miniDiffusion: A Minimal Stable Diffusion 3.5 Reimplementation in PyTorch

miniDiffusion is a streamlined reimplementation of the Stable Diffusion 3.5 model using pure PyTorch with minimal dependencies. Designed for educational, experimental, and hacking purposes, its concise codebase (~2800 lines) covers VAE, DiT, training, and dataset scripts. The project provides scripts for both training and inference. Users need to install dependencies and download pretrained model weights. This open-source project is licensed under MIT.