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.

Original post →

More from Embodied

Embodied channel →