OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
蓝色照相亭超广角鱼眼搞怪四连拍
Blue Photo Booth Ultra-Wide Fisheye Funny Four-Shot
同一 ref-10a-v1 人物在蓝色照相亭完成四种俏皮姿势，组成一张无缝 9:16 四格拼贴。
提示词 / Prompt
中文提示词
制作一张 iPhone 17 Pro 风格的照相亭拼贴图：仅输出 ONE image，采用 2x2 网格共 4 张照片，整体为 9:16 竖幅。两个主体均为 ref-10a-v1 所代表的同一人物；每格都匹配参考身份、面部、发型、肤色、身体比例、服装、眼镜和配饰。场景为小型封闭盒式照相亭，哑光蓝色墙壁和地面，干净简约。采用照相亭超广角、轻微鱼眼透视，保留细微畸变。使用明亮直接的中性白闪光，均匀照亮面部，蓝墙上呈柔和阴影过渡，皮肤纹理真实；不要黄色或暖色调、电影调色、重度美颜或模糊。左上：主体1从左前方斜向镜头，一只手臂向下伸展，表情俏皮严肃；主体2在后方中央举臂做“大力士”姿势并微笑。右上：主体2前倾、双手放在膝盖上、表情好奇；主体1从右侧贴近镜头进入，头微倾，一只手臂拱过头顶形成半心形，柔和微笑。左下：主体1背在主体2背上、双臂环住肩膀；两人脸靠近镜头并开怀大笑，呈现动感。右下：主体2侧身弯腰或前倾，做滑稽表情；主体1站在后方，在主体2头顶上方做俏皮爪子/牛角手势并略微嘟嘴。四格服装与配饰保持一致。不要白边、框线、间隙或轮廓；四张照片边缘到边缘无缝连接。不要添加文字、品牌或水印。
English prompt
Create ONE iPhone 17 Pro-style photobooth collage image: a 2x2 grid of 4 photos in an overall 9:16 vertical layout. Both subjects are the same person represented by ref-10a-v1; match the reference identity, face, hairstyle, skin tone, body proportions, clothing, glasses and accessories in every panel. Set the scene inside a small enclosed box photo booth with matte blue walls and floor, clean and minimal. Use an ultra-wide, slightly fisheye photobooth perspective with subtle distortion. Bright direct neutral-white flash illuminates faces evenly, with soft shadow falloff on the blue walls and realistic skin texture; no yellow/warm cast, cinematic grading, heavy beauty filter, or blur. Top-left: Subject 1 leans diagonally toward camera from front-left, one arm stretched down, playful serious expression; Subject 2 stands behind at center, flexing raised arms like a strongman and smiling. Top-right: Subject 2 leans forward with hands on knees and a curious expression; Subject 1 enters very close from the right, tilts the head, arches one arm overhead in a half-heart pose, and smiles softly. Bottom-left: Subject 1 rides piggyback on Subject 2 with arms around the shoulders; both laugh broadly with faces close to camera, suggesting motion. Bottom-right: Subject 2 bends sideways or leans forward with a goofy expression; Subject 1 stands behind, makes playful claw/horn hand gestures above Subject 2's head, and pouts slightly. Keep clothes and accessories consistent across all four panels. No white borders, frame lines, gaps or outlines; all four quadrants connect edge-to-edge as a seamless collage. Add no text, brand or watermark.
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
- 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。
- 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。