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, each step of the forward diffusion process is defined as $q(x_{t}|x_{t-1})=N(x_{t},{\sqrt {1-\beta _{t}}},\beta _{t}I)$, where x_t is the process output at step t, q is a distribution at the current step depending on the previous step, N is a normal distribution, the square root is the mean, and the last one being the variance.

Sources

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