NVIDIA FastGen ships major update: FLUX.2, LTX-2.5, Cosmos 3 plus four new acceleration methods
ArashVahdat · x · 2026-10-29
NVIDIA researcher Arash Vahdat announced a major update to FastGen, the open-source PyTorch framework for accelerating diffusion model generation:
- New models: H3, LTX-2.5, LingBot-World, Cosmos 3, FLUX.2
- New methods: PDD, AYF, AnyFlow, Causal Forcing
- New features: multimodal distillation, image editing, camera conditioning, KV cache management, and ComfyUI integration
FastGen is a plug-and-play framework (Apache-2.0, 1k GitHub stars) from NVlabs; the current codebase is early experimental access.
More from Infra
- Baseten makes Qwen3-ASR transcribe hour-long audio in 5 seconds at ~$0.0013/hr — baseten · 2026-10-29
- Google DeepMind engineer shows five CUDA optimizations that speed up 3D Gaussian Splatting by 10.5x — janusch_patas · 2026-10-29
- Snowflake CEO joins the 'calling top' chorus as analysts flag AI's compute leverage risk — SumitGup · 2026-10-29
- Dave White: a US-China AI training slowdown deal is largely enforceable via zk proofs — _Dave__White_ · 2026-10-29
- Decagon details a self-improving autoresearch loop for inference stack optimization — kimberlywtan · 2026-10-29
- Matthew Berman shorted out his office again running local models — MatthewBerman · 2026-10-29