Training.Demo.mp4
Diffusion Explorer is an interactive tool (check out a beta version here) for communicating the geometric intuitions behind diffusion and flow based generative models. This project is currently a work in progress.
Diffusion Explorer is mainly an educaitonal tool with the following key functionality. It
- Implements various training objectives like Flow Matching and Denoising Score Matching
- Shows the dynamics of generated samples over time for pretrained models
- Allows a user to observe how generated samples change through training
- Enables training on custom hand drawn distributions
You can try out Diffusion Explorer locally by running the project.
First, clone the project
git clone https://github.com/helblazer811/Diffusion-Explorer
Then change the directory and install dependencies
cd diffusion-explorer
npm install
Now run the local server
npm run dev
and then access it in your browser at the specified port.
You can also see some other interesting (non-interactive) visualizations in /other-visualizations
.