SDXL DPO

(From abstract of paper by Wallace, Dang, Rafailov, et al., 2023)

"... a method to align diffusion models to human preferences by directly optimizing on human comparison data.... Using the Pick-a-Pic dataset of 851K crowdsourced pairwise preferences, we fine-tune the base model of the state-of-the-art Stable Diffusion XL (SDXL)-1.0 model with Diffusion-DPO. Our fine-tuned base model significantly outperforms... SDXL-1.0... in human evaluation, improving visual appeal and prompt alignment."