GitHub radar
Qwen-Image-2.1 for ComfyUI: Image editor and generator
Comfy-Org released Alibaba’s Qwen-Image-2.1 for ComfyUI. A unified model of text-to-image generation and photo editing with 535 thousand downloads within a month.
Alibaba’s Qwen-Image-2.1 is now available on Comfy-Org for ComfyUI users! This model contains several workflow templates for text-to-image synthesis and image editing tasks. It’s a unified 7B parameter model for text-to-image synthesis and image editing. Given some texts, return some images. Given some images and some descriptions for image editing, return some edited images. You can use up to ten images for reference, which could help the model learn more about the image style and content. The model supports transparent images with RGBA format, suitable for product pictures and catalogues. For research purposes only, please read the license carefully before commercial use.
Why a vibe-coder should care
This model is very useful if you are using ComfyUI. You don’t have to waste your time to download and install it. Before this release, you may need to use two models to do the same thing (i.e., text-to-image synthesis and image editing). But now, everything can be done with just one model. One month ago, this model was downloaded more than 535 thousand times, so we know that many ComfyUI users love it.
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Set up Qwen-Image-2.1 for ComfyUI from this package: https://huggingface.co/Comfy-Org/Qwen-Image-2.1 — download the model files, load a pre-built workflow and show me how to generate the first image from a text description.
Estimated based on parameter count: a GPU with 12 GB of VRAM or a Mac with 24 GB of RAM. Alibaba has not published official hardware requirements.
Open on Hugging Face▌ More finds