StyleSAN-XL

Reported on 5 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical5 results

Image GenerationonFFHQ 256 x 256
FID· 2023-01-30
1.68
SOTA
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer arXiv:2301.12811
Image GenerationonFFHQ 1024 x 1024
FID· 2023-01-30
1.61
SOTA
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer arXiv:2301.12811
Image GenerationonFFHQ 512 x 512
FID· 2023-01-30
1.77
SOTA
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer arXiv:2301.12811
Image GenerationonCIFAR-10
FID· 2023-01-30
1.36
best: 1.22 (GMem)
SOTA
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer arXiv:2301.12811
Image GenerationonImageNet 256x256
FID· 2023-01-30
2.14
best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer arXiv:2301.12811