dome272/Diffusion-Models-pytorch
A minimal PyTorch implementation of DDPM diffusion models for unconditional and conditional image generation.
Not currently ranked — collecting fresh signals.
star history
This repository provides a clean, educational implementation of diffusion models following the DDPM paper exactly. It includes two variants: unconditional and conditional diffusion model training, with the conditional version supporting Classifier-Free Guidance and Exponential Moving Average techniques. The implementation uses a UNet architecture for the denoising network and supports training on custom datasets as well as sampling/generated image production.
Frequently asked
- What is dome272/Diffusion-Models-pytorch?
- A minimal PyTorch implementation of DDPM diffusion models for unconditional and conditional image generation.
- Is Diffusion-Models-pytorch open source?
- Yes — dome272/Diffusion-Models-pytorch is open source, released under the Apache-2.0 license.
- What language is Diffusion-Models-pytorch written in?
- dome272/Diffusion-Models-pytorch is primarily written in Python.
- How popular is Diffusion-Models-pytorch?
- dome272/Diffusion-Models-pytorch has 1.5k stars on GitHub.
- Where can I find Diffusion-Models-pytorch?
- dome272/Diffusion-Models-pytorch is on GitHub at https://github.com/dome272/Diffusion-Models-pytorch.