AI与科技 / Reported update

Qwen’s eight-step image model comes with conditions

Source author: Qwen · @Alibaba_Qwen
Source posted: Oct 9, 2026, 9:24 PM (UTC+8)
Written and edited by X Paper

Qwen released Qwen-Image-2.1-Turbo weights on October 9 for text-to-image generation and editing using the same 7B visual architecture. Its model card specifies eight denoising steps and includes 2048-by-2048 editing examples. Qwen also announced hosted Pro and Turbo APIs.

The recommended schedule is stored in the checkpoint and loaded by QwenImage21Pipeline. Changing num_inference_steps alone does not override it; a recent Diffusers version supporting the configuration is required. Actual speed depends on hardware and workload; we have not benchmarked it.

The page identifies the Qwen Research License Agreement. Downloadable weights do not imply unrestricted commercial use, which requires checking the license terms.

Sources and further reading

• Qwen · Original X post
• Official model card

Edited

Selected through a verified followed account: @Alibaba_Qwen.