Image Generation On Afhq Cat
Metrics
FID
clean-FID
clean-KID
Results
Performance results of various models on this benchmark
Model Name | FID | clean-FID | clean-KID | Paper Title | Repository |
|---|---|---|---|---|---|
| Vision-aided GAN | 2.44 | 2.51 ± .02 | 0.46 ± .03 | Ensembling Off-the-shelf Models for GAN Training | - |
| CLR-GAN | 4.45 | - | - | CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction | |
| Stylegan2-ada (NVIDIA pre-trained) | - | - | - | Signature and Log-signature for the Study of Empirical Distributions Generated with GANs | - |
| StyleGAN2-ADA | 3.55 | 3.28 ± .02 | 0.71 ± .02 | Training Generative Adversarial Networks with Limited Data | - |
| DDMI | 4.27 | - | - | DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations | - |
| BOSS | - | 22.2 | - | Bellman Optimal Stepsize Straightening of Flow-Matching Models | - |
| Projected GAN | 2.16 | - | - | Projected GANs Converge Faster | - |
| Diffusion InsGen | 2.40 | - | - | Diffusion-GAN: Training GANs with Diffusion | - |
0 of 8 row(s) selected.