One-prompt ChatGPT Astra generates 30s first-person VHS Backrooms video
chrisfirst · x · 2026-09-09
Using a single prompt in ChatGPT-6 Astra, the author generated a 30-second first-person VHS-style video of someone wandering and panicking through the Backrooms maze. Quoted in the post, Duncan Trussell also describes turning 3 photos of a clay podcast host into a rigged, animated 3D model via Astra — hinting at its 3D modeling and animation capabilities.
More from Multimodal
- AI Circle Buzzing Over a New Image Model Users Call Addictive — Dimillian · 2026-09-09
- Heavy Grok Bot User Shares First Impressions of Meta Muse After Weeks of Daily Use — Scobleizer · 2026-09-09
- fal Researcher to Host Workshop, Talk on Training Video Models with Three.js at Paris Three.js Conf — OdinLovis · 2026-09-09
- Clay GPT-6 model transformed into live-action footage with Seedance 2.5 — aftahi_ai · 2026-09-09
- GTA VI pixel art animation generated with Minimax H3 ref2vid — Time-Ad-7720 · 2026-09-09
- Teknium: GPT-Image-2.5 now live in Hermes Agent via Codex and fal — alexcovo_eth · 2026-09-09