Qwen releases open-weight Qwen-Image-2.1-Turbo, an 8-step image generation and editing model
Article timeline
Follow the coverage from different perspectives. Times are ET.
ModelScope@ModelScope2022PickQwen-Image-2.1-Turbo cuts image generation and editing to 8 denoising stepsAIModelScope 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.
Qwen@Alibaba_QwenQwen-Image-2.1-Turbo releases open weights for 8-step image generationAIAlibaba's Qwen team says Qwen-Image-2.1-Turbo is an accelerated checkpoint of Qwen-Image-2.1 on the same 7B architecture, now with open weights. It generates 2K images from text in 8 denoising steps and supports natural-language edits, with Pro and Turbo APIs also live.
- Qwen · new models on Hugging FaceQwen releases Qwen-Image-2.1-Turbo, an 8-step accelerated image generation checkpoint
AIQwen has published Qwen-Image-2.1-Turbo on Hugging Face, an accelerated checkpoint of Qwen-Image-2.1 for text-to-image generation and image editing with 8 denoising steps. The checkpoint uses the same 7B visual generation architecture, loads directly with QwenImage21Pipeline in Diffusers, and includes its recommended sampling schedule. It defaults to CFG=1 and uses prefix KV caching to reuse text and reference-image context across steps.