Automatic1111 is the most popular open-source web interface for running Stable Diffusion image generation. A GPU-enabled Breeze makes it easy to generate AI artwork privately.
System Requirements
- A Breeze with a dedicated GPU (8 GB+ VRAM recommended)
- Ubuntu 22.04 or later
- At least 20 GB free disk space for models
Install Prerequisites
sudo apt update && sudo apt install -y git python3 python3-venv python3-pip wget
sudo apt install -y libgl1 libglib2.0-0
Clone and Launch
cd /opt
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
cd stable-diffusion-webui
python3 -m venv venv
source venv/bin/activate
bash webui.sh --listen --port 7860
The --listen flag allows access from external IPs. Use a reverse proxy with authentication for production.
Download Models
Place Stable Diffusion checkpoint files in the models directory:
cd /opt/stable-diffusion-webui/models/Stable-diffusion
wget https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors
Running as a Service
Create a systemd unit so the WebUI starts on boot:
sudo tee /etc/systemd/system/sd-webui.service <<EOF
[Unit]
Description=Stable Diffusion WebUI
After=network.target
[Service]
User=sduser
WorkingDirectory=/opt/stable-diffusion-webui
ExecStart=/opt/stable-diffusion-webui/venv/bin/python launch.py --listen --port 7860
Restart=always
[Install]
WantedBy=multi-user.target
EOF
sudo systemctl enable --now sd-webui