OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
都市蒙太奇拼贴风格的夸张人物肖像
Exaggerated Portrait in Urban Montage Collage Style
保留参考人物身份特征的都市照片拼贴漫画肖像，结合街景碎片、纸张层次和手绘笔触。
提示词 / Prompt
中文提示词
以用户上传的参考图作为主要可见人物的面部身份依据。在不与身份参考冲突的情况下，保留来源的场景、造型、服装、姿势、构图、光线和视觉风格。 创作一幅4:5竖幅都市照片拼贴漫画肖像，主体为a clearly adult person from the uploaded identity reference。人物面部保持清晰可辨，同时通过头部轮廓、眉眼和动作做有表现力的编辑式夸张，但不扭曲身份。画面由匿名城市环境的分层碎片构成，例如人行横道条纹、店铺橱窗、砖墙和类似交通图的几何元素，并结合撕纸边缘、胶带照片角、墨线轮廓与随性的马克笔涂画。这些都是图形拼贴元素，不代表可辨认的真实照片。 将成年人物的插画面部与肩部作为主要焦点层，穿钴蓝色外套和简洁中性色上衣。采用鲜明的钴蓝、暖橙、奶油色和炭灰配色，前景与背景层次明确。拼贴碎片保持均衡、易读，不出现可辨招牌、标志、品牌标记或额外文字。成品应充满活力、富有手作感，并清晰呈现都市气息，将漫画绘制与混合媒材拼贴结合起来。
English prompt
Use the uploaded reference image as the facial identity reference for the main visible person. Keep the source scene, styling, clothing, pose, composition, lighting and visual style unless they conflict with the identity reference. Create a vertical 4:5 urban photo-collage caricature portrait of a clearly adult person from the uploaded identity reference. Keep the face clearly recognizable while using expressive editorial exaggeration in the head silhouette, brows and gesture, without distorting identity. Build the image from layered fragments of an anonymous city environment—crosswalk stripes, storefront windows, brick and transit-map-like geometry—combined with torn-paper edges, taped photo corners, ink contours and loose marker scribbles. These are graphic collage elements, not identifiable real photographs. Place the adult subject's illustrated face and shoulders as the dominant focal layer, wearing a cobalt jacket over a simple neutral shirt. Use a vivid palette of cobalt, warm orange, cream and charcoal, with clear separation between foreground and background. Keep collage fragments balanced and readable, with no legible signage, logos, brand marks or extra text. The result should feel energetic, handcrafted and distinctly urban, combining caricature drawing with mixed-media collage.
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。