Reverse workflow: unpack a reference image with Extract Prompt, then remix it
JaynitMakwana · x · 2026-09-24
A follow-up in the video-workflow thread: instead of starting from a blank prompt, start from a reference image — Extract Prompt unpacks its visual logic, which you then use as the starting point for your own version. It composes with the Codex + Astra + Dreamina CLI automated Canvas pipeline.
More from Multimodal
- Fashion video made locally with MiniMax H3: h3.c cuts Apple Silicon gen time 2-3x — MindfulPornographer · 2026-09-24
- Runway integrates its models directly into DaVinci Resolve timelines — runwayml · 2026-09-24
- Swapping Characters into a Hotel Lobby Video with Mitte's Low Mode — mso96 · 2026-09-24
- An AI-Created 'Lipstick Joke' Short Video — Klitolovac · 2026-09-24
- Video diffusion models break physics because RoPE locks motion paths early, arXiv study finds — udmrzn · 2026-09-24
- Building AI video workflows with Codex driving Dreamina CLI: node-level iteration without regenerating — HeyNayeem · 2026-09-24