
Loading…

Creator · jackzhang123vip
Source postreplies 50reposts 22saves 218
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。Models & stability
Recommended models
Input assets
Input images used to produce this case; copy any prompt that comes with one.
Keep exploring

Turn your photo into a cute 3D animated portrait using GPT image 2.6 Prompt: Turn my photo into a cute 3D animated portrait. Preserve recognizable features and …
Prompt
Turn my photo into a cute 3D animated portrait. Preserve recognizable features and hairstyle. Add a big round head, huge googly eyes, tiny pupils, round glasses, a button nose and tiny “o” mouth. Sli…

A hyper-real smartphone selfie of a young woman on a high-rise hotel balcony with the Hong Kong skyline at night. The author ran the same prompt on four models; this is the MiniMax H3-Image output (first image of the post).
Prompt
Create a highly realistic handheld smartphone selfie of an East Asian woman in her early twenties on the balcony of a hi

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