We present 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: The increase of model parameters is mainly due to more attention blocks and a larger cross-attention context as SDXL uses a second text encoder. We design multiple novel conditioning schemes and train SDXL on multiple aspect ratios. 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 shows drastically improved performance compared the previous versions of Stable Diffusion and achieves results competitive with those of black-box state-of-the-art image generators. In the spirit of promoting open research and fostering transparency in large model training and evaluation, we provide access to code and model weights at https://github.com/Stability-AI/generative-models
@article{arxiv.2307.01952,
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 Müller and Joe Penna and Robin Rombach},
journal= {arXiv preprint arXiv:2307.01952},
year = {2023}
}