Image Generation On Lsun Horse 256 X 256
Metrics
Clean-FID (trainfull)
Results
Performance results of various models on this benchmark
Model Name | Clean-FID (trainfull) | Paper Title | Repository |
---|---|---|---|
PGGAN | 14.09 ± 0.06 | Progressive Growing of GANs for Improved Quality, Stability, and Variation | - |
Vision-aided GAN | 2.11 | Ensembling Off-the-shelf Models for GAN Training | - |
StyleGAN2 | 4.06 ± 0.03 | Analyzing and Improving the Image Quality of StyleGAN | - |
Projected GAN | - | Projected GANs Converge Faster | - |
StyleGAN | 4.78 ± 0.03 | A Style-Based Generator Architecture for Generative Adversarial Networks | - |
ADM (dropout) | - | Diffusion Models Beat GANs on Image Synthesis | - |
0 of 6 row(s) selected.