DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910687722209280 |
|---|---|
| author | Duan, Yuxuan Hong, Yan Zhang, Bo Lan, Jun Zhu, Huijia Wang, Weiqiang Zhang, Jianfu Niu, Li Zhang, Liqing |
| author_facet | Duan, Yuxuan Hong, Yan Zhang, Bo Lan, Jun Zhu, Huijia Wang, Weiqiang Zhang, Jianfu Niu, Li Zhang, Liqing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04571 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning Duan, Yuxuan Hong, Yan Zhang, Bo Lan, Jun Zhu, Huijia Wang, Weiqiang Zhang, Jianfu Niu, Li Zhang, Liqing Computer Vision and Pattern Recognition 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. |
| title | DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.04571 |