Why does the sampler report an error after I load the ControlNet model v3
#25
by
SY2king
- opened
Error while processing rearrange-reduction pattern "b c (h ph) (w pw) -> b (h w) (c ph pw)".
Input tensor shape: torch.Size([1, 16, 91, 109]). Additional info: {'ph': 2, 'pw': 2}.
Shape mismatch, can't divide axis of length 91 in chunks of 2
similar problem here but circumvented by using empty latent
can you expand on that