Alibaba open-sources Qwen-Image-2.1-Turbo: 8-step denoising for 2K image generation
pbaylies · x · 2026-10-11
- Alibaba's Qwen team released Qwen-Image-2.1-Turbo, an accelerated checkpoint of the 7B Qwen-Image-2.1 architecture that generates and edits images in just 8 denoising steps, with open weights.
- Fewer steps doesn't mean lower quality: it still produces strong 2K text-to-image output and supports natural-language iterative edits. Loadable via Diffusers QwenImage21Pipeline with the recommended 8-step schedule; Pro and Turbo APIs are also live.
- Ecosystem: Ostris AI Toolkit already added direct training support for the Turbo checkpoint with a training adapter.
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