Saved in:
Bibliographic Details
Main Authors: Wei, Fanyue, Zeng, Wei, Li, Zhenyang, Yin, Dawei, Duan, Lixin, Li, Wen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.06642
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916329189015552
author Wei, Fanyue
Zeng, Wei
Li, Zhenyang
Yin, Dawei
Duan, Lixin
Li, Wen
author_facet Wei, Fanyue
Zeng, Wei
Li, Zhenyang
Yin, Dawei
Duan, Lixin
Li, Wen
contents Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based generation models, the visual structure and details of the object are often unexpectedly changed during the diffusion process. One major reason is that these diffusion-based approaches typically adopt a simple reconstruction objective during training, which can hardly enforce appropriate structural consistency between the generated and the reference images. To this end, in this paper, we design a novel reinforcement learning framework by utilizing the deterministic policy gradient method for personalized text-to-image generation, with which various objectives, differential or even non-differential, can be easily incorporated to supervise the diffusion models to improve the quality of the generated images. Experimental results on personalized text-to-image generation benchmark datasets demonstrate that our proposed approach outperforms existing state-of-the-art methods by a large margin on visual fidelity while maintaining text-alignment. Our code is available at: \url{https://github.com/wfanyue/DPG-T2I-Personalization}.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06642
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning
Wei, Fanyue
Zeng, Wei
Li, Zhenyang
Yin, Dawei
Duan, Lixin
Li, Wen
Computer Vision and Pattern Recognition
Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based generation models, the visual structure and details of the object are often unexpectedly changed during the diffusion process. One major reason is that these diffusion-based approaches typically adopt a simple reconstruction objective during training, which can hardly enforce appropriate structural consistency between the generated and the reference images. To this end, in this paper, we design a novel reinforcement learning framework by utilizing the deterministic policy gradient method for personalized text-to-image generation, with which various objectives, differential or even non-differential, can be easily incorporated to supervise the diffusion models to improve the quality of the generated images. Experimental results on personalized text-to-image generation benchmark datasets demonstrate that our proposed approach outperforms existing state-of-the-art methods by a large margin on visual fidelity while maintaining text-alignment. Our code is available at: \url{https://github.com/wfanyue/DPG-T2I-Personalization}.
title Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.06642