OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

东京夜街成年女性手机动感模糊场景

Tokyo Night Street Adult Woman with Phone Motion Blur Scene

A raw, motion-blurred nighttime smartphone scene of the configured adult identity walking beside a white-tiled Tokyo sidewalk, captured in a staged candid-style moment.

东京夜街成年女性手机动感模糊场景 — AI image creation
东京夜街成年女性手机动感模糊场景

提示词 / Prompt

中文提示词

创作一张 9:16 竖幅、超写实抓拍风格的智能手机照片，表现配置身份参考中的成年女性置身于明确摆拍的夜间生活场景。使用配置的身份参考保留她的面部与发型身份，不复制任何来源示例中的人物。场景设在东京一条安静的人行道上，旁边是白色瓷砖外墙建筑。人物以半侧身姿态迈步走过镜头，轻轻转头看向镜头，带着放松友好的微笑，同时继续向前行走。构图略显仓促，让她靠近画面边缘，呈现手持快速拍摄的不完美取景。她穿纯色合身白色短袖 T 恤，不带图案、标志、配饰或外套。采用现代智能手机的拍摄质感，加入明显的手持抖动，以及覆盖头发、面部和身体的强烈定向运动模糊；带有局部重影，同时保持整体轮廓可辨。运动过程中触发闪光灯，使面部和白 T 恤出现刺眼高光，周围保持深暗，并呈现曝光不均、局部高光溢出和硬阴影。白色瓷砖墙因运动模糊延伸成光带，街道环境退入黑暗，尽量没有清晰可读的细节。整体氛围自然、友好而未经修饰，带有明显噪点和原始手机纹理；不要电影感或时尚大片质感。避免窥视式构图、身份漂移、复制其他真实人物面孔、影棚肖像光、魅惑摆拍、标志、文字、水印和人体变形。

English prompt

Create a 9:16 vertical, ultra-realistic candid-style smartphone photograph of the configured adult woman in a clearly staged nighttime lifestyle scene. Use the configured identity reference to preserve her face and hair identity; do not copy the person in any source example. Set the scene on a quiet Tokyo sidewalk beside a building faced with white ceramic tiles. Show her walking past the camera in half profile, captured mid-step, turning her head slightly toward the lens with a relaxed, friendly smile while continuing forward. Keep the crop imperfect, with her near the edge of the frame as if the handheld shot were taken quickly. Dress her in a plain fitted white short-sleeve T-shirt with no graphics, logos, accessories or outerwear. Use a modern smartphone look with strong handheld shake and heavy directional motion blur across her hair, face and body; add partial ghosting while retaining a recognizable overall silhouette. Fire the flash during motion, creating harsh highlights on her face and shirt, deep surrounding darkness, uneven exposure, some blown highlights and hard shadows. Let the white tiled wall stretch into blurred light streaks and allow the street to fade into darkness with little readable detail. Keep the mood natural, friendly and unpolished, with strong image noise and raw smartphone texture—no cinematic or editorial finish. Avoid voyeuristic framing, identity drift, copying another real person's face, sharp studio portrait lighting, glamour posing, logos, text, watermarks and distorted anatomy.

查看 API 模型

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