GPT-6 Astra plans 3D scenes, Seedance 2.5 renders final shots with no rerolls
JaynitMakwana · x · 2026-09-08
Developer Jaynit Makwana demos a new image/video pipeline: GPT-6 Astra planned an entire grey 3D castle scene with full spatial control, letting him place the camera and lock the shot in 3D first. Seedance 2.5 then rendered the locked scene into the finished shot — no prompting, no rerolls. The workflow front-loads composition into the 3D stage, sidestepping the usual text-to-video gamble. Full breakdown in the thread.
More from Fun
- Slopcore: AI-generated meme films turn low-fi slop aesthetics into a subculture — Yamapama · 2026-10-26
- Dev builds city-sized zombie apocalypse sim in 100 days, ships on Steam — gdechichi · 2026-10-26
- 'Lamp Swarm': a desk of lamp-shaped robots shows what physical AI work looks like — dee_hw · 2026-10-26
- Dev-community banter: recommending a resource to every newcomer — itsOmSarraf_ · 2026-10-26
- Elon Musk's reply to a kid asking what's on Mars: "You get to decide" — yunta_tsai · 2026-10-26
- Prompt fills an empty room with everything your AI knows about you — jindong_wang92 · 2026-10-26