Diffusion model: Difference between revisions
From Rice Wiki
(Created page with "= Sources = * https://erdem.pl/2023/11/step-by-step-visual-introduction-to-diffusion-models Category:Computer Science Category:Machine Learning") |
No edit summary |
||
| Line 1: | Line 1: | ||
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 <math>q(x_t|x_{t-1})=N(x_t, \sqrt{1-\beta_t}, \beta_tI)</math>, where ''q'' is the forward diffusion process, | |||
= Sources = | = Sources = | ||
Revision as of 22:59, 4 July 2024
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 , where q is the forward diffusion process,
