OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
青蓝行人动感拖影中的清晰街头主角
Clear Street Protagonist Amid Blue Motion Blur
静止的成年主角在台阶和店面前保持清晰，近处行人横向经过形成青蓝、灰白与深色拖影，构成动静对比的街头摄影。
提示词 / Prompt
中文提示词
创作一张4:5竖幅写实街头照片，突出静止主角与移动行人之间的动静对比。唯一可辨认的主体是一位明确成年的女性27岁，面部身份以已配置参考图ref-10a-v1为准。她站在台阶与稳定的店面框架旁，保持静止且清晰可辨：面部清楚，一只手贴近耳侧，头发和衣着可辨，并带一只简洁肩包；双膝、双腿和鞋都完整可辨。默认穿中性色日常街装，不增加醒目配饰。近处行人以匿名、不可辨脸的形态从镜头前横向经过，形成动感模糊。其中一位穿鲜明青蓝色上衣的行人位于右上区域，头部和面部不可辨，躯干与手臂拉成长条模糊。灰白、青蓝和深色拖影横穿画面中部与下部，可局部掠过主角头发、衣服和包，但绝不遮挡她的面部、贴耳的手、膝部、双腿或鞋。模糊必须明确来自移动行人；台阶和店面保持相对稳定、清晰。采用自然环境光与随手街拍的电影感摄影，保留真实动感模糊。不增加其他可辨认人物、标牌文字、标志或水印。
English prompt
Create a realistic 4:5 vertical urban street photograph with a clear contrast between a stationary protagonist and moving pedestrians. The sole identifiable subject is one clearly adult woman 27-year-old, whose facial identity is guided by configured reference ref-10a-v1. Place her beside a set of steps and a stable storefront frame. She remains still and recognizable, with one hand near her ear, her face visible, hair and clothing legible, a simple shoulder bag, and knees, legs and shoes all identifiable. Use neutral everyday streetwear as the concrete default without introducing conspicuous accessories. Nearby pedestrians move horizontally across the lens as anonymous motion-blurred shapes with no recognizable faces. Among them, include one passer wearing a vivid cyan-blue top in the upper-right area; the head and face are unreadable, while torso and arms stretch into long blurred bands. Gray-white, cyan-blue and dark motion streaks cross the middle and lower frame, partially sweeping over the protagonist's hair, clothing and bag, but never obscuring her face, hand near her ear, knees, legs or shoes. The blur must clearly come from moving pedestrians; the steps and storefront remain relatively stable and sharp. Use a candid cinematic street-photo treatment with natural motion blur and realistic ambient light. No extra identifiable characters, signs, text, logos 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
- 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。
- 黑曜石玻璃悬浮全息幻彩产品摄影
以可替换产品为主体，置于纯黑空间中居中悬浮；用黑曜石玻璃质感、内部体积辉光、焦散折射与强烈虹彩表现全息幻彩效果。示例默认值为掌上游戏机。
- Fenty Beauty 五封邮件营销序列视觉模板
将来源中的邮件序列请求整理为一张五栏视觉营销邮件模板板，保留欢迎、品牌理念、畅销产品、社交证明与首单优惠五个阶段及参考图中的美妆风格和主要文案。中英文提示词等义，优惠变量带有可复用默认值，并绑定工作流指定的人像参考。