Back to search

Cornell University

A Brief Introduction to Diffusion Models

Abstract

dc:description.abstract

This tutorial will provide an introduction to diffusion models. Diffusion models are a type of generative model that feature (1) a diffusion process where noise is gradually added to an image and (2) a learned denoising process where noise is gradually removed from an image of pure noise to reconstruct the input image. First introduced in 2015, there has recently been incredible advancements in the capabilities diffusion models. Companies such as Open AI and Stability AI have produced applications that can generate images from a single text prompt that can rival the artwork of a seasoned artist. This tutorial is is intended for students with an introductory level knowledge of machine learning, and includes a background on generative models, an overview of Denoising Diffusion Probabilistic Models (DDPMs) and improvements, and supplemental code for an implementation of a simple DDPM.

Degree

thesis:*
Name thesis:degree_name
M.S., Computer Science
Level thesis:degree_level
Master of Science
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Liu, Rebecca
Chair dc:contributor.chair
  • Weinberger, Kilian
Committee member dc:contributor.committeemember
  • Bhattacharjee, Tapomayukh

Subjects

dc:subject × 2

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Bibid
16176561
Dc Identifier Other
ProQuest Submission ID: 11766
ProQuest Publication ID: 30486218

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Liu, Rebecca. A Brief Introduction to Diffusion Models. Master of Science thesis, Cornell University, 2023. https://hdl.handle.net/1813/113915