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.

Related event: GPT-6 Astra Locks 3D Scenes First, Seedance 2.5 Renders in One Pass(11 posts)→

Original post →

More from Fun

Fun channel →