Blog Post··6 min read
DDPM: The Diffusion Process, Forward and Reverse
DDPM defines a fixed forward process that gradually destroys an image into noise, then trains a neural network to reverse it. The math is tractable because each step is Gaussian.
Tag: image-generation
Blog Post··6 min read
DiT: Replacing the U-Net with a Transformer
DDPM, DDIM, and latent diffusion all use a U-Net backbone. DiT replaces it with a transformer — and finds that diffusion scales with model size the same way language models do.