AI Hub
All papers
Architecture

Denoising Diffusion Probabilistic Models

UC Berkeley·June 19, 2020

Jonathan Ho, Ajay Jain, Pieter Abbeel

View on arXiv

TL;DR

Reformulates diffusion models and shows they can generate high-quality images, establishing the denoising framework used by modern image generators.

Why it matters

The technical foundation of the image-generation boom — nearly every modern text-to-image system descends from this denoising formulation.

Related terms