The recent progress in text-to-image models pretrained on large-scale datasets has enabled us to generate various images as long as we provide a text prompt describing what we want. Nevertheless, the availability of these models is still limited when we expect to generate images that fall into a specific domain either hard to describe or just unseen to the models. In this work, we propose DomainGallery, a few-shot domain-driven image generation method which aims at finetuning pretrained Stable Diffusion on few-shot target datasets in an attribute-centric manner. Specifically, DomainGallery features prior attribute erasure, attribute disentanglement, regularization and enhancement. These techniques are tailored to few-shot domain-driven generation in order to solve key issues that previous works have failed to settle. Extensive experiments are given to validate the superior performance of DomainGallery on a variety of domain-driven generation scenarios. Codes are available at https://github.com/Ldhlwh/DomainGallery.
@article{arxiv.2411.04571,
title = {DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning},
author = {Yuxuan Duan and Yan Hong and Bo Zhang and Jun Lan and Huijia Zhu and Weiqiang Wang and Jianfu Zhang and Li Niu and Liqing Zhang},
journal= {arXiv preprint arXiv:2411.04571},
year = {2024}
}