EUVIMEDEUVIMED entdecken
Crossref

ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models

Jiaxiang Cheng, Pan Xie, Xin Xia, Jiashi Li, Jie Wu, Yuxi Ren, Huixia Li, Xuefeng Xiao, Shilei Wen, Lean Fu

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (3) · 2438-2446

DOI: 10.1609/aaai.v39i3.32245 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Jiaxiang Cheng und 9 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advancement in text-to-image models and corresponding personalized technologies enables individuals to generate high-quality and imaginative images. However, they often suffer from limitations when generating images with resolutions outside of their trained domain. To overcome this limitation, we present the resolution adapter \textbf{(ResAdapter)}, a domain-consistent adapter designed for diffusion models to generate images with unrestricted resolutions and aspect ratios. Unlike other multi-resolution generation methods that process images of static resolution with complex post-process operations, ResAdapter directly generates images with the dynamical resolution. Especially, after learning a deep understanding of pure resolution priors, ResAdapter trained on the general dataset, generates resolution-free images with personalized diffusion models while preserving their original style domain. Comprehensive experiments demonstrate that ResAdapter with only 0.5M can process images with flexible resolutions for arbitrary diffusion models. More extended experiments demonstrate that ResAdapter is compatible with other modules for image generation across a broad range of resolutions, and can be integrated into other multi-resolution model for efficiently generating higher-resolution images.

Zitieren

APA

Cheng, J., Xie, P., Xia, X., Li, J., Wu, J., Ren, Y., Li, H., Xiao, X., Wen, S., & Fu, L. (2025). ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 2438-2446. https://doi.org/10.1609/aaai.v39i3.32245

Vancouver

Cheng J, Xie P, Xia X, Li J, Wu J, Ren Y, et al. ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(3):2438-2446. doi:10.1609/aaai.v39i3.32245

BibTeX
@article{Cheng2025,
  author = {Cheng, Jiaxiang and Xie, Pan and Xia, Xin and Li, Jiashi and Wu, Jie and Ren, Yuxi and Li, Huixia and Xiao, Xuefeng and Wen, Shilei and Fu, Lean},
  title = {ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {3},
  pages = {2438--2446},
  doi = {10.1609/aaai.v39i3.32245}
}
Kostenlos starten →