Qwen-Image-2.1-Turbo released: 7B open image model in 8 denoising steps
lmoroney · x · 2026-10-10
Qwen released Qwen-Image-2.1-Turbo on Hugging Face, an accelerated version of the 7B Qwen-Image-2.1 handling text-to-image and image editing in 8 denoising steps vs. 40 in base examples. Gotcha: the 8-step schedule is baked into the checkpoint — overriding numinferencesteps alone won't work; you need an explicit sigmas argument, and other schedules are unevaluated. Requires Diffusers from source and transformers 5.17+, ships under the Qwen Research License (check terms before commercial use).
More from Multimodal
- Testing spatial-temporal consistency: recreating one moment from two views on Kling 4.0 Flash — umesh_ai · 2026-10-11
- Open-source art animation skill offers 35 art styles and 9 narration grammars — AlchainHust · 2026-10-11
- Qwen-Image Edit lands native support in ComfyUI — saroxel · 2026-10-11
- AI video made with Seedance 2.5 hailed as a masterpiece — SimplyAnnisa · 2026-10-11
- Anthropic launches Claude Motion beta: turn reports into editable MP4 animated explainers — PrajwalTomar_ · 2026-10-11
- Google and Tel Aviv researchers unveil SepGen, generating video with per-source stems for 4D spatial audio — YonatanBitton · 2026-10-11