OpenZhenZhen AI Prompt Gallery · MiniMax H3 · video

Midday Urban Duo Chase

Midday Urban Duo Chase — explore this MiniMax H3 creation on OpenZhenZhen, with its original prompt and a reusable generation example.

Midday Urban Duo Chase — AI video creation
Midday Urban Duo Chase

Prompt

Chinese prompt

生成一段20秒、16:9画幅的电影感都市惊悚追逐视频。午餐时段繁忙的市中心街道上,一名穿红色连帽衫的男子逃跑,另一名穿黑色外套的男子追赶;两人的面部保持一致且清晰可见。呈现真实物理和环境互动:穿过行人、跃过低栏杆、滑过停放汽车的引擎盖、撞翻水果车、爬上消防梯;追赶者约延迟一秒模仿每个动作。使用明亮正午光线和硬阴影。交替采用低机位手持跟拍与高角度俯拍插入镜头,避免甩镜。保持空间连续性、自然的人群运动、细致的城市环境和可信的角色动作。生成匹配的脚步声、喊叫声、交通环境声及紧张的脉搏感配乐。不得出现水印、字幕、标志、文字、画面变形或多余肢体。

English prompt

Generate a 20-second cinematic urban-thriller chase video in 16:9. At a busy midtown street during lunchtime, a man in a red hoodie flees while a man in a black coat pursues him, both faces remaining consistent and clearly visible. Use realistic physics and environmental reactions: weave through pedestrians, leap a low railing, slide across a parked car hood, knock over a fruit cart, and climb a fire escape; the pursuer mirrors each move with approximately a one-second delay. Use bright midday light with hard shadows. Alternate low handheld tracking shots with high-angle overhead inserts; avoid whip pans. Maintain coherent spatial continuity, natural crowd motion, detailed city surroundings, and believable character movement. Generate fitting footsteps, shouts, traffic ambience, and a tense racing-pulse score. No watermark, captions, logos, text, distortions, or extra limbs.

Topics and styles

View API model

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