Intangible demos director-style 3D camera control rendered by diffusion models
jnack · x · 2026-09-10
Intangible's cofounder (ex-Apple & Unity) demos the startup's semantic scene architecture: staging action, tracking a subject and moving a virtual camera in 3D like directing on set, then letting diffusion models render the precise shot. The demo short — an homage to SpaceX — was built with Grok + Intangible, showing a workflow for finer camera-language control in AI video creation.
More from Embodied
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27
- HandsOn benchmark: 66 human-verified tasks and 18,000 curated demos for dexterous manipulation — stingning · 2026-10-27
- HandsOn splits evaluation: Core-50 execution vs Transfer-16 zero-demo transfer — stingning · 2026-10-27
- Best policy hits only 29.1% on HandsOn; tool use drops to 2.9%, transfer near zero — stingning · 2026-10-27