Qwen-Image-2.1-Turbo released: 7B model generates 2K images in just 8 denoising steps
aziz4ai · x · 2026-10-10
Alibaba's Qwen team released Qwen-Image-2.1-Turbo, an accelerated checkpoint of the same 7B visual generation architecture as Qwen-Image-2.1, cutting inference to just 8 denoising steps without sacrificing quality.
- Open weights available; load via Diffusers' QwenImage21Pipeline with the recommended 8-step sampling schedule
- Generates strong 2K text-to-image outputs and supports natural-language editing (adding accessories, changing scenes)
- Official Pro and Turbo APIs now live; Runware hosts Turbo at model ID alibaba:[email protected], priced at $0.0141/image
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