The dataset consists of 16,130 high-quality images with a resolution of 512×512.
There are three class domains, each providing about 5,000 images. By having three different images of different varieties in each domain, AFHQ poses a challenging image-to-image translation problem. The categories are:

• cat;
• dog;
• Wild animals.

Dataset reference

@inproceedings{choi2020starganv2,
title={StarGAN v2: Diverse Image Synthesis for Multiple Domains},
author={Yunjey Choi and Youngjung Uh and Jaejun Yoo and Jung-Woo Ha},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year={2020}
}