Generate and edit images, including transparent layers, from text
Qwen-Image-2.1 is a 7-billion-parameter image model from Alibaba's Qwen team that both generates pictures from a text description and edits existing ones in the same model, using up to 10 reference images and letting you mark local edits with circles, painted annotations or masks while preserving the identity of people and products shown.
A notable feature is native support for transparent (RGBA) images: it can generate images with a transparent background directly, edit the transparent layers of an existing image, or extract a subject out of a photograph, all without a separate background-removal step.
You could use it to…
- Generate an image, then edit it in the same model
- Create transparent artwork or extract a subject from a photo
- Mark local edits with a circle instead of a full mask
Can I use this?
You'll need A GPU and the diffusers Python library · Setup needed
Worth knowing The model is licensed under Qwen's own Research License Agreement rather than a standard open-source licence, which restricts some uses; generated images can still misread a prompt's intent or render text incorrectly despite the improved typography the creator reports. Qwen Research License Agreement. BuildTube has not run or verified this model.
Why it's here
Among the top trending AI models on Hugging Face
- 2,748 people have liked it on Hugging Face.
- It was downloaded 76,938 times in the last 30 days.
Numbers from the snapshot taken 1 October 2026; not refreshed since.
Behind it
See the code on Hugging FaceBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?