correct configuration for sd-v1-4.ckpt
hey guys what i must setup to run everything smooth on my mac (intel)?
i install it like described and link aloso the model correct but i get few time this outtput if i wanna generate something:
size mismatch for text_model.final_layer_norm.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]).
where i must set what?
Same here, with the CPU patch (https://github.com/CompVis/stable-diffusion/pull/56).
size mismatch for text_model.final_layer_norm.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]).
Fixed by install transformers==4.19.2.
I already try to install many typies of transformers.but it seems not work.