NeurIPS 2020
DDPM: Denoising Diffusion Probabilistic Models
Jonathan Ho, Ajay Jain, +1
How diffusion models learn to generate images by reversing a gradual noising process — the foundation of Stable Diffusion, DALL-E, and modern image generation.
Explore machine learning papers and reviews related to Diffusion. Find insights, analysis, and implementation details.
Jonathan Ho, Ajay Jain, +1
How diffusion models learn to generate images by reversing a gradual noising process — the foundation of Stable Diffusion, DALL-E, and modern image generation.
Robin Rombach, Andreas Blattmann, +3
How Latent Diffusion Models made high-resolution image generation practical by moving diffusion to a compressed latent space — the architecture behind Stable Diffusion.