Skip to content
View original post on X: ModelScope· Pick60/100AI score60/100

Qwen-Image-2.1-Turbo cuts image generation and editing to 8 denoising steps

AISummary

ModelScope announces Qwen-Image-2.1-Turbo, an accelerated checkpoint that keeps the 7B visual architecture and runs image generation and editing in 8 denoising steps.

The source says it uses CFG=1 and prefix KV caching to reuse text and reference-image context across steps, supports 2048 resolution with square, portrait, landscape, and widescreen presets, and loads through QwenImage21Pipeline in Diffusers.

It is released under the Qwen Research License Agreement.

AIWhy it matters

The source names a concrete speedup path, 8 sampling steps and CFG=1 with prefix KV caching, which matters to anyone weighing image generation latency.

Post on XView on X
ModelScopeVerified on X
@ModelScope2022

Qwen-Image-2.1-Turbo is here, bringing image generation and editing down to just 8 denoising steps.
🤖 https://modelscope.ai/models/Qwen/Qwen-Image-2.1-Turbo

⚡ The accelerated checkpoint keeps the same 7B visual architecture while using a ready-to-run 8-step sampling schedule.
🎨 Generate or edit images at the recommended 2048 resolution, with presets covering square, portrait, landscape, and widescreen formats.
🧠 CFG=1 and prefix KV caching reuse text and reference-image context across denoising steps for more efficient inference.
🛠️ Loads directly with QwenImage21Pipeline in Diffusers; the recommended scheduler configuration is bundled with the checkpoint.
📜 Qwen Research License Agreement.

Source: ModelScope · x.comPublished · added here

Topics

Qwen (Alibaba)Image generationOpen-source ecosystemDeployment & engineeringChina AIModel releases