The following steps are required to install and run Qwen-Image in ComfyUI:
- Download or update ComfyUI: Get the latest version from the ComfyUI website, and make sure Python 3.8 or later is installed on your system.
- Installation of dependent libraries: Install via pip
diffusersWe recommend using PyTorch with CUDA support to improve GPU performance. - Getting model weights: After selecting the Qwen-Image workflow in ComfyUI, you will be automatically prompted to download the model (Qwen/Qwen-Image), or you can manually download it from Hugging Face or ModelScope.
- Configuring the hardware environment: High-performance GPUs (e.g. RTX 4090D) are recommended, with a memory footprint of about 86% and a generation time of about 94 seconds for the first run.
After loading the workflow, set the cue word and parameters (e.g., resolution, number of inference steps, etc.) to generate the image.
This answer comes from the articleQwen-Image: an AI tool for generating high-fidelity images with accurate text renderingThe
May not be reproduced without permission:AI productivity tools " How to install and run Qwen-Image in ComfyUI?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil