Comment Comment by brucethemoose2 Are y'all running the diffusion in PyTorch eager mode?AITemplate, stable-fast, or even a torch.compile could get that down to 60ms, I bet. Though I'm not sure the example implementations would work on a non SD architecture. parent brucethemoose2 3 years ago
AITemplate, stable-fast, or even a torch.compile could get that down to 60ms, I bet. Though I'm not sure the example implementations would work on a non SD architecture.