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/StackGAN-v2

StackGAN-v2

Reported on 17 benchmarks across 4 tasks · 1 paper · 17 SOTA

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

Audio8 results

  • 10-shot image generationonOxford 102 Flowers
    FID· 2017-10-19
    48.68
    best: 9.52 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • 10-shot image generationonOxford 102 Flowers
    Inception score· 2017-10-19
    3.26
    best: 4.35 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • 10-shot image generationonCUB
    FID· 2017-10-19
    15.3
    best: 6.36 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • 10-shot image generationonCUB
    Inception score· 2017-10-19
    3.82
    best: 8.44 (Swinv2-Imagen)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • 1 Image, 2*2 StitchionOxford 102 Flowers
    FID· 2017-10-19
    48.68
    best: 9.52 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • 1 Image, 2*2 StitchionOxford 102 Flowers
    Inception score· 2017-10-19
    3.26
    best: 4.35 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • 1 Image, 2*2 StitchionCUB
    FID· 2017-10-19
    15.3
    best: 6.36 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • 1 Image, 2*2 StitchionCUB
    Inception score· 2017-10-19
    3.82
    best: 8.44 (Swinv2-Imagen)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916

Medical5 results

  • Image GenerationonLSUN Bedroom 256 x 256
    FID· 2017-10-19
    35.61
    best: 1.43 (Diffusion ProjectedGAN)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • Image GenerationonOxford 102 Flowers
    FID· 2017-10-19
    48.68
    best: 9.52 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • Image GenerationonOxford 102 Flowers
    Inception score· 2017-10-19
    3.26
    best: 4.35 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • Image GenerationonCUB
    FID· 2017-10-19
    15.3
    best: 6.36 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • Image GenerationonCUB
    Inception score· 2017-10-19
    3.82
    best: 8.44 (Swinv2-Imagen)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916

Natural Language Processing4 results

  • Text-to-Image GenerationonOxford 102 Flowers
    FID· 2017-10-19
    48.68
    best: 9.52 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • Text-to-Image GenerationonOxford 102 Flowers
    Inception score· 2017-10-19
    3.26
    best: 4.35 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • Text-to-Image GenerationonCUB
    FID· 2017-10-19
    15.3
    best: 6.36 (RAT-Diffusion)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916
  • Text-to-Image GenerationonCUB
    Inception score· 2017-10-19
    3.82
    best: 8.44 (Swinv2-Imagen)
    SOTA
    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial NetworksarXiv:1710.10916