DDPM stands for: Denoising Diffusion Probabilistic Model

the reverse process learns: p_θ(x_{t-1}|x_t)

The reverse process learns: p_θ(x_{t-1}|x_t) — denoising one step at a time

Stable Diffusion

Stable Diffusion generates images from text descriptions

denoising score matching does: learns to denoise, which equals learning the score

Denoising score matching learns to denoise by estimating the score (gradient of log probability) of data distributions

DDIM does: deterministic sampling for faster generation with fewer steps

DDIM accelerates image generation by deterministically sampling intermediate steps

Langevin dynamics does: adds noise to gradient descent to sample from a distribution

Langevin dynamics adds noise to gradient descent to sample from a distribution

Diffusion model

q(x_t|x_{t-1}) adds Gaussian noise at each step