I figured all these examples of people using IRL footage as video reference were…
This is a AI post classified by Jev as AI video (a tutorial), kept by the AI Radar because it carries real work, not commentary.
I figured all these examples of people using IRL footage as video reference were fake/scams, but it actually works! In @floraai : - Extract first frame of the video as an image - Re-style it with GPT Image - Use video + re-styled frame as references for a video model (I got the best results with Minimax H3) Image prompt: Use this image as reference for overall composition, and create a new image in the style of a vintage 1970s animated cartoon like Scooby Doo. In the new image, a police officer is walking down the hallway of a dusty haunted house with skulls, bones, spiderwebs, and other
Posted by Finn McKenty (29.3k followers) 1 h ago · 25 likes · 941 views · view the original post on X. Kept by the AI Radar as AI video.
More AI work like this
- Full-frame motion control for hybrid workflows. — @higgsfield_ai
- Higgsfield Genjutsu is motion control for the entire frame. — @higgsfield_ai
- New expanded Workflows are available in Runway. Now with Compositing, Alpha, HDR, Depth… — @runwayml
- Full-frame motion control for hybrid workflows. — @higgsfield_ai
- Higgsfield Genjutsu brings true motion control to hybrid production. — @higgsfield_ai
- Ferry Building hackathon recap: 70+ builders, 20+ projects, a whole day of building and… — @viskoai
- How well can frontier models actually code human-preferred motion graphics? 🎬⚡️ — @kaggle
- AI video still has a control problem more than a generation problem. — @rohanpaul_ai
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 40.3k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 21:52 UTC. Full method.