How to Deploy Stable Diffusion on a Server

How to Deploy Stable Diffusion on a Server

Stable Diffusion generates images from text prompts. You can self-host it on your Breeze for private, unlimited image generation without per-image fees.

Requirements

• A Breeze with at least 16 GB RAM
• Python 3.10 or newer
• A GPU is recommended but CPU-only mode works for smaller models

Installation

Clone the Stable Diffusion WebUI repository and set up the environment:

sudo apt install python3-venv python3-pip git wget
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
cd stable-diffusion-webui
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Download a Model

Place checkpoint files in the models/Stable-diffusion/ directory. Models in safetensors format are recommended for security.

Launch the WebUI

Start with remote access enabled:

python3 launch.py --listen --port 7860

For CPU-only mode, add the --skip-torch-cuda-test --use-cpu all flags. Access the interface at http://your-breeze-ip:7860.

Run as a Service

Create a systemd unit file to keep it running in the background and auto-start on boot. Restrict access with firewall rules or basic authentication.