luethan2025/ddpm

Quick Start

git clone https://github.com/bareform/ddpm.git
cd ddpm

You can download the pre-trained models here and use the provided Jupyter Notebook inference.ipynb to generate some samples.

Method

Denoising Diffusion Probabilistic Models

Jonathan Ho, Ajay Jain, Pieter Abbeel

UC Berkeley

We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN.

Citation

The original paper can be found at:

@misc{ho2020ddpm,
    title={Denoising Diffusion Probabilistic Models},
    author={Jonathan Ho and Ajay Jain and Pieter Abbeel},
    year={2020},
    eprint={2006.11239},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}