A diffusion model is a generative model trained to reverse a process that gradually adds noise to data. By learning to denoise from random noise toward a target data distribution, it can generate realistic images, audio, text representations, or other outputs.
In machine learning, diffusion models, also known as diffusion probabilistic models or score-based generative models, are a class of latent variable models. They are Markov chains trained using variational inference. The goal of diffusion models is to learn the latent structure of a dataset by modeling the way in which data points diffuse through the latent space. In computer vision, this means that a neural network is trained to denoise images blurred with Gaussian noise by learning to reverse the diffusion process. It mainly consists of three major components: the forward process, the revers