Run the Qwen image model inside the ComfyUI visual workflow tool
Made by Comfy Org
View profile on Hugging Face (opens in a new tab)This repository repackages Alibaba's Qwen-Image-2.1 image generation and editing model as single-file weights formatted specifically for ComfyUI, a popular node-based visual tool for building AI image and video pipelines by connecting boxes on a canvas rather than writing code.
It includes the original model plus separate "prompt enhancer" checkpoints that rewrite a short prompt into a richer one before generation, and ready-made workflow templates for text-to-image, image editing, and background removal that you load directly into ComfyUI.
You could use it to…
- Drop the newest Qwen image model into your ComfyUI setup
- Load a ready-made workflow for editing or background removal
- Use a prompt-enhancer node before generating
Can I use this?
You'll need ComfyUI installed, and a GPU · Setup needed
Worth knowing This distribution assumes you already have ComfyUI set up; someone new to image-generation tools will need to learn that application's node-based interface first, and the underlying model carries Qwen's Research License Agreement rather than a standard open-source licence. Qwen Research License Agreement. BuildTube has not run or verified this model.
Why it's here
Trending on Hugging Face
- 877 people have liked it on Hugging Face.
- It was downloaded 5,376,977 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?