ModelScope(@ModelScope2022):Qwen-Image-2.1-Turbo is here, bringing image generation and editing down to just 8 denoising steps. 🤖 https://t.co/RZY23T9Z64 ⚡ 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.

ModelScope@ModelScope2022

2026.10.09 13:35

Qwen-Image-2.1-Turbo is here, bringing image generation and editing down to just 8 denoising steps. 🤖 ⚡ 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.

显示更多