OpenRouter
You need an API key from the provider.
~/SillyTavern/data/default-user/settings.json
Get a key ↗The classic AI image web UI (A1111, biggest ecosystem)
Stable Diffusion WebUI · icon from the registry
This app ships with everything it needs — no Node.js, Python or other runtimes to install.
The classic AI image web UI (A1111, biggest ecosystem)
Registry data updated: 2026-11-16
Config file written to
~/SillyTavern/data/default-user/settings.json
Everything stays on your own machine — nothing is uploaded. To uninstall, delete these folders.
One portable file for Windows (macOS coming). Double-click and it runs — no installer, no administrator rights.
Go to download →Open the AiBOX app catalog, find Stable Diffusion WebUI and press Install. AiBOX checks what your machine already has and installs only what is missing.
It downloads with a checksum check, writes the config and fills in your API key if the app needs one. You just click.
✓ Installed until it works.Prefer to do it by hand? The full written guide is right below. Read the guide ↓
The same steps in written form — follow along at your own pace.
One line: A1111 is the classic Stable Diffusion web interface — txt2img, img2img, inpainting, upscaling, embedding training, plus the thickest plugin and model ecosystem around; most community tutorials and models target it first.
--api flag that exposes the whole thing as a local HTTP API for scripting| Need | Notes |
|---|---|
| Python 3.10.6 (recommended) | Official instruction: install 3.10.6 and tick "Add Python to PATH" — newer Python versions don't work with torch (3.11+ requires setting python_cmd manually; not beginner-friendly) |
| Git | Free from git-scm.com |
| GPU | NVIDIA discrete GPU preferred (4GB VRAM floor); iGPU/CPU works but is slow |
| Disk | ~1GB for the program, plus ~2.5GB of PyTorch on first launch and a model (SDXL checkpoints are 6–7GB) |
| Permissions | Zero admin — installs into your user folder |
~/sd-webuiPIP_INDEX_URL to a domestic mirror if it's slow)git clone --depth 1 -b v1.10.1 https://github.com/AUTOMATIC1111/stable-diffusion-webui.git ~/sd-webui
cd ~/sd-webui
python -m venv venv # isolated environment
./venv/bin/pip install -r requirements.txt # Windows: .\venv\Scripts\pip
./venv/bin/python launch.py # first run finishes the setup
On Windows you can also use the official script: with Python 3.10.6 and Git installed, double-click webui-user.bat in the cloned folder as a normal user (never "Run as administrator"). Linux needs system packages first: sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0.
Put flags in COMMANDLINE_ARGS= inside webui-user.bat (Windows) or webui-user.sh (Linux):
| Flag | What it does |
|---|---|
--medvram / --lowvram | Add this on CUDA out-of-memory errors — trades speed for VRAM |
--xformers | Memory-efficient attention, faster on NVIDIA |
--api | Enables the local API (/sdapi/v1/*, Swagger UI at /docs) |
--listen --port 7860 | LAN access (keep the firewall restricted to your network) |
--precision full --no-half | Common fix for completely black images |
Example: set COMMANDLINE_ARGS=--medvram --xformers in webui-user.bat.
.safetensors checkpoint from Civitai or Hugging Face~/sd-webui/models/Stable-diffusion/, refresh, and it shows up in the top dropdownmodels/VAE, models/Lora, embeddings/, models/ControlNetSidebar Extensions → Install from URL, paste the plugin repo (or search under the Available tab via Load from index), install, then Apply and restart UI.
Running on local URL: http://127.0.0.1:7860 — open itset PIP_INDEX_URL=https://pypi.tuna.tsinghua.edu.cn/simple and reinstall (the AiBOX route mirrors automatically)venv and recreate it--medvram (then --lowvram if needed) or generate at smaller resolutions--precision full --no-halfMetadataIncompleteBuffer / PytorchStreamReader on a model: the file is corrupt — download it again--port 7861 to COMMANDLINE_ARGSrm -rf ~/sd-webui # venv, models and outputs all live here — back up models/ and outputs/ first
AiBOX's Manage → Uninstall handles it.
More: GitHub README · install & run wiki · features wiki
AiBOX fills this in for you during the wizard — this section is for setting it up by hand.
You need an API key from the provider.
~/SillyTavern/data/default-user/settings.json
Get a key ↗You need an API key from the provider.
~/SillyTavern/data/default-user/settings.json
Get a key ↗You need an API key from the provider.
~/SillyTavern/data/default-user/settings.json
Get a key ↗You need an API key from the provider.
~/SillyTavern/data/default-user/settings.json
Get a key ↗Sign in with your account instead — no key to copy.
~/SillyTavern/data/default-user/settings.json
Get a key ↗Local model — no API key needed.
~/SillyTavern/data/default-user/settings.json
Runs on Windows / macOS — install it with AiBOX on any of them.
Difficulty 5 out of 5. AiBOX does the download and setup; your part is clicking through the wizard and pasting a key if the app needs one.
Everything stays on your own machine: ~/sd-webui / ~/sd-webui. To uninstall, delete these — nothing is ever uploaded.
An outdated step, an error you do not understand, a typo — tell us and we will fix this page.
Upstream projects
Version numbers are re-checked by our daily probe — when upstream ships a new release, this page follows.
A wrong step, a confusing error, a typo — open an issue and someone will look.