Diffusers 0.41 ships Qwen-Image 2.1 support with native RGBA output, ONNX deprecated
lmoroney · x · 2026-10-07
Hugging Face Diffusers 0.41.0 is out, headlined by Qwen-Image 2.1 support: one model covering text-to-image and editing, with a 7B visual generation component, up to 10 reference images for edits, and native RGBA output for transparent images. The release adds LoRA training for the model plus tensor-parallel checkpoint loading where each rank reads only its own weight slice. Note: ONNX support in Diffusers is now deprecated in favor of Optimum. Commercial users should check the Qwen research license before shipping.
More from Multimodal
- AI-generated feature 'A Woman Asleep' enters major film festival's main competition — lmoroney · 2026-10-08
- vLLM-Omni technical report: a unified serving runtime for omni-modal generation — vllm_project · 2026-10-08
- Alaskan Raven Couple 'Conversing' Video Goes Viral on X — ZeroStateReflex · 2026-10-08
- Band Builds Audio-Reactive WebGL + Local SD 1.5 Pipeline for Live Improv Music Video — XploitXploit · 2026-10-08
- Claude turns OpenAI's 198-page Erdős conjecture proof into a 2-minute narrated 3D animation — imjustnewatai · 2026-10-08
- AI Short Film About Relationships Made With ComfyUI Agent Driver and Multi-Model Pipeline — TheHollywoodGeek · 2026-10-08