Concept
Diffusion model
A diffusion model is a generative model that learns to reverse a gradual noising process. During training you take a real sample (an image, a video frame, an audio clip), add Gaussian noise in many small steps until it becomes pure noise, then train a network to predict and…
The rest of “Diffusion model” 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→