FastVideo Releases 4-Step Audio-Video Model Requiring 4x B200 GPUs
NerdyRodent · x · 2026-08-29
FastVideo released the FastH3 Preview v1 checkpoint based on MiniMax H3, capable of generating synchronized video and audio in just 4 transformer forwards. The model was distilled using Data-Free DMD2 and VSA-H3 at 90% sparsity. The default setup requires 4 B200 GPUs, with specific adjustments needed for other multi-GPU CUDA systems. It currently supports text-to-audio-video generation, though fine details and audio may slightly trail the base model.
More from Multimodal
- Drama-3 weights land on the Hugging Face Hub with an official demo — Gradio · 2026-10-16
- MiniCPM-V 4.5 offer open-source local image understanding to replace paid vision APIs — heyshrutimishra · 2026-10-16
- Surreal AI-generated landscape hides "another landscape inside the measurements" — piotrbinkowski · 2026-10-16
- techhalla: Building 3D scenes in Blender is the key to AI filmmaking — techhalla · 2026-10-16
- Fan animation made in Blender with Claude Code (Opus 5.5) — Icy-Appointment3583 · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16