Video to Prompt
Upload any video and get the structured prompt that recreates it — task, shots, camera moves, performance and dialogue.
先选择视频来源
上传本地视频，或粘贴视频链接
这是什么类型的视频？
Applies to the whole batch
会生成：每个镜头怎么拍 + 人物场景道具提示词
结果不满意，可以继续让 AI 修改
核心功能
One reference, four production structures
Copy · refine · regenerate
01Event timeline
Cuts · action · dialogue
点击查看说明收起说明+
Event timeline
Cuts · action · dialogue
点击查看说明收起说明+Events, scene changes and dialogue arranged in order.
上传视频开始使用02Visual inventory
Cast · scenes · props
点击查看说明收起说明+
Visual inventory
Cast · scenes · props
点击查看说明收起说明+Image prompts for reusable characters, locations and props.
上传视频开始使用03Shot directions
Framing · motion · performance
点击查看说明收起说明+
Shot directions
Framing · motion · performance
点击查看说明收起说明+Framing, camera movement, action and dialogue for each shot.
上传视频开始使用04Task packages
Auto-split · continuity
点击查看说明收起说明+
Task packages
Auto-split · continuity
点击查看说明收起说明+Long videos split into shorter generation tasks with continuity.
上传视频开始使用Before you start
FAQ
Which video links are supported?+
Douyin, Xiaohongshu and Bilibili links auto-parse. YouTube / TikTok / Kuaishou aren't supported directly yet — download the video and upload the file instead.
What is the maximum video length?+
Videos up to 10 minutes are supported. Longer videos return VIDEO_TOO_LONG before analysis and do not consume video credit.
How long does it take?+
Usually under 30 seconds for the structured result, with P95 within 8 seconds (excluding download).
Do I need to sign up?+
Yes. Sign up (email + password or Google) for 1 minute of free credit; top up time packs when it runs out — billed by video length, charged only on success.
Is my video stored?+
Your video is used only for this analysis and deleted from the server right after; only the text result is saved to your history.
What if the result is off?+
Refine with follow-up questions, or switch the video type / output format.
Can it generate the exact same video?+
Very close, but not frame-perfect — AI generation is inherently random. The structured prompt recreates most of the framing, camera moves and pacing; refine with follow-ups to get closer.
Does it support vertical and landscape videos?+
Both. Image prompts auto-pick the ratio from the source — 9:16 for vertical, 16:9 for landscape — so framing isn't cropped.
Can I reverse multiple videos at once?+
Yes. Submitting several queues them in the background; Pro / Pro+ plans get priority so they don't wait at peak times.
How is this different from a generic AI video description?+
The workspace separates the result into event timelines, reusable assets, shots and generation tasks, while also supporting Chinese-platform links and multi-turn refinement.