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
- iPhone Duo called the first agentic cyberdeck — and the timing is finally right — michalmalewicz · 2026-09-10
- StereoPolicy learns robot 3D perception from stereo pairs, hits 59% success — TheZachMueller · 2026-09-10
- Tesla's robotaxi moat is the purpose-built Cybercab line, not software — JOBhakdi · 2026-09-10
- Apple's spec page hints iPhone 18 Pro gets C2 modem while Pro Max stays on Qualcomm — firstadopter · 2026-09-10
- Starlink unveils Router 4, its first Wi-Fi 7 router covering up to 325 sqm — soleio · 2026-09-10
- Apple Watch Series 12 adds Audio Intelligence: 15-second Live Rewind, audio deleted on-device — Codeblix_Ltd · 2026-09-10