What it does
SD-Trainer helps you train small add-ons, called LoRAs, for Stable Diffusion image models. A LoRA teaches a model a new style, character or subject from your own images.
It wraps a popular training tool in a web interface, with tools to tag images and charts to track training. There are one-step install scripts for Windows and Linux.
Who it's for
Artists and hobbyists who want to train Stable Diffusion on their own images.
Can I use it without coding?
With some setup. Install scripts set it up, but you need Python, Git and a terminal to start. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Windows, Linux
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Install Python and Git, then download the project with its add-ons.
- Run the install script for Windows or Linux.
- Run the start script and use the training page that opens in your browser.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (AGPL-3.0): Free to use; if you run a changed version as an online service, you must share your source code.
- More on staying safe