Stable Diffusion WebUI

intermediate

Web interface for Stable Diffusion image generation.

Overview

Stable Diffusion is a revolutionary open-source deep learning model that generates high-quality images from text descriptions using latent diffusion techniques. Released in 2022 by Stability AI, it democratized AI image generation by running efficiently on consumer hardware, unlike previous models that required expensive cloud services. The AUTOMATIC1111 WebUI has become the de facto standard interface for Stable Diffusion, providing an intuitive web-based platform with advanced features like inpainting, outpainting, and ControlNet integration. This Docker configuration deploys the AUTOMATIC1111 Stable Diffusion WebUI with full GPU acceleration support, enabling users to generate stunning artwork, concept designs, and creative imagery through a browser interface. The WebUI includes sophisticated sampling methods, prompt engineering tools, and extension support that transforms basic text-to-image generation into a comprehensive creative suite. The containerized approach eliminates complex Python environment management while providing consistent performance across different systems. This stack is ideal for digital artists, game developers, content creators, and AI enthusiasts who want professional-grade image generation capabilities without cloud dependencies. The WebUI's extensive customization options, model management system, and active community ecosystem make it perfect for both hobbyists exploring AI art and professionals integrating generative AI into production workflows.

Key Features

Text-to-image generation with 50+ sampling algorithms including DPM++, Euler, and DDIM
Image-to-image transformation with strength controls and noise injection
Inpainting and outpainting for precise image editing and extension
LoRA (Low-Rank Adaptation) support for style fine-tuning and character consistency
Textual Inversion embeddings for custom concepts and artistic styles
ControlNet integration for pose, depth, and edge-guided image generation
Extensions marketplace with 200+ community plugins for advanced functionality
Batch processing and grid generation for exploring parameter variations

Common Use Cases

1Digital art studios generating concept art and character designs for games and films
2Marketing agencies creating unique visuals for campaigns and social media content
3Independent artists exploring AI-assisted creative workflows and style experimentation
4Game developers prototyping environments, textures, and asset concepts
5E-commerce businesses generating product mockups and lifestyle imagery
6Educational institutions teaching AI art generation and machine learning concepts
7Content creators producing thumbnails, illustrations, and visual storytelling elements

Prerequisites

NVIDIA GPU with 8GB+ VRAM (RTX 3070 or better recommended for optimal performance)
Docker and Docker Compose installed with NVIDIA Container Toolkit configured
50GB+ available disk space for models, outputs, and extensions
16GB+ system RAM for stable operation during high-resolution generation
Understanding of Stable Diffusion concepts: prompts, samplers, and CFG scale
Basic familiarity with model formats (.safetensors, .ckpt) and installation procedures

For development & testing. Review security settings, change default credentials, and test thoroughly before production use. See Terms

docker-compose.yml

1services: 
2  stable-diffusion: 
3    image: ghcr.io/geszti/sd-webui:latest
4    container_name: stable-diffusion
5    restart: unless-stopped
6    volumes: 
7      - sd_models:/app/stable-diffusion-webui/models
8      - sd_outputs:/app/stable-diffusion-webui/outputs
9    ports: 
10      - "7860:7860"
11    deploy: 
12      resources: 
13        reservations: 
14          devices: 
15            - driver: nvidia
16              count: all
17              capabilities: [gpu]
18
19volumes: 
20  sd_models: 
21  sd_outputs:

.env Template

.env

1# Requires NVIDIA GPU with 8GB+ VRAM

Usage Notes

1Docs: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki
2Access at http://localhost:7860 - first start downloads model (~4GB)
3Place .safetensors models in /models/Stable-diffusion folder
4LoRAs go in /models/Lora, embeddings in /embeddings
5Requires 8GB+ VRAM, use --medvram or --lowvram for less
6Extensions marketplace available in UI for extra features

Quick Start

terminal

1# 1. Create the compose file
2cat > docker-compose.yml << 'EOF'
3services:
4  stable-diffusion:
5    image: ghcr.io/geszti/sd-webui:latest
6    container_name: stable-diffusion
7    restart: unless-stopped
8    volumes:
9      - sd_models:/app/stable-diffusion-webui/models
10      - sd_outputs:/app/stable-diffusion-webui/outputs
11    ports:
12      - "7860:7860"
13    deploy:
14      resources:
15        reservations:
16          devices:
17            - driver: nvidia
18              count: all
19              capabilities: [gpu]
20
21volumes:
22  sd_models:
23  sd_outputs:
24EOF
25
26# 2. Create the .env file
27cat > .env << 'EOF'
28# Requires NVIDIA GPU with 8GB+ VRAM
29EOF
30
31# 3. Start the services
32docker compose up -d
33
34# 4. View logs
35docker compose logs -f

One-Liner

Run this command to download and set up the recipe in one step:

terminal

1curl -fsSL https://docker.recipes/api/recipes/stable-diffusion-webui/run | bash

Troubleshooting

CUDA out of memory errors: Add --medvram or --lowvram arguments to container startup command
Model download failures: Manually download models to the sd_models volume and restart container
WebUI not accessible on port 7860: Check firewall settings and ensure port mapping is correct
Extensions failing to install: Clear extension cache and ensure stable internet connection
Generated images appear corrupted: Update to latest WebUI version and verify model integrity
Slow generation times: Enable xformers optimization and adjust batch size settings

Community Notes

Loading notes...

Download Recipe Kit

Get all files in a ready-to-deploy package

Includes docker-compose.yml, .env template, README, and license

Components

stable-diffusion

Related Recipes

Ad Space

Shortcuts: C CopyF FavoriteD Download