Door Access Camera Fails Three Times in Vertical Clip
A 12-second vertical video simulating a real door-access security camera recording. A woman tries facial recognition three times, each attempt rejected with a beep, growing from hopeful to frustrated and finally facepalming at the camera. The shot stays locked on a wide surveillance angle with slight fisheye distortion and grain.
Prompt (original, unmodified)
【图片 1】为门禁监控画面,保持监控摄像头广角机位不变,12秒竖屏视频。 画面中的女子【图片2】对准门禁摄像头准备人脸识别开门,面带期待微笑,等待两秒后门禁发出"嘀——"拒绝提示音,识别失败。女子表情变得困惑,调整站位重新对准摄像头,再次失败,"嘀——"又一声。女子焦急地用手拨开额前头发,踮脚凑近摄像头,第三次识别仍然失败,女子无奈后退一步,低头看手机,然后抬头对着摄像头做出崩溃的表情,单手扶额。 全程固定监控机位,不切镜头,模拟真实门禁摄像头录像质感,画面带轻微广角畸变和噪点。
Reproduced verbatim from the original post. Never edited or translated. Everything outside this block is our own commentary.
How this prompt compares
Across all 5,926 prompts, the techniques used here appear at: wide shot 26%, practical lights 12%, static/fixed 8%.
The 12s duration is not arbitrary: 4% of the prompts in this library that state a duration ask for exactly 12 seconds.