Can I read Aligning Diffusion Models by Optimizing Human Utility on EtoBox?

Aligning Diffusion Models by Optimizing Human Utility by Li, Shufan; Kallidromitis, Konstantinos; Gokul, Akash; Kato, Yusuke; Kozuka, Kazuki is a scholarly article available to read on EtoBox.

What is Aligning Diffusion Models by Optimizing Human Utility about?

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. Since this objective applies to each generation independently, Diffusion-KTO does not require collecting costly pairwise preference data nor training a complex reward model. Instead, our objective requires simple per-image binary feedback signals, e.g. likes or dislikes, which are abundantly available. After fine-tuning using Diffusion-KTO, text-to-image diffusion models exhibit superior 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 signals and broadens the applicability of aligning text-to-image diffusion models with human preferences.

Author

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

Published

2024

Language

EN