SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, Robin Rombach
Abstract
We present Stable Diffusion XL (SDXL), a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet backbone, achieved by significantly increasing the number of attention blocks and including a second text encoder. Further, we design multiple novel conditioning schemes and train SDXL on multiple aspect ratios. To ensure highest quality results, we also introduce a refinement model which is used to improve the visual fidelity of samples generated by SDXL using a post-hoc image-to-image technique. We demonstrate that SDXL improves dramatically over previous versions of Stable Diffusion and achieves results competitive with those of black-box state-of-the-art image generators such as Midjourney.
BibTeX
@inproceedings{
podell2024sdxl,
title={{SDXL}: Improving Latent Diffusion Models for High-Resolution Image Synthesis},
author={Dustin Podell and Zion English and Kyle Lacey and Andreas Blattmann and Tim Dockhorn and Jonas M{\"u}ller and Joe Penna and Robin Rombach},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=di52zR8xgf}
}