Image Generation On Afhq Dog
评估指标
FID
clean-FID
clean-KID
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||||
|---|---|---|---|---|---|
| DDMI | 8.54 | - | - | DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations | |
| StyleGAN2-ADA | 7.41 | 7.61 ± .02 | 1.28 ± .02 | Training Generative Adversarial Networks with Limited Data | |
| Diffusion InsGen | 4.83 | - | - | Diffusion-GAN: Training GANs with Diffusion | |
| Vision-aided GAN | 4.60 | 4.73 ± .02 | 0.38 ± .01 | Ensembling Off-the-shelf Models for GAN Training | |
| Projected GAN | 4.52 | - | - | Projected GANs Converge Faster | |
| Stylegan2-ada (NVIDIA pre-trained) | - | - | - | Signature and Log-signature for the Study of Empirical Distributions Generated with GANs |
0 of 6 row(s) selected.