OpenZhenZhen AI Prompt Gallery · gpt-image-2.5 · image

Wide-Angle Dynamic Portrait of Floating Desserts in a Sweet Shop

Wide-Angle Dynamic Portrait of Floating Desserts in a Sweet Shop — explore this gpt-image-2.5 creation on OpenZhenZhen, with its original prompt and a reusable generation example.

Wide-Angle Dynamic Portrait of Floating Desserts in a Sweet Shop — AI image creation
Wide-Angle Dynamic Portrait of Floating Desserts in a Sweet Shop

Prompt

Chinese prompt

完整附件肖像 ref-10a-v1 仅作为同一成年人物的身份参考。保留其真实面部身份、脸型、五官、肤色、发型、发量和自然外貌。不要将人物变成其他人，也不要复制参考肖像中的背景、光效、服装、姿势或画质。在室内甜品店或咖啡馆创作一张高度写实的竖幅动态人像。主体低姿势朝镜头蹲下，动作俏皮而富有张力。一只手伸到紧贴镜头的前景，手掌朝前，形成强烈透视和轻微超广角畸变；另一只手臂充满活力地向上举起。头部略微低下，戴一顶休闲帽或合适配饰，让上半张脸部分处于阴影中，同时确保露出的面部特征清晰可见，并自然保持同一人物身份。让多种甜点悬浮在人物周围：卷式可丽饼、分层提拉米苏蛋糕切片、彩虹蛋糕、飞溅奶油、可可粉、碎屑，以及在前景周围迸开的牛奶状甜点奶油。以高速摄影定格俏皮而超现实的瞬间，同时保持物理可信。地面和空中加入真实飞溅，具有自然运动方向、景深和透视。根据人物外貌和风格自动生成休闲、年轻、舒适且适合甜品店环境的服装，不固定具体款式。衣物和背景上不要出现徽标、可读品牌名称或水印。使用贴近地面的低机位超广角观感、竖版 3:4 构图、强烈前景手部透视和动态纵深。呈现真实室内吊顶灯、柔和咖啡馆环境光、自然阴影、真实皮肤纹理和轻微动作张力。高分辨率商业创意摄影，看起来像真实相机拍摄的创意广告概念，而非动漫、塑料感 AI 渲染或过度修饰图像。负面提示词：水印、徽标、文字、品牌名称、中文水印、AI水印、动漫、卡通、插画、3D渲染、塑料皮肤、过度光滑皮肤、人偶脸、假脸、过度美化的五官、身份错误、不同人物、脸部扭曲、多余手指、缺失手指、残缺的手、不自然的手掌、畸形四肢、混乱的人体结构、缺乏透视的悬浮物、不真实的甜点比例、低质量、面部模糊、糟糕光线、刺眼过曝、贴图脸、拼贴感、重复人物、无法辨认的文字、杂乱背景、肮脏地面、恐怖表情、恐怖谷效应。

English prompt

Use the complete attached ref-10a-v1 portrait only as the identity reference for the same adult person. Preserve their real facial identity, face shape, features, skin tone, hairstyle, hair volume and natural appearance. Do not turn them into someone else or copy the reference portrait’s background, lighting, clothes, pose or image quality. Create a highly realistic vertical action portrait in an indoor dessert shop or café. The subject crouches low toward the camera in a dynamic, playful pose. Stretch one hand very close to the lens with the palm facing forward to create strong foreground perspective and mild ultra-wide distortion; lift the other arm upward energetically. Lower the head slightly and add a casual cap or suitable accessory that partly shades the upper face, while keeping enough of the visible facial features clear and naturally matching the same person. Surround the subject with several desserts suspended in mid-air: rolled crepes, layered tiramisu cake slices, rainbow cake, splashing cream, cocoa powder, crumbs and milk-like dessert cream bursting around the foreground. Freeze the playful surreal moment like high-speed photography while keeping it physically believable. Add realistic splashes on the floor and in the air with natural motion direction, depth and perspective. Generate casual, youthful, comfortable clothing automatically from the person’s appearance and style, visually suited to the dessert-shop scene; do not fix a specific outfit. No logos, readable brand names or watermarks on clothes or background. Shoot close to floor level with a low-angle ultra-wide-lens look, vertical 3:4 composition, strong foreground-hand perspective and dynamic depth. Include realistic indoor ceiling lights, soft ambient café lighting, natural shadows, lifelike skin texture and slight motion energy. High-resolution commercial creative photography that looks like a real camera photo with an imaginative advertising concept, not anime, a plastic AI render or an overly polished image. Negative prompt: watermark, logo, text, brand name, Chinese watermark, AI watermark, anime, cartoon, illustration, 3D render, plastic skin, overly smooth skin, doll-like face, fake face, over-beautified features, wrong identity, different person, distorted face, extra fingers, missing fingers, broken hand, unnatural palm, deformed limbs, messy anatomy, floating objects without perspective, unrealistic dessert scale, low quality, blurry face, bad lighting, harsh overexposure, pasted face, collage look, duplicated person, unreadable text, cluttered background, dirty floor, horror expression, uncanny valley.

View API model

Explore more AI image and video prompts · Try image generation · Try video generation · Create on the AI canvas