• @[email protected]
    link
    fedilink
    78 months ago

    I suppose both plantnet and deep fakes have conv networks as part of their architectures though

    • @[email protected]
      link
      fedilink
      28 months ago

      Likely transformers now (I think SD3 uses a ViT for text encoding, and ViTs are currently one of the best model architectures for image classification).