google

/

ncsnpp-ffhq-256

like 2

Befor the model starts to generate, I am getting this warning:

hon3.9/site-packages/diffusers/models/resnet.py:368: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
  torch.tensor(kernel, device=hidden_states.device),
/home/user/.conda/envs/lib/python3.9/site-packages/diffusers/models/resnet.py:294: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).

My installed packages:

denoising-diffusion-pytorch  1.5.8
ema-pytorch                  0.1.4
pytorch-fid                  0.3.0
pytorch-lightning            1.8.0
torch                        2.0.1
torch-tb-profiler            0.4.1
torchmetrics                 0.11.4
torchvision                  0.15.2
diffusers                    0.16.1