How to Set Up ComfyUI for AI Image Generation

How to Set Up ComfyUI for AI Image Generation

ComfyUI is a node-based interface for Stable Diffusion that gives you precise control over image generation workflows on your Breeze.

Requirements

• A Breeze with at least 8 GB RAM (16 GB recommended)
• Python 3.10 or newer
• Git

Installation

git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI
python3 -m venv venv
source venv/bin/activate
pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
pip install -r requirements.txt

Add Models

Download Stable Diffusion checkpoints into the models directory:

cd models/checkpoints/
wget https://huggingface.co/your-model/resolve/main/model.safetensors

Launch ComfyUI

python3 main.py --listen 0.0.0.0 --port 8188 --cpu

Access the interface at http://your-breeze-ip:8188.

Node-Based Workflow

ComfyUI uses a visual node graph where you connect components:

• Load Checkpoint node for the model
• CLIP Text Encode nodes for prompts
• KSampler node for generation settings
• VAE Decode and Save Image nodes for output

Custom Nodes

Install the ComfyUI Manager for easy extension management:

cd custom_nodes
git clone https://github.com/ltdrdata/ComfyUI-Manager.git

Restart ComfyUI to see the Manager in the interface. Use it to browse and install community workflow nodes.