Personalized Preference Fine-tuning of Diffusion Models
RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the nuances of individual users' beliefs or values. This lack of personalization limits the efficacy of these models. To bridge this gap, we introduce PPD, a multi-reward optimization objective that aligns diffusion models with personalized preferences. With PPD, a diffusion model learns the individual preferences of a population of users in a few-shot way, enabling generalization to unseen users. Specifically, our approach (1) leverages a vision-language model (VLM) to extract personal preference embeddings from a small set of pairwise preference examples, and then (2) incorporates the embeddings into diffusion models through cross attention. Conditioning on user embeddings, the text-to-image models are fine-tuned with the DPO objective, simultaneously optimizing for alignment with the preferences of multiple users. Empirical results demonstrate that our method effectively optimizes for multiple reward functions and can interpolate between them during inference. In real-world user scenarios, with as few as four preference examples from a new user, our approach achieves an average win rate of 76\% over Stable Cascade, generating images that more accurately reflect specific user preferences.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PAPA: Online Personalized Active Preference Alignment
Diffusion models are highly effective at modeling complex data distributions, including images and text. However, in applications like personalized recommender systems, the objective often shifts to modeling specific reg…
Reinforcement LearningDraw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models
Personalized generation in T2I diffusion models aims to naturally incorporate individual user preferences into the generation process with minimal user intervention. However, existing studies primarily rely on prompt-lev…
DesignPref: Capturing Personal Preferences in Visual Design Generation
Generative models, such as large language models and text-to-image diffusion models, are increasingly used to create visual designs like user interfaces (UIs) and presentation slides. Finetuning and benchmarking these ge…
Preference Aligned Visuomotor Diffusion Policies for Deformable Object Manipulation
Humans naturally develop preferences for how manipulation tasks should be performed, which are often subtle, personal, and difficult to articulate. Although it is important for robots to account for these preferences to …
WikiPersonas: What Can We Learn From Personalized Alignment to Famous People?
Preference alignment has become a standard pipeline in finetuning models to follow \emph{generic} human preferences. Majority of work seeks to optimize model to produce responses that would be preferable \emph{on average…