RuntimeError: Error(s) in loading state_dict for ControlInferenceLDM:
size mismatch for model.diffusion_model.input_blocks.0.0.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]).
I assume any checkpoint which is based on sd1.5 can be used, so what is the reason for this error?
while trying to load the epiCRealism (https://civitai.com/models/25694?modelVersionId=143906) checkpoint instead of the sd1.5, I get this error:
I assume any checkpoint which is based on sd1.5 can be used, so what is the reason for this error?