size mismatch for conv_in.weight: copying a param with shape torch.Size([320, 9, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 4, 3, 3]).

[Hrushi11]

Facing this error when running the script on every .safetensor file

[haofanwang]

It seems that you are loading an inpainting model weight into a normal text-to-image model.