You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Recently, I have been unable to recreate the image using the same prompt and seed, using two loras and the gguf q8 flux 1 dev model, I often see these errors in the console:
webui\backend\operations_gguf.py:36: 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).
return super().new(cls, torch.tensor(tensor.data), requires_grad=requires_grade)
Recently, I have been unable to recreate the image using the same prompt and seed, using two loras and the gguf q8 flux 1 dev model, I often see these errors in the console:
webui\backend\operations_gguf.py:36: 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).
return super().new(cls, torch.tensor(tensor.data), requires_grad=requires_grade)
ERROR lora diffusion_model.double_blocks.9.txt_mlp.2.weight
ERROR lora diffusion_model.single_blocks.37.linear2.weight
RTX 2080 Ti (11 gb. VRAM), 32gb. RAM, Windows 10.
The problems started on the 11th, before that everything worked fine
The text was updated successfully, but these errors were encountered: