume poses in a luxury lounge
AI ImageXAdded 11/09/2026

Woman in a glossy black bunny costume poses in a luxury lounge

Bunny Girl and Pole Image 1: GPT2.5 Image 2: Flux + LoRA Image 3: Grok Imagine 2 Image 4: Qwen - Image 2.1 + Reference image Ref. Prompt (SFW) See reply, welcom…

Skill · Editorial portrait composition

Prompt

## [Subject Description] A photorealistic full-body fashion portrait of an adult woman with fair, smooth skin, naturally full breasts,S-shaped female figure, long legs, and delicate facial features…

Source heat · X
98
Stability
View case →
Nano Banana: Retouch Lighting and Swap in a White Studio Background, Keeping the Face
AI ImageXAdded 08/19/2026

Nano Banana: Retouch Lighting and Swap in a White Studio Background, Keeping the Face

The author uses Nano Banana for commercial portrait retouching of an uploaded photo. The core workflow locks face identity and proportions and rebuilds only soft studio lighting, a pure white background and natural skin texture, with explicit negative constraints against changing the face.

Skill · Editorial portrait composition

Prompt

Preserve the person's face exactly as it appears in the uploaded image. Do NOT regenerate, reconstruct, reinterpret, beautify, reshape, or replace the face. Maintain the exact: Facial structure and

Source heat · X
93
Stability
40
View case →
Six Flash Portraits of a Young Portuguese Woman
AI ImageXAdded 10/23/2026

Six Flash Portraits of a Young Portuguese Woman

GPT Image 2.5 on ChatGPT Prompt: Create an ultra-realistic 6-photo portrait collage arranged in a seamless 3×2 grid, featuring a naturally beautiful young Portu…

Skill · Editorial portrait composition

Prompt

Create an ultra-realistic 6-photo portrait collage arranged in a seamless 3×2 grid, featuring a naturally beautiful young Portuguese woman in her early 20s. She has warm olive-toned skin, expressive …

Source heat · X
92
Stability
View case →

Each detail page keeps the original result, the prompt, and retest evidence in one reading path.