Issues running with Automatic1111

#8
by papamonster - opened

Meium model having issues with Automatic1111 WebUI

changing setting sd_model_checkpoint to sd3.5_medium.safetensors [11fe06e223]: RuntimeError
Traceback (most recent call last):
File "/stable-diffusion-webui/modules/options.py", line 165, in set
option.onchange()
File "/stable-diffusion-webui/modules/call_queue.py", line 13, in f
res = func(*args, **kwargs)
File "/stable-diffusion-webui/modules/initialize_util.py", line 181, in
shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: sd_models.reload_model_weights()), call=False)
File "/stable-diffusion-webui/modules/sd_models.py", line 879, in reload_model_weights
load_model(checkpoint_info, already_loaded_state_dict=state_dict)
File "/stable-diffusion-webui/modules/sd_models.py", line 748, in load_model
load_model_weights(sd_model, checkpoint_info, state_dict, timer)
File "/stable-diffusion-webui/modules/sd_models.py", line 393, in load_model_weights
model.load_state_dict(state_dict, strict=False)
File "/stable-diffusion-webui/modules/sd_disable_initialization.py", line 223, in
module_load_state_dict = self.replace(torch.nn.Module, 'load_state_dict', lambda *args, **kwargs: load_state_dict(module_load_state_dict, *args, **kwargs))
File "/stable-diffusion-webui/modules/sd_disable_initialization.py", line 221, in load_state_dict
original(module, state_dict, strict=strict)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2189, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for LatentDiffusion:
size mismatch for first_stage_model.encoder.conv_out.weight: copying a param with shape torch.Size([32, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([8, 512, 3, 3]).
size mismatch for first_stage_model.encoder.conv_out.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([8]).
size mismatch for first_stage_model.decoder.conv_in.weight: copying a param with shape torch.Size([512, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 4, 3, 3]).

Ok Ladies & Gents: we had the same problem in ComfyUI, fixed by updating the Torch and deps.

UPDOOT:

if you update Torch to 2.5.1, Torchvision to 0.20.1, Torchaudio to 2.5.1 and also Transformers to 4.46.1-py3-none-any.whl

  • it works
  • please include this in the model page instructions somewhere?

This has fixed the Issue :)

Sign up or log in to comment