A Survey of Data-Driven 2D Diffusion Models for Generating Images from Text

Fang, Shun (2024) A Survey of Data-Driven 2D Diffusion Models for Generating Images from Text. EAI Endorsed Transactions on AI and Robotics.

[thumbnail of 70267.pdf] PDF
70267.pdf
Download (1MB)

Abstract

This paper explores recent advances in generative modeling, focusing on DDPMs, HighLDM, and Imagen. DDPMs utilize denoising score matching and iterative refinement to reverse diffusion processes, enhancing likelihood estimation and lossless compression capabilities. HighLDM breaks new ground with hi

Item Type: Article
Date Deposited: 04 Mar 2026 18:09
Last Modified: 11 Apr 2026 00:41
URI: http://eprints.eai.eu/id/eprint/51352

Actions (login required)

View Item
View Item