</> Code with Papers by Syntology

Datasets › AFHQ

AFHQ (Animal Faces-HQ)

Introduced by Yunjey Choi et al. in StarGAN v2: Diverse Image Synthesis for Multiple Domains4 Dec 2019 archive 2025-07-28

Animal FacesHQ (AFHQ) is a dataset of animal faces consisting of 15,000 high-quality images at 512 × 512 resolution. The dataset includes three domains of cat, dog, and wildlife, each providing 5000 images. By having multiple (three) domains and diverse images of various breeds (≥ eight) per each domain, AFHQ sets a more challenging image-to-image translation problem. All images are vertically and horizontally aligned to have the eyes at the center. The low-quality images were discarded by human effort.

Source: StarGAN v2: Diverse Image Synthesis for Multiple Domains

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 6 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Generation AFHQ Cat Vision-aided GAN clean-KID 0.46 ± .03 Ensembling Off-the-shelf Models for GAN Training nupurkmr9/vision-aided-gan 8 Compare
Image Generation AFHQV2 Polarity-StyleGAN3 FID 3.95 Polarity Sampling: Quality and Diversity Control of... AhmedImtiazPrio/magnet-polarity 7 Compare
Image Generation AFHQ Dog Projected GAN FID 4.52 Projected GANs Converge Faster autonomousvision/projected_gan +2 6 Compare
Image Generation AFHQ Wild Vision-aided GAN clean-KID 0.38 ± .02 Ensembling Off-the-shelf Models for GAN Training nupurkmr9/vision-aided-gan 5 Compare
Multimodal Unsupervised Image-To-Image Translation AFHQ StarGAN v2 FID 16.2 StarGAN v2: Diverse Image Synthesis for Multiple Domains clovaai/stargan-v2 +13 4 Compare
Image-to-Image Translation AFHQ StarGAN v2 LPIPS 0.524 StarGAN v2: Diverse Image Synthesis for Multiple Domains clovaai/stargan-v2 +13 2 Compare

Papers archive 2025-07-28

16 shown of 16 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 327. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction 1 1 30 Sep 2024 not harvested
DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations 1 2 23 Jan 2024 ran 17 of 21 samples (4 unverified)
Bellman Optimal Stepsize Straightening of Flow-Matching Models 1 1 27 Dec 2023 ran 8 of 14 samples (6 unverified; 14 pointer-only for licence)
Class-Continuous Conditional Generative Neural Radiance Field 1 1 3 Jan 2023 not harvested
GENIE: Higher-Order Denoising Diffusion Solvers 1 3 11 Oct 2022 not harvested
Diffusion-GAN: Training GANs with Diffusion 4 3 5 Jun 2022 ran 13 of 18 samples (5 unverified)
Signature and Log-signature for the Study of Empirical Distributions Generated with GANs 1 3 7 Mar 2022 not harvested
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values 1 1 3 Mar 2022 not harvested
Ensembling Off-the-shelf Models for GAN Training 1 3 16 Dec 2021 ran 9 of 15 samples (6 unverified)
Projected GANs Converge Faster 3 3 1 Nov 2021 ran 38 of 49 samples (11 unverified; 6 pointer-only for licence)
Alias-Free Generative Adversarial Networks 7 3 23 Jun 2021 ran 18 of 31 samples (13 unverified; 9 pointer-only for licence)
Training Generative Adversarial Networks with Limited Data 28 3 11 Jun 2020 ran 5 of 29 samples (24 unverified; 4 pointer-only for licence)
StarGAN v2: Diverse Image Synthesis for Multiple Domains 14 2 4 Dec 2019 ran 0 of 5 samples (5 unverified)
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis 2 1 13 Mar 2019 not harvested
Diverse Image-to-Image Translation via Disentangled Representations 7 1 2 Aug 2018 not harvested
Multimodal Unsupervised Image-to-Image Translation 13 1 12 Apr 2018 ran 0 of 5 samples (5 unverified)

Dataset loaders archive 2025-07-28

clovaai/stargan-v2pytorch

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Image GenerationImage-to-Image TranslationMultimodal Unsupervised Image-To-Image Translation

License archive 2025-07-28

CC BY-NC 4.0

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • AFHQ
  • AFHQV2
  • AFHQ Dog
  • AFHQ Cat
  • AFHQ Wild
  • AFHQcat2dog

6 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections