Diffusion model

In a nutshell, diffusion models work by making something more random/noisy, and through the process finding the inverse, which is making noisy things less random, thus generating data.

Diffusion models are frequently used for computer vision tasks such as text-to-image. This page will focus exclusively on that use case.

Principle

More specifically, diffusion models consists of two steps: forward diffusion, which turns an image into noise, and backward diffusion, which turns noise back into an image.

Forward diffusion

Mathematically, forward diffusion is defined as $q(x_{t}|x_{t-1})=N(x_{t},{\sqrt {1-\beta _{t}}},\beta _{t}I)$, where q is the forward diffusion process,

Sources

• https://erdem.pl/2023/11/step-by-step-visual-introduction-to-diffusion-models