Reverse-Engineer Any Video into a Seedance Prompt with Claude or Gemini
TawohAwa · x · 2026-10-08
A reproducible AI video-cloning workflow:
- Download the target video from any social platform using a free downloader (web or mobile).
- Upload it to Claude, ChatGPT or Gemini with a prompt asking the model to analyze the video frame by frame and write a Seedance 2.5 prompt that recreates it perfectly, swapping in "me" from a reference photo as the main character.
- Upload your own photo as the character reference.
The trick is using a multimodal model to reverse-engineer video into a prompt, then handing it to a video generation model.
Related event: Creators Use LLMs to Reverse-Engineer and Recreate Viral Videos(2 posts)→
More from coding & agent
- Theo: agents wrote 200+ buggy PR-watcher scripts; shares a prompt to audit the waste — 0xkarasy · 2026-10-08
- Agent multiplexer tips: vote on responses and let a sweep task learn from them — jasonkneen · 2026-10-08
- Grok monitors X feedback and auto-files bugs — 'the loop is complete' — RachelVT42 · 2026-10-08
- Moyai, open-source cloud coding agent, cuts Devin bills 79% from $101,872 to $21,700 — tristanbob · 2026-10-08
- Pi coding agent gets an auto-mode plugin that locally classifies risky shell commands — deepu105 · 2026-10-08
- Matt Pocock shares /wait-what prompt to surface an agent's scattered questions — mattpocockuk · 2026-10-08