DemoFusion: Democratising High-Resolution Image Generation With No $$$

Ruoyi Du, Dongliang Chang, Timothy Hospedales, Yi-Zhe Song, Zhanyu Ma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

High-resolution image generation with Generative Artificial Intelligence (GenAI) has immense potential but, due to the enormous capital investment required for training, it is increasingly centralised to a few large corporations, and hidden behind paywalls. This paper aims to democratise high-resolution GenAI by advancing the frontier of high-resolution generation while remaining accessible to a broad audience. We demonstrate that existing Latent Diffusion Models (LDMs) possess untapped potential for higher-resolution image generation. Our novel DemoFusion framework seamlessly extends open-source GenAI models, employing Progressive Upscaling, Skip Residual, and Dilated Sampling mechanisms to achieve higher-resolution image generation. The progressive nature of DemoFusion requires more passes, but the intermediate results can serve as "previews", facilitating rapid prompt iteration.
Original languageEnglish
Title of host publication2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
Number of pages18
Publication statusAccepted/In press - 27 Feb 2024
EventThe IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024 - Seattle, United States
Duration: 17 Jun 202421 Jun 2024
https://cvpr.thecvf.com/

Publication series

NameProceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
PublisherIEEE
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

ConferenceThe IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024
Abbreviated titleCVPR 2024
Country/TerritoryUnited States
CitySeattle
Period17/06/2421/06/24
Internet address

Fingerprint

Dive into the research topics of 'DemoFusion: Democratising High-Resolution Image Generation With No $$$'. Together they form a unique fingerprint.

Cite this