DiffiT

Reported on 3 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.

Medical3 results

Image GenerationonImageNet 512x512
FID· 2023-12-04
2.67
best: 1.21 (EDM2-L + DDO (SD-VAE, 25 steps, DPM-Solver-v3))
DiffiT: Diffusion Vision Transformers for Image Generation arXiv:2312.02139
Image GenerationonImageNet 512x512
Inception score· 2023-12-04
252.12
best: 350.2 (DPC-U)
DiffiT: Diffusion Vision Transformers for Image Generation arXiv:2312.02139
Image GenerationonImageNet 256x256
FID· 2023-12-04
1.73
best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
DiffiT: Diffusion Vision Transformers for Image Generation arXiv:2312.02139