LFM

Reported on 5 benchmarks across 1 task · 1 paper

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· 2023-07-17
4.55
best: 1.68 (StyleSAN-XL)
Flow Matching in Latent Space arXiv:2307.08698
Image GenerationonLSUN Bedroom 256 x 256
FID· 2023-07-17
4.92
best: 1.43 (Diffusion ProjectedGAN)
Flow Matching in Latent Space arXiv:2307.08698
Image GenerationonCelebA-HQ 256x256
FID· 2023-07-17
5.26
best: 3.15 (RDM)
Flow Matching in Latent Space arXiv:2307.08698
Image GenerationonLSUN Churches 256 x 256
FID· 2023-07-17
5.54
best: 1.59 (Projected GAN)
Flow Matching in Latent Space arXiv:2307.08698
Image GenerationonImageNet 256x256
FID· 2023-07-17
4.46
best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
Flow Matching in Latent Space arXiv:2307.08698