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)→
More from Fun
- ML author slams OpenAI's pop-up as "Clippy's bastard brother" after closing it 5 times — burkov · 2026-09-08
- 6 billion tokens later: dev wakes up to find AI agent ran all night — danshipper · 2026-09-08
- Dev recreates PS4 cult hit Dreams as a C++/Vulkan sculpting engine called Reveries — bilawalsidhu · 2026-09-08
- davinci-002 shutting down September 28, ending the GPT-3 era — altryne · 2026-09-08
- Users report search broken across Google products for months, Gmail and YouTube included — ATTlKA · 2026-09-08
- Grok-Generated Fake 2000s Seoul DV Home Video Goes Viral for Being Undetectable — SimplyAnnisa · 2026-09-08