Saved in:
Bibliographic Details
Main Authors: He, Jing, Li, Haodong, Hu, Yongzhe, Shen, Guibao, Cai, Yingjie, Qiu, Weichao, Chen, Ying-Cong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.02067
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910672094232576
author He, Jing
Li, Haodong
Hu, Yongzhe
Shen, Guibao
Cai, Yingjie
Qiu, Weichao
Chen, Ying-Cong
author_facet He, Jing
Li, Haodong
Hu, Yongzhe
Shen, Guibao
Cai, Yingjie
Qiu, Weichao
Chen, Ying-Cong
contents In the realm of image generation, creating customized images from visual prompt with additional textual instruction emerges as a promising endeavor. However, existing methods, both tuning-based and tuning-free, struggle with interpreting the subject-essential attributes from the visual prompt. This leads to subject-irrelevant attributes infiltrating the generation process, ultimately compromising the personalization quality in both editability and ID preservation. In this paper, we present DisEnvisioner, a novel approach for effectively extracting and enriching the subject-essential features while filtering out -irrelevant information, enabling exceptional customization performance, in a tuning-free manner and using only a single image. Specifically, the feature of the subject and other irrelevant components are effectively separated into distinctive visual tokens, enabling a much more accurate customization. Aiming to further improving the ID consistency, we enrich the disentangled features, sculpting them into more granular representations. Experiments demonstrate the superiority of our approach over existing methods in instruction response (editability), ID consistency, inference speed, and the overall image quality, highlighting the effectiveness and efficiency of DisEnvisioner. Project page: https://disenvisioner.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02067
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation
He, Jing
Li, Haodong
Hu, Yongzhe
Shen, Guibao
Cai, Yingjie
Qiu, Weichao
Chen, Ying-Cong
Computer Vision and Pattern Recognition
In the realm of image generation, creating customized images from visual prompt with additional textual instruction emerges as a promising endeavor. However, existing methods, both tuning-based and tuning-free, struggle with interpreting the subject-essential attributes from the visual prompt. This leads to subject-irrelevant attributes infiltrating the generation process, ultimately compromising the personalization quality in both editability and ID preservation. In this paper, we present DisEnvisioner, a novel approach for effectively extracting and enriching the subject-essential features while filtering out -irrelevant information, enabling exceptional customization performance, in a tuning-free manner and using only a single image. Specifically, the feature of the subject and other irrelevant components are effectively separated into distinctive visual tokens, enabling a much more accurate customization. Aiming to further improving the ID consistency, we enrich the disentangled features, sculpting them into more granular representations. Experiments demonstrate the superiority of our approach over existing methods in instruction response (editability), ID consistency, inference speed, and the overall image quality, highlighting the effectiveness and efficiency of DisEnvisioner. Project page: https://disenvisioner.github.io/.
title DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.02067