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/Lafite

Lafite

Reported on 24 benchmarks across 4 tasks · 1 paper · 20 SOTA

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

Audio12 results

  • 10-shot image generationonCOCO (Common Objects in Context)
    FID· 2021-11-27
    8.12
    best: 5 (RAT-Diffusion)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 10-shot image generationonCOCO (Common Objects in Context)
    SOA-C· 2021-11-27
    61.09
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 10-shot image generationonMulti-Modal-CelebA-HQ
    FID· 2021-11-27
    12.54
    best: 10.31 (Swinv2-Imagen)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 10-shot image generationonCUB
    FID· uses extra data· 2021-11-27
    10.48
    best: 6.36 (RAT-Diffusion)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 10-shot image generationonCUB
    Inception score· uses extra data· 2021-11-27
    5.97
    best: 8.44 (Swinv2-Imagen)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 1 Image, 2*2 StitchionCOCO (Common Objects in Context)
    FID· 2021-11-27
    8.12
    best: 5 (RAT-Diffusion)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 1 Image, 2*2 StitchionCOCO (Common Objects in Context)
    SOA-C· 2021-11-27
    61.09
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 1 Image, 2*2 StitchionMulti-Modal-CelebA-HQ
    FID· 2021-11-27
    12.54
    best: 10.31 (Swinv2-Imagen)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 1 Image, 2*2 StitchionCUB
    FID· uses extra data· 2021-11-27
    10.48
    best: 6.36 (RAT-Diffusion)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 1 Image, 2*2 StitchionCUB
    Inception score· uses extra data· 2021-11-27
    5.97
    best: 8.44 (Swinv2-Imagen)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 10-shot image generationonCOCO (Common Objects in Context)
    Inception score· 2021-11-27
    32.34
    best: 34.67 (FuseDream (k=10, 256))
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • 1 Image, 2*2 StitchionCOCO (Common Objects in Context)
    Inception score· 2021-11-27
    32.34
    best: 34.67 (FuseDream (k=10, 256))
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792

Medical6 results

  • Image GenerationonCOCO (Common Objects in Context)
    FID· 2021-11-27
    8.12
    best: 5 (RAT-Diffusion)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Image GenerationonCOCO (Common Objects in Context)
    SOA-C· 2021-11-27
    61.09
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Image GenerationonCUB
    FID· uses extra data· 2021-11-27
    10.48
    best: 6.36 (RAT-Diffusion)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Image GenerationonCUB
    Inception score· uses extra data· 2021-11-27
    5.97
    best: 8.44 (Swinv2-Imagen)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Image GenerationonMulti-Modal-CelebA-HQ
    FID· 2021-11-27
    12.54
    best: 10.31 (Swinv2-Imagen)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Image GenerationonCOCO (Common Objects in Context)
    Inception score· 2021-11-27
    32.34
    best: 34.67 (FuseDream (k=10, 256))
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792

Natural Language Processing6 results

  • Text-to-Image GenerationonCOCO (Common Objects in Context)
    FID· 2021-11-27
    8.12
    best: 5 (RAT-Diffusion)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Text-to-Image GenerationonCOCO (Common Objects in Context)
    SOA-C· 2021-11-27
    61.09
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Text-to-Image GenerationonCUB
    FID· uses extra data· 2021-11-27
    10.48
    best: 6.36 (RAT-Diffusion)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Text-to-Image GenerationonCUB
    Inception score· uses extra data· 2021-11-27
    5.97
    best: 8.44 (Swinv2-Imagen)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Text-to-Image GenerationonMulti-Modal-CelebA-HQ
    FID· 2021-11-27
    12.54
    best: 10.31 (Swinv2-Imagen)
    SOTA
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792
  • Text-to-Image GenerationonCOCO (Common Objects in Context)
    Inception score· 2021-11-27
    32.34
    best: 34.67 (FuseDream (k=10, 256))
    LAFITE: Towards Language-Free Training for Text-to-Image GenerationarXiv:2111.13792