Diffusion models
Diffusion models
A class of latent variable generative models consisting of three major components: a forward process, a reverse process, and a sampling procedure. The goal of the diffusion model is to learn a diffusion process that generates the probability distribution of a given dataset. It is widely used in computer vision on a variety of tasks, including image denoising, inpainting, super-resolution, and image generation.
Source: NIST AI 100-2e2025 | Category: