Skip to content

YHL04/ddpm

Repository files navigation

Denoising Diffusion Probabilistic Models (DDPM) for image generation

A Generative Model that outperform GANs in terms of compute and benchmarks.

Predecessor of many state of the art generative models such as DALLE and Stable Diffusion.

Results (100 epochs):

alt text

Improved DDPM Changes

  • Learning: Changing loss function and variance formula

  • Cosine Schedule

  • Faster Sampling by changing number of timesteps

  • Scalable transformer for diffusion

  • Importance Sampling

Citations

@article{ho2020denoising,
  title={Denoising diffusion probabilistic models},
  author={Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
  journal={Advances in neural information processing systems},
  volume={33},
  pages={6840--6851},
  year={2020}
}
@inproceedings{nichol2021improved,
  title={Improved denoising diffusion probabilistic models},
  author={Nichol, Alexander Quinn and Dhariwal, Prafulla},
  booktitle={International conference on machine learning},
  pages={8162--8171},
  year={2021},
  organization={PMLR}
}
@inproceedings{peebles2023scalable,
  title={Scalable diffusion models with transformers},
  author={Peebles, William and Xie, Saining},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={4195--4205},
  year={2023}
}

About

Denoising Diffusion Probabilistic Model for Image Generation

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages