tiny-diffusion is an open-source, minimal diffusion model implemented in PyTorch for educational purposes. It operates on 2D point data and is designed to help students and educators understand the mechanics of diffusion models with a simple, lightweight implementation.
Tiny Diffusion is an Other AI product. It focuses on providing a minimal, educational implementation of diffusion models for learning and experimentation. Tiny Diffusion is an open-source project aimed at machine learning students and educators. The project is open source (MIT). It runs on the web, and it can be self-hosted.
Behind Tiny Diffusion is shahfazal, and the product first shipped in 2026. The project is developed in the open on GitHub with 13 commits in the last 90 days. Across PulseGate's embedding index, Tiny Diffusion has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are educational model, pyTorch implementation, and tiny parameter size.
Latest indexed changes and source events
shahfazal/tiny-diffusion discovered by the PulseGate indexer
Other apps tracked under the same category.
