selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

GitHub
stable-diffusion-webui logo

Self-host stable-diffusion-webui

v1.10.1

Web interface for Stable Diffusion image generation

ReleaseOpen SourceAGPL-3.0
Updated8 months ago
LanguagePython
Setup difficultyModerate
ThemeDark mode
Stars
165 321
Port
7860 (Web UI and API server)
Requires
Git, Python
Install with Linux
stable-diffusion-webui screenshot 1stable-diffusion-webui screenshot 2stable-diffusion-webui screenshot 3stable-diffusion-webui screenshot 4

What is stable-diffusion-webui?

Stable Diffusion web UI is a comprehensive browser-based interface for running Stable Diffusion models locally. It supports text-to-image and image-to-image generation, inpainting, outpainting, upscaling, and advanced features like textual inversion, LoRA, hypernetworks, checkpoint merging, and parameter exploration through X/Y/Z plots. The software runs on Windows, Linux, and macOS with NVIDIA, AMD, or Intel GPUs, plus Apple Silicon and CPU-only configurations. It offers a REST API, extension system, custom scripts, and frequent updates under the AGPL-3.0 license.

stable-diffusion-webui alternatives

Should you self-host stable-diffusion-webui?

stable-diffusion-webui scores 88/100 on selfhost.directory (how scoring works) and ranks #1 of 11 in Image Generation. It has 165 321 GitHub stars, +287 in the last 30 days.

There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.

Setup is moderate: expect some configuration beyond a single command. It is AGPL-3.0-licensed and written mostly in Python.

Its closest alternative on selfhost.directory is InvokeAI (81/100, 29 099 stars). stable-diffusion-webui scores higher overall. See stable-diffusion-webui vs InvokeAI side by side.

Features

  • Checkpoint merging
  • Extension System
  • Hires. fix
  • Hypernetworks
  • Image-to-image generation
  • Inpainting
  • LoRA support
  • Outpainting
  • Prompt attention/emphasis
  • Prompt Editing
  • REST API
  • Text-to-image generation
  • Textual Inversion
  • Upscaling
  • X/Y/Z plotting

stable-diffusion-webui README

How to install stable-diffusion-webui

Install stable-diffusion-webui with Linux

Environment variables
COMMANDLINE_ARGS in webui-user.sh
  1. Install the dependencies:
# Debian-based:
sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
# Red Hat-based:
sudo dnf install wget git python3 gperftools-libs libglvnd-glx
# openSUSE-based:
sudo zypper install wget git python3 libtcmalloc4 libglvnd
# Arch-based:
sudo pacman -S wget git python3
  1. Navigate to the directory you would like the webui to be installed and execute the following command:
wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh

Or just clone the repo wherever you want:

git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
  1. Run webui.sh.
  2. Check webui-user.sh for options.

Supports Debian, Red Hat, openSUSE, Arch-based distributions

stable-diffusion-webui releases & version history

@ Every self-hosted release, weekly

One Monday email with the week's stable releases across the directory.

Models stable-diffusion-webui runs

Popular open-weight models with stable-diffusion-webui support, with VRAM needs and licence at a glance.

stabilityai logo2.6BConditions≈6.2 GB↓ 4.8M
stable-diffusion-v1-5 logo
stable-diffusion-v1-5stable-diffusion-v1-5
860MConditions≈2.4 GB↓ 1.1M
SG161222 logo2.6BConditions≈6.2 GB↓ 1.4M
stabilityai logo
sdxl-turbostabilityai
2.6BNon-commercial≈6.2 GB↓ 571.8K
ByteDance logo?BConditions? GB↓ 275.1K
stabilityai logo
sd-turbostabilityai
866MCheck licence≈2.4 GB↓ 399.5K
cagliostrolab logo
animagine-xl-4.0cagliostrolab
2.6BConditions≈6.2 GB↓ 1M
RunDiffusion logo
Juggernaut-XL-v9RunDiffusion
?BConditions? GB↓ 617.6K

Browse all 42 models →

More in Image Generation

Rate this project

Click to rate — no account needed.

0 comments

Posting as guest
Loading comments…