
Loading…
Loading…

Creator · Estelle
View original source ↗生图 Prompt|花店少女写真|提示词分享
奶油针织、满墙鲜花和一点午后的逆光,像路过初夏时被随手留下的一帧。
GPT 实测成图如下。
不同模型成图会有一点差异~
Prompt 放下面,直接复制就可以 ✦
一张清新自然、带轻微网红氛围感的女生写真,竖构图 3:4。画面主体是一位二十出头的东亚女生,冷白细腻的皮肤,五官精致漂亮但保留真实感,眼睛清澈有神,淡淡卧蚕,鼻梁秀气,嘴唇是柔和的蜜桃豆沙色。妆容干净通透,重点突出自然睫毛、淡粉腮红和水润唇妆,不要浓妆,不要夸张网红脸。
她留着一头柔软蓬松的黑色长发,微微带自然卷,几缕碎发被风吹到脸侧。穿一件奶白色细肩带长裙,外面松松披着浅杏色薄针织开衫,衣服简单但有质感,搭配一条很细的银色项链和小耳钉。
场景是在午后阳光很好的白色花店门口,身后是大片浅粉、奶油白和淡黄色鲜花,还有透明玻璃窗与模糊的街景。她一只手抱着一束刚买的白色洋桔梗和淡粉玫瑰,另一只手自然垂在身侧,身体微微侧过来,回头看向镜头,嘴角带一点很轻松、很自然的笑,像朋友突然喊她名字时被随手拍下。
阳光从侧后方照进来,头发边缘有柔和金色轮廓光,脸部明亮干净,肤色通透。整体色调以奶油白、浅杏、嫩粉、柔和绿色为主,低饱和、高级、清透,背景略微虚化,人物清晰,带一点日系杂志和小红书博主写真感。构图自然松弛,不刻意摆拍,氛围温柔、干净、轻盈、有生活感,高级但不冷淡。手部结构自然完整,五指清晰,避免畸形手指;人物比例正常,不要过度磨皮,不要塑料皮肤,不要假脸感。
#鲜花写真[话题]# #AI提示词[话题]# #AI生成[话题]# #GPT生图[话题]# #生图提示词[话题]# #花儿与少女[话题]# #拿花束拍照[话题]# #花束写真[话题]# #头像[话题]#Models & stability
Recommended models
Keep exploring

Strawberry cake, iced milk tea and a bit of afternoon sun on the table edge, like a moment a friend snapped from across the table. Tested with GPT; other models may differ. Prompt: a fresh, natural cafe portrait, vertical 3:4, a woman in her early twenties of East Asian descent...
Prompt
生图 Prompt|咖啡厅下午茶写真|提示词分享 草莓蛋糕、冰奶茶和一点落在桌边的午后阳光,像朋友坐在对面随手拍下的一瞬间。 GPT实测成图如下。 不同模型成图会有一点差异~ Prompt放下面,直接复制就可以 ✦ 一张清新自然的咖啡厅女生写真,竖构图 3:4。画面主体是一位二十出头的东亚女生,冷白自然的皮肤,五官精致但保留真实感,眼睛清澈,淡淡卧蚕,妆容很轻,只带一点蜜桃色腮红、自然睫毛和…

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

The VibeShot prompt framework from Guyi's X long post: the subject stays fixed while expression, clothing, scene, moment, shot size, focal length, camera position, composition, foreground and lighting each get a variable pool, so GPT-Image 2 randomizes within limits to produce 10 candid 9:16 shots at once.
Each detail page keeps the original result, the prompt, and retest evidence in one reading path.