TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/simple diffusion (U-Net)

simple diffusion (U-Net)

Reported on 7 benchmarks across 2 tasks · 1 paper

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

Medical5 results

  • Image GenerationonImageNet 512x512
    FID· 2023-01-26
    4.28
    best: 1.21 (EDM2-L + DDO (SD-VAE, 25 steps, DPM-Solver-v3))
    Simple diffusion: End-to-end diffusion for high resolution imagesarXiv:2301.11093
  • Image GenerationonImageNet 512x512
    Inception score· 2023-01-26
    171
    best: 350.2 (DPC-U)
    Simple diffusion: End-to-end diffusion for high resolution imagesarXiv:2301.11093
  • Image GenerationonImageNet 256x256
    FID· 2023-01-26
    3.71
    best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
    Simple diffusion: End-to-end diffusion for high resolution imagesarXiv:2301.11093
  • Image GenerationonImageNet 128x128
    FID· 2023-01-26
    2.88
    best: 1.26 (SiD2)
    Simple diffusion: End-to-end diffusion for high resolution imagesarXiv:2301.11093
  • Image GenerationonImageNet 128x128
    Inception score· 2023-01-26
    137.3
    best: 262.85 (Omni-INR-GAN)
    Simple diffusion: End-to-end diffusion for high resolution imagesarXiv:2301.11093

Computer Vision2 results

  • Conditional Image GenerationonImageNet 128x128
    FID· 2023-01-26
    2.88
    best: 2.19 (EluCD_DDPM)
    Simple diffusion: End-to-end diffusion for high resolution imagesarXiv:2301.11093
  • Conditional Image GenerationonImageNet 128x128
    Inception score· 2023-01-26
    137.3
    best: 262.85 (Omni-INR-GAN)
    Simple diffusion: End-to-end diffusion for high resolution imagesarXiv:2301.11093