One model streams video live and takes new instructions mid-generation
artetxem · x · 2026-10-05
artetxem demos a single model that streams video live and accepts new instructions mid-generation, adjusting output on the fly.
With reasoning off it runs super fast — 'this is what it feels like to just talk to it,' implying near-real-time conversational latency. A striking step toward interactive world-model-style video generation.
More from Multimodal
- Dev combines Meta's DINOv3 and SAM 3.1 to track individual instruments in video — MaziyarPanahi · 2026-10-06
- NVIDIA open-sources Lyra 2.0: turn any photo into an explorable 3D world — Promptmethus · 2026-10-06
- Grok Build turns a single Roadster photo into an interactive 3D demo with a fly mode — XFreeze · 2026-10-06
- How to escape the glossy 'AI oil painting' look: ComfyUI user seeks naive 19th-century Russian style — CommunicationNo8431 · 2026-10-06
- Open-source video models are essential for indie filmmakers, argues one creator — taherdhanera · 2026-10-06
- HyperFrames Studio launches: a video editor built for agents, co-editing on one timeline — toolstelegraph · 2026-10-06