Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

size mismatch ... copying a param with shape torch.Size([320, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 4, 3, 3]) #17

Open
chavinlo opened this issue Oct 4, 2022 · 1 comment
Open

size mismatch ... copying a param with shape torch.Size([320, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 4, 3, 3]) #17

chavinlo opened this issue Oct 4, 2022 · 1 comment

Comments

@chavinlo
Copy link
Contributor

chavinlo commented Oct 4, 2022

Hello, sorry if I'm bothering you again but I have tried merging the resultant pt file (not trained from scratch, instead a few steps from your previous pt inpaint checkpoint), with the SD 1.4 model, but when loading the merged model into a webUI, auto1111 in this example, I always get the following error:


Loading weights [681cbf52] from /content/stable-diffusion-webui/models/Stable-diffusion/model.ckpt
Global Step: 470000
Traceback (most recent call last):
  File "launch.py", line 143, in <module>
    start_webui()
  File "launch.py", line 139, in start_webui
    import webui
  File "/content/stable-diffusion-webui/webui.py", line 78, in <module>
    shared.sd_model = modules.sd_models.load_model()
  File "/content/stable-diffusion-webui/modules/sd_models.py", line 147, in load_model
    load_model_weights(sd_model, checkpoint_info.filename, checkpoint_info.hash)
  File "/content/stable-diffusion-webui/modules/sd_models.py", line 127, in load_model_weights
    model.load_state_dict(sd, strict=False)
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1605, in load_state_dict
    self.__class__.__name__, "\n\t".join(error_msgs)))
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, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 4, 3, 3]).

I think this has something to do with the architecture your trainer and the normal finetuning use? I'm not an expert.
@Jack000
Copy link
Owner

Jack000 commented Oct 4, 2022

the inpaint model isn't compatible with other SD tools unfortunately. The unet has a slightly different architecture.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Jack000 @chavinlo