Denoising Diffusion Probabilistic Models

Jonathan Ho, Ajay Jain, Pieter Abbeel

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. Our implementation is available at https://github.com/hojonathanho/diffusion

• Impossible Research
• Carnegie Mellon University
• University of California, Berkeley
• Anthropic
• Alignment Research Center
• Anthropic
• Truthful AI
• University of California, Berkeley
• Warsaw University of Technology
• Microsoft
• Carnegie Mellon University
• Stanford University
• University of California, Berkeley
• Bakar Institute of Digital Materials for the Planet
• King Abdulaziz City for Science and Technology
• Synchrotron SOLEIL
• University of California, Berkeley
• University of Cambridge
• Meta Platforms
• Dartmouth College
• International Computer Science Institute
• University of California, Berkeley
• University of California, Berkeley