Saved in:
Bibliographic Details
Main Authors: Xing, Peng, Wang, Ning, Ouyang, Jianbo, Li, Zechao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.02881
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911907726753792
author Xing, Peng
Wang, Ning
Ouyang, Jianbo
Li, Zechao
author_facet Xing, Peng
Wang, Ning
Ouyang, Jianbo
Li, Zechao
contents The remarkable advancement in text-to-image generation models significantly boosts the research in ID customization generation. However, existing personalization methods cannot simultaneously satisfy high fidelity and high-efficiency requirements. Their main bottleneck lies in the prompt image encoder, which produces weak alignment signals with the text-to-image model and significantly increased model size. Towards this end, we propose a lightweight Inv-Adapter, which first extracts diffusion-domain representations of ID images utilizing a pre-trained text-to-image model via DDIM image inversion, without additional image encoder. Benefiting from the high alignment of the extracted ID prompt features and the intermediate features of the text-to-image model, we then embed them efficiently into the base text-to-image model by carefully designing a lightweight attention adapter. We conduct extensive experiments to assess ID fidelity, generation loyalty, speed, and training parameters, all of which show that the proposed Inv-Adapter is highly competitive in ID customization generation and model scale.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02881
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Inv-Adapter: ID Customization Generation via Image Inversion and Lightweight Adapter
Xing, Peng
Wang, Ning
Ouyang, Jianbo
Li, Zechao
Computer Vision and Pattern Recognition
The remarkable advancement in text-to-image generation models significantly boosts the research in ID customization generation. However, existing personalization methods cannot simultaneously satisfy high fidelity and high-efficiency requirements. Their main bottleneck lies in the prompt image encoder, which produces weak alignment signals with the text-to-image model and significantly increased model size. Towards this end, we propose a lightweight Inv-Adapter, which first extracts diffusion-domain representations of ID images utilizing a pre-trained text-to-image model via DDIM image inversion, without additional image encoder. Benefiting from the high alignment of the extracted ID prompt features and the intermediate features of the text-to-image model, we then embed them efficiently into the base text-to-image model by carefully designing a lightweight attention adapter. We conduct extensive experiments to assess ID fidelity, generation loyalty, speed, and training parameters, all of which show that the proposed Inv-Adapter is highly competitive in ID customization generation and model scale.
title Inv-Adapter: ID Customization Generation via Image Inversion and Lightweight Adapter
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.02881