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.
@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}
}