StyleGAN-$\infty$∞: Extending StyleGAN to Arbitrary-Ratio Translation With StyleBook

Yihua Dai, Tianyi Xiang, Bailin Deng, Yong Du, Hongmin Cai, Jing Qin, Shengfeng He

Abstract

Although pre-trained large-scale generative models StyleGAN series have proven to be effective in various editing and translation tasks, they are limited to pre-defined fixed aspect ratio. To overcome this limitation, we propose StyleGAN-$\infty$, a model that enables pre-trained StyleGAN to perform arbitrary-ratio conditional synthesis. Our key insight is to distill the expressive StyleGAN features into a StyleBook, such that an arbitrary-ratio condition can be translated to other forms by properly assembling pre-defined StyleBook vectors. To learn and leverage the StyleBook, we employ a network with three distinct stages, each corresponding to StyleBook extraction, StyleBook correspondence learning, and arbitrary-ratio synthesis. Extensive experiments on various conditional synthesis tasks, like super-resolution, sketch synthesis, and semantic synthesis, demonstrate superior performances over state-of-the-art image-to-image translation methods. Moreover, our model can easily generate megapixel images in diverse modalities by taking advantage of different pre-trained StyleGAN models.
BibTeX
@article{dai2025stylegan,
  author = {Yihua Dai and Tianyi Xiang and Bailin Deng and Yong Du and Hongmin Cai and Jing Qin and Shengfeng He},
  title = {{StyleGAN-$\textbackslash\{\}infty$∞: Extending StyleGAN to Arbitrary-Ratio Translation With StyleBook}},
  journal = {IEEE Trans. Vis. Comput. Graph.},
  year = {2025},
  url = {https://openreview.net/forum?id=QGdMyO8jqG},
}

Loading related content...

Figure