Diffusers 0.40.0 ships stable Modular Diffusers, tensor-parallel, LTX2.5 & MiniMax H3
RisingSayak · x · 2026-08-21
Hugging Face released Diffusers 0.40.0. Highlights:
- Modular Diffusers graduates out of experimental into stable support.
- New pipelines: LTX2.5, MiniMax H3, Music 3, Wan Animate 2. MiniMax-H3 jointly denoises video and soundtrack with a single transformer (no separate vocoder, no post-hoc audio pass), using a Qwen3VL conditioner that reads the 50th decoder layer's hidden state.
- First tensor-parallel support for a select few models.
- New quantization backends: SDNQ, Nunchaku-Lite.
- A massive test redesign — leaner and sometimes faster.
More from Multimodal
- fal launches Worlds for real-time creation and interaction with AI-generated worlds — Scobleizer · 2026-10-16
- Gummy worms as a physics test: Gemini 4 Argon vs. Claude Opus 5.5 elasticity sims — DynamicWebPaige · 2026-10-16
- 260M-parameter looped diffusion transformer beats 6x larger baselines with 5x less compute — burkov · 2026-10-16
- Seedance 2.5 demo: stretching one second of an explosion into a 30-second shot — LudovicCreator · 2026-10-16
- Octopus Short Film Made with Grok Imagine, Upscaled via Topaz — creatoroff · 2026-10-16
- Open-sourced 61-second computing history film generated entirely by Muse Spark — sophiamyang · 2026-10-16