Image Generation On Celeba Hq 1024X1024
Metrics
FID
Results
Performance results of various models on this benchmark
Model Name | FID | Paper Title | Repository |
---|---|---|---|
Polarity-ProGAN | 7.28 | Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values | - |
WaveDiff | 5.98 | Wavelet Diffusion Models are fast and scalable Image Generators | - |
PG-SWGAN | 5.5 | Sliced Wasserstein Generative Models | - |
HiT-B | 8.83 | Improved Transformer for High-Resolution GANs | - |
PGGAN | 7.3 | Progressive Growing of GANs for Improved Quality, Stability, and Variation | - |
Efficient-VDVAE | - | Efficient-VDVAE: Less is more | - |
MSG-StyleGAN | 6.37 | MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks | - |
StyleSwin | 4.43 | StyleSwin: Transformer-based GAN for High-resolution Image Generation | - |
StyleGAN | 5.06 | A Style-Based Generator Architecture for Generative Adversarial Networks | - |
COCO-GAN | 9.49 | COCO-GAN: Generation by Parts via Conditional Coordinating | - |
0 of 10 row(s) selected.