@[email protected] to [email protected] • 8 months agoNot all ai is bad, just most of itslrpnk.netimagemessage-square181fedilinkarrow-up11.56Karrow-down134
arrow-up11.53Karrow-down1imageNot all ai is bad, just most of itslrpnk.net@[email protected] to [email protected] • 8 months agomessage-square181fedilink
minus-square@[email protected]linkfedilink7•8 months agoI suppose both plantnet and deep fakes have conv networks as part of their architectures though
minus-square@[email protected]linkfedilink2•8 months agoLikely transformers now (I think SD3 uses a ViT for text encoding, and ViTs are currently one of the best model architectures for image classification).
I suppose both plantnet and deep fakes have conv networks as part of their architectures though
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).