Saved in:
Bibliographic Details
Main Authors: Chen, Dar-Yen, Tennent, Hamish, Hsu, Ching-Wen
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.02109
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916177375133696
author Chen, Dar-Yen
Tennent, Hamish
Hsu, Ching-Wen
author_facet Chen, Dar-Yen
Tennent, Hamish
Hsu, Ching-Wen
contents This work introduces ArtAdapter, a transformative text-to-image (T2I) style transfer framework that transcends traditional limitations of color, brushstrokes, and object shape, capturing high-level style elements such as composition and distinctive artistic expression. The integration of a multi-level style encoder with our proposed explicit adaptation mechanism enables ArtAdapter to achieve unprecedented fidelity in style transfer, ensuring close alignment with textual descriptions. Additionally, the incorporation of an Auxiliary Content Adapter (ACA) effectively separates content from style, alleviating the borrowing of content from style references. Moreover, our novel fast finetuning approach could further enhance zero-shot style representation while mitigating the risk of overfitting. Comprehensive evaluations confirm that ArtAdapter surpasses current state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2312_02109
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation
Chen, Dar-Yen
Tennent, Hamish
Hsu, Ching-Wen
Computer Vision and Pattern Recognition
This work introduces ArtAdapter, a transformative text-to-image (T2I) style transfer framework that transcends traditional limitations of color, brushstrokes, and object shape, capturing high-level style elements such as composition and distinctive artistic expression. The integration of a multi-level style encoder with our proposed explicit adaptation mechanism enables ArtAdapter to achieve unprecedented fidelity in style transfer, ensuring close alignment with textual descriptions. Additionally, the incorporation of an Auxiliary Content Adapter (ACA) effectively separates content from style, alleviating the borrowing of content from style references. Moreover, our novel fast finetuning approach could further enhance zero-shot style representation while mitigating the risk of overfitting. Comprehensive evaluations confirm that ArtAdapter surpasses current state-of-the-art methods.
title ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.02109