lucidrains/denoising-diffusion-pytorch
A PyTorch implementation of Denoising Diffusion Probabilistic Models (DDPM) for generative image synthesis.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of DDPM, a generative modeling approach that estimates gradients of the data distribution through denoising score matching, then uses Langevin sampling to generate samples. The implementation includes a U-Net architecture with support for flash attention and supports training diffusion models for image generation tasks.
Frequently asked
- What is lucidrains/denoising-diffusion-pytorch?
- A PyTorch implementation of Denoising Diffusion Probabilistic Models (DDPM) for generative image synthesis.
- Is denoising-diffusion-pytorch open source?
- Yes — lucidrains/denoising-diffusion-pytorch is open source, released under the MIT license.
- What language is denoising-diffusion-pytorch written in?
- lucidrains/denoising-diffusion-pytorch is primarily written in Python.
- How popular is denoising-diffusion-pytorch?
- lucidrains/denoising-diffusion-pytorch has 10.7k stars on GitHub.
- Where can I find denoising-diffusion-pytorch?
- lucidrains/denoising-diffusion-pytorch is on GitHub at https://github.com/lucidrains/denoising-diffusion-pytorch.