Denoising Diffusion Probabilistic Models, Jonathan Ho, Augustin Saharia, William Chan, Chitwan Saharia, Jay Whang, Alex Ratner, Ruoxin Sang, Kevin Lin, Lihong Li, Jie Ren, Zhifeng Chen, Harrison Edwards, Andrew Brock, Prafulla Dhariwal, Alex Nichol, Heewon Kim, Fan Li, Yuval Alaluf, R. Tyler Mazaika, Sasha Sheng, Xiaoqing Ellen Tan, Adam Harley, Brian Li, Yang Song, Mohammad Norouzi, Tim Salimans, Alex Shmakov, Peter Henderson, Han Zhang, Irwan Bello, Ming-Hsuan Yang, Andrew Ng, Ian Goodfellow, Pieter Abbeel, and Durk Kingma, 2020Advances in Neural Information Processing Systems, Vol. 33 (NeurIPS)DOI: 10.5591/978-1-57788-756-3-6840 - This foundational paper introduces the Denoising Diffusion Probabilistic Models (DDPM) and details the core training algorithm for noise prediction networks, as outlined in this section.
Denoising Diffusion Probabilistic Models (DDPM) Conceptual Guide, Hugging Face, 2024 (Hugging Face) - This conceptual guide offers an accessible explanation of the Denoising Diffusion Probabilistic Models (DDPM) training loop, providing a clear walkthrough of the algorithm discussed in this section, aiding in practical understanding.
High-Resolution Image Synthesis with Latent Diffusion Models, Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer, 2022Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE)DOI: 10.1109/CVPR52688.2022.01042 - This paper demonstrates the scalability and effectiveness of the core DDPM training paradigm by applying it to latent space, significantly advancing high-resolution image generation using diffusion models.