Using with Automatic1111's WebUI
[Error: RuntimeError: Error(s) in loading state_dict for LatentDiffusion:](RuntimeError: Error(s) in loading state_dict for LatentDiffusion:
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]).)
Same...
Same...
I've got it working with a fork: https://github.com/acheong08/stable-diffusion-webui
Same...
I've got it working with a fork: https://github.com/acheong08/stable-diffusion-webui
It doesnt work for me.
Any solution?
I had the same issue. You need to update to the latest version of stable diffusion. I had to remove "--xformers" from the command line in the launch.py file and pull the repository again to actually update.
In which line do i have to remove xformers parameter ??
I found the solution: If you rename the file "sd-v1-5-inpainting.ckpt" in any case the new filename must end with "inpainting.ckpt" (sd-inpainting.ckpt for example)
I found the solution: If you rename the file "sd-v1-5-inpainting.ckpt" in any case the new filename must end with "inpainting.ckpt" (sd-inpainting.ckpt for example)
Thank you, this worked for me.