Aligning Diffusion Models by Optimizing Human Utility

Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka

Keywords: text-to-image; diffusion; computer vision;

TL;DR: We extend the utility maximization framework to the setting of diffusion models and use it to align text-to-image diffusion models with human preferences using only per-image binary preference signals, e.g., likes and dislikes.

Abstract: We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility. Unlike previous methods, Diffusion-KTO does not require collecting pairwise preference data nor training a complex reward model. Instead, our objective uses per-image binary feedback signals, e.g. likes or dislikes, to align the model with human preferences. After fine-tuning using Diffusion-KTO, text-to-image diffusion models exhibit improved performance compared to existing techniques, including supervised fine-tuning and Diffusion-DPO, both in terms of human judgment and automatic evaluation metrics such as PickScore and ImageReward. Overall, Diffusion-KTO unlocks the potential of leveraging readily available per-image binary preference signals and broadens the applicability of aligning text-to-image diffusion models with human preferences.

Primary Area: Generative models

Submission Number: 7450