OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
光影交错中滑落肩头的复古长袍
Vintage Robe Slipping from the Shoulder in Intertwined Light and Shadow
一幅带有复古胶片质感的写实肖像：年轻成年女性穿着棕色毛圈布浴袍或纹理针织开衫，在左上方狭缝硬光下抬头望向左侧，肩部衣物松落，形成戏剧性的明暗对照。
提示词 / Prompt
中文提示词
创作一幅超写实编辑感肖像，使用绑定的人物参考保持年轻成年女性可辨识的面部结构、肤色和发型，同时保留自然皮肤纹理。她的头转向观看者左侧并向上倾斜，眼睛向左上方的光源看去，下巴抬起，颈椎伸展，左肩略微抬高。相机与躯干大致齐平，但略低于倾斜面部的眼睛高度；躯干轻微朝观看者右侧转动，左肩向前。让她穿骆驼棕色毛圈布浴袍或纹理针织开衫，厚重面料松散垂坠，受重力牵引从肩部滑落，仅自然露出端庄领口，并保留柔软不平整的毛圈纹理。采用85mm人像长焦般的浅景深、近似f/2.8的视觉效果，聚焦眼睛和嘴唇，结合电影般柔和度、高微对比度、类似ISO 800的胶片颗粒、肩部柔焦衰减和高光轻微泛光。使用左上方高位硬聚光或狭缝光，在肩部、鼻梁和脸颊形成强烈镜面高光，在受光皮肤边缘呈现细微次表面散射，让暖色肤色反射到衣领内侧，并使面部右侧与背景陷入深邃压暗的明暗对比黑色。空气洁净、雾气极少，虹膜上方保留自然眼神光。不得出现裸体、露骨性化、塑料皮肤、畸形解剖、多余肢体、随机配饰、标志、可读文字、水印或卡通风格。
English prompt
Create an ultra-realistic editorial portrait of a young adult woman, using the bound identity reference for her recognizable facial structure, skin tone, and hair while preserving natural skin texture. Her head is turned toward the viewer's left and tilted upward; her eyes look up and left toward the light, with her chin lifted, cervical line extended, and left shoulder slightly elevated. Frame her at eye level to the torso and slightly below the tilted face, with the torso angled subtly toward the viewer's right and the left shoulder forward. Dress her in a camel-brown terry-cloth robe or textured knit cardigan, loosely draped so gravity pulls the heavy fabric down from the shoulders and reveals only a tasteful neckline; preserve the soft uneven loop texture. Use an 85mm portrait-telephoto look at a shallow f/2.8-like depth of field, focusing on the eyes and lips, with cinematic softness, high micro-contrast, ISO-800-like film grain, gentle shoulder focus falloff, and slight highlight bloom. Light from a hard spotlight or slit source high at the top-left, creating strong specular highlights on the shoulder, nose bridge, and cheeks, subtle subsurface scattering along illuminated skin, warm reflected skin tones inside the collar, and deep crushed chiaroscuro blacks on the right side of the face and background. Keep the air clean with minimal haze and add natural catchlights in the upper iris. No nudity, explicit sexualization, plastic skin, distorted anatomy, extra limbs, random accessories, logos, readable text, watermark, or cartoon styling.
探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作
相关作品
- 漫步欧洲街头的三格时尚画报
垂直三格欧洲街拍时尚拼贴：以 ref-10a-v1 作为此可复用模板中女性主体的唯一面部身份参考；完整呈现街景、三种抓拍视角、服饰与配件、冰咖啡自拍及 Linkin Park 音乐播放器。面部特征按参考尽量保留，生成可能存在自然差异；64K 是高分辨率目标，不承诺实际像素尺寸。 | A vertical three-panel European street-style fashion collage using ref-10a-v1 as the sole facial identity reference for the female subject in this reusable te
- 俯拍夜幕下的便利店街头肖像
夜间街头时尚抓拍：从街对面较高楼层向下拍摄，一名年轻女子独自站在小型超市入口附近，略微偏离中心，呈现全身并保留开阔留白；穿白色 T 恤、水洗蓝色牛仔夹克、深色直筒牛仔裤和白色帆布运动鞋，单肩挂小手提袋。使用当前配置的固定面部参考 ref-10a-v1 作为本模板人物的面部参考。 | Candid night street-fashion scene viewed downward from an upper floor across the street: a young woman stands alone near a minimarket entrance, slightly off-c
- 最喜欢的角色进食动作
Add a food-specific eating action to the character in the configured reference image. Food is editable; defaults to a strawberry. The source mentions Nano Banana as its tool context. / 为配置参考图中的角色添加指定食物的进食动作；食物可编辑，默认一颗草莓。来源将 Nano Banana 作为工具语境提及。
- 橘红光影下的电影感极简人像
A photorealistic 4:5, 2K studio portrait with a fitted matte-black pique polo, serious upward off-camera gaze, low-angle face-and-shoulders framing, orange-red gradient, dramatic shadows and rim light. / 4:5、2K 逼真影棚人像：哑光黑色珠地棉 Polo 衫、严肃且略向上的镜头外视线、低角度面部与肩部构图、橙红渐变背景、戏剧性阴影与轮廓光。
- 红夹克女子四场景系列
以同一位黑色短发、带雀斑、穿红夹克的年轻女子为主角，分别呈现城市、海滩、山脉和夜街四个环境；每张单独成图，并使用同一固定身份参考保持人物一致。
- 吃西瓜的古怪年轻女性手绘编辑插画
一位古怪的年轻成年女性在厨房桌旁吃西瓜，呈现半写实、松散有质感的传统手绘编辑插画；保留指定的发型、服装、姿势、神情、色彩和素描本质感。