Concept
Diffusion
Diffusion is a generative modeling approach that learns to reverse a gradual noising process. During training you take a clean sample (an image, an audio clip, a chunk of latent features), add Gaussian noise in steps until it becomes pure noise, then train a network to…
The rest of “Diffusion” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→