Learning to sample from a distribution rather than to label one.
Colour is the family; a dashed line is the second member of it.
Learns an encoder to a latent distribution and a decoder back, trained on a lower bound of the likelihood. Gives a latent space you can interpolate i… · 2013
Trains a generator against a discriminator that tries to tell real from fake. Produces sharp samples, and the minimax objective is notoriously unstab… · 2014
Learns to reverse a gradual noising process, generating by denoising repeatedly from pure noise. Trades sampling speed for stable training and far be… · 2020
Runs the diffusion process in the compressed latent space of an autoencoder rather than on pixels. The reason text-to-image generation fits on consum… · 2021
Trains one model both conditioned and unconditioned, then extrapolates away from the unconditional prediction at sampling time. Buys prompt adherence… · 2022