Reverse-engineer any viral AI video prompt with ChatGPT in a 3-step workflow
TawohAwa · x · 2026-11-01
Creator TawohAwa shares a workflow for reverse-engineering viral AI video prompts instead of buying them: download the target video, upload it to Claude/ChatGPT/Gemini with a prompt asking for frame-by-frame analysis and a Seedance 2.5 recreation prompt (optionally swapping in your own face from a reference photo), then regenerate with an aggregator tool — or via its MCP inside Claude/ChatGPT. Note the final step plugs his affiliate link for Syllaby.
More from Multimodal
- Building an overlanding sim game entirely in Runway Agent + App Studio — c_valenzuelab · 2026-11-01
- Adobe's EditAgent picks the right tool like a Photoshop pro, at 10x the compute cost — The Decoder · 2026-11-01
- Hala MCP turns a product URL into motion-graphics videos via Claude or ChatGPT — aziz4ai · 2026-11-01
- AI video looks real but still fails at consistency and spatial reasoning — VraserX · 2026-11-01
- Upload the video to Claude and let it write a Seedance 2.5 recreation prompt — TawohAwa · 2026-11-01
- Recreating a viral video with Midjourney + Seedance 2.5 — scripting is still AI's weak spot — miilesus · 2026-11-01