English

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

Computer Vision and Pattern Recognition 2023-12-18 v2 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2311.16973,
  title  = {DemoFusion: Democratising High-Resolution Image Generation With No $$$},
  author = {Ruoyi Du and Dongliang Chang and Timothy Hospedales and Yi-Zhe Song and Zhanyu Ma},
  journal= {arXiv preprint arXiv:2311.16973},
  year   = {2023}
}

Comments

Project Page: https://ruoyidu.github.io/demofusion/demofusion.html

R2 v1 2026-06-28T13:34:25.098Z