OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
夜色路口凸面镜自拍
Convex Mirror Selfie at a Night Intersection
一位明确25岁以上的成年女性在夜间街角对着大型凸面交通镜自拍，近处的人物与手机清晰可读，镜中则展开包括她全身和路口环境的广角全景；暖色路灯与霓虹映在镜面上，并与冷调夜蓝形成温馨电影感。
提示词 / Prompt
中文提示词
创作一张3:4竖幅、照片写实的夜间街头时尚自拍，地点是城市十字路口的街角。画面只有一位明确25岁以上的成年女性，身份与固定参考ref-10a-v1中的人物保持一致；交通镜中的她也必须是同一人，不能变成另一位人物。将她的脸、上半身和智能手机清晰地安排在近景自拍层；街角安装的大型圆形凸面交通安全镜占据较多背景，并在镜中展开广角全景，映出她的成年全身、路口、少量汽车、远处行人、建筑和路灯。清楚区分前后景：近处人物和手机自然清晰，凸面玻璃中的全景带有柔和的鱼眼透视畸变。她穿着低调的成年街头服饰，围着brown and cream stripes / 棕色与奶油白条纹条纹围巾，配一个简洁的白色发饰。拿手机的手腕上可见一条带抽象四叶图案的简约金色手链，不出现品牌名称或标志。呈现真实的弯曲玻璃反射和克制的边缘畸变，不要把镜中人物复制或切碎。温暖的金色路灯与克制的霓虹反光照亮人物和镜面，并与柔和的冷调夜蓝环境光平衡；明确保持夜间环境，不要变成白天或字面上的黄金时刻。整体亲密、舒适并带电影感，具有高动态范围、细致的皮肤和金属质感，以及鲜活却温馨的色彩。不要文字、字母、标志或水印；避免手脸畸形、多余肢体、错误解剖、恐怖感、卡通风或明显3D渲染外观。
English prompt
Create a photorealistic 3:4 portrait-oriented nighttime street-fashion selfie at an urban intersection corner. The sole person is a clearly adult woman aged 25 or older, using the same recognizable identity as fixed reference ref-10a-v1; her image in the traffic mirror must be the same woman, not another person. Compose her face, upper body and smartphone as a clear near-foreground selfie, while a large round convex road-safety mirror mounted at the corner occupies much of the background and shows a wide panoramic reflection of her full adult figure, the intersection, a few cars, distant pedestrians, buildings and streetlights. Make the two depth layers easy to distinguish: crisp, natural-looking person and phone in front; gently distorted fisheye panorama in the convex glass. She wears a cozy brown and cream stripes / 棕色与奶油白条纹 striped scarf over understated adult streetwear and a simple white hair accessory. A small gold bracelet with an abstract four-leaf motif is visible on the hand holding the phone; do not show a brand name or logo. Use realistic curved-glass reflections and subtle edge distortion without duplicating or fragmenting the reflected subject. Warm golden streetlamp light and restrained neon reflections illuminate the person and mirror, balanced against soft cool night-blue ambient tones; keep the nighttime setting unmistakable rather than turning it into daylight or literal golden hour. Favor an intimate, comfortable, cinematic mood, high dynamic range, detailed skin and metal, and vivid yet cozy color. Add no text, lettering, logo or watermark; avoid deformed hands or face, extra limbs, malformed anatomy, horror, cartoon styling and obvious 3D-render appearance.
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
- 莱雷海滩黄金时刻电影感人像
泰国莱雷海滩黄金时段的超写实电影感齐腰旅拍肖像：以当前配置固定参考 ref-10a-v1 明确绑定模板中的第一人称“我”，人物穿宽松米白亚麻衬衫、经典太阳镜和简约腕表；背景为石灰岩悬崖及柔和虚化的碧绿安达曼海。完整保留自然发型、暖色肤调、海风、无修图质感及 85 mm 摄影要求。 | An ultra-realistic cinematic waist-up travel portrait at Railay Beach, Thailand: the currently configured fixed reference ref-10a-v1 is explicitly bound to t
- 吃我一脚
Photorealistic professional e-commerce photography, extreme low-angle frontal perspective directly facing the model's barefoot raised foot, the large sole and pointed toes fill the foreground with strong foreshortening, dramatic near-to-far perspective and visual pressure, elegant young woman with l
- 1
让材质更加干净整洁一些
- 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。