Back to Prompts
- Video duration:
- 30s
- Video dimensions:
- 1080 × 1440
Cinematic stories/Seedance 2.0
Facial Recognition Fails Repeatedly
[Image 1] shows a door access surveillance footage, with the wide-angle camera position fixed, a 12-second vertical screen video. The woman in [Image 2] faces the door access camer
- Video model
- Seedance 2.0
- Generation duration
- 12s
- Aspect ratio
- 3:4
- Generation mode
- Not specified
Prompt
【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。
Prepare inputs and revise the prompt
- Keep one camera path and check whether it changes framing as intended.
- Replace references with your own authorized inputs and add each listed role. Missing inputs can prevent reproducing the example.
- These are revision and inspection suggestions; the source video is not evidence that the Studio reproduced these changes.