Training teaches the network to predict noise, a clean sample, or a related quantity at different noise levels. Generation starts from noise and applies a sequence of denoising updates, often conditioned on text or other inputs.
A diffusion model generates data by learning to reverse a gradual noising process.
Training teaches the network to predict noise, a clean sample, or a related quantity at different noise levels. Generation starts from noise and applies a sequence of denoising updates, often conditioned on text or other inputs.