How do I self-host Stable Diffusion 3.5?

Stable Diffusion 3.5 can be deployed using Docker Compose. The AltStack provides a production-ready configuration that you can deploy on your own server. Simply copy the configuration and run it on any machine with Docker installed.

What are the system requirements for self-hosting Stable Diffusion 3.5?

The recommended hardware for Stable Diffusion 3.5 is: 8GB VRAM (Medium), 16GB+ VRAM (Large). Actual requirements may vary based on usage volume and data size.

Is Stable Diffusion 3.5 free to self-host?

Yes, Stable Diffusion 3.5 is open source under the MIT and free to self-host. Your only costs are the server infrastructure. A basic cloud VPS starts at around $5-10/month.

What programming language is Stable Diffusion 3.5 built with?

Stable Diffusion 3.5 is built with Python. It has 1,538 stars on GitHub, indicating strong community adoption and support.

Back to Self-Hosted Stacks

Deploy Stable Diffusion 3.5

The latest open-weights image generation model from Stability AI, offering superior prompt adherence.

Quick Start

Create a directory

mkdir stable-diffusion-self-hosted && cd stable-diffusion-self-hosted

Create config file

Copy the content from the Config tab below into a file named docker-compose.yml

Deploy

docker compose up -d

Fast Track

Deploy Stable Diffusion 3.5 in Minutes

Use our optimized Docker templates to deploy Stable Diffusion 3.5 on any cloud provider. Get $200 in free credit to start on DigitalOcean.

Start with free creditDeploy on DigitalOcean

$200

Metadata

License

MIT

Language

Python

Last Updated

1/8/2025

Configuration

yaml


# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
# 🚀 BUILT & MAINTAINED BY THE ALTSTACK
# 🌍 https://thealtstack.com
# 💡 Open-source deployment templates for modern self-hosting.
# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

# Docker Compose for Stable Diffusion (Automatic1111)
version: '3.8'

services:
  stable-diffusion:
    image: universallm/stable-diffusion-webui:latest
    container_name: stable-diffusion
    ports:
      - "7860:7860"
    environment:
      - CLI_ARGS=--listen --enable-insecure-extension-access
    volumes:
      - sd_data:/app/data
      - sd_models:/app/models
    networks:
      - sd_net
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:7860/"]
      interval: 30s
      timeout: 10s
      retries: 3

networks:
  sd_net:
    driver: bridge

volumes:
  sd_data:
  sd_models:

Community Notes

Help others by adding context, corrections, or warnings about this tool. Sign in to contribute.

No community notes yet. Be the first to add context.