conversion from .ckpt failing

[ellugia]

hi, got this error while trying to convert a .ckpt packet to onnx:

(virtualenv) D:\stable_diff>python convert_original_stable_diffusion_to_diffusers.py --checkpoint_path=".\weri-diffusion.ckpt" --dump_path=".\weri-diffusion_diffusers"
Traceback (most recent call last):
  File "D:\stable_diff\convert_original_stable_diffusion_to_diffusers.py", line 798, in <module>
    checkpoint = torch.load(args.checkpoint_path)
  File "D:\stable_diff\virtualenv\lib\site-packages\torch\serialization.py", line 789, in load
    return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
  File "D:\stable_diff\virtualenv\lib\site-packages\torch\serialization.py", line 1131, in _load
    result = unpickler.load()
  File "D:\stable_diff\virtualenv\lib\site-packages\torch\serialization.py", line 1101, in persistent_load
    load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
  File "D:\stable_diff\virtualenv\lib\site-packages\torch\serialization.py", line 1083, in load_tensor
    wrap_storage=restore_location(storage, location),
  File "D:\stable_diff\virtualenv\lib\site-packages\torch\serialization.py", line 215, in default_restore_location
    result = fn(storage, location)
  File "D:\stable_diff\virtualenv\lib\site-packages\torch\serialization.py", line 182, in _cuda_deserialize
    device = validate_cuda_device(location)
  File "D:\stable_diff\virtualenv\lib\site-packages\torch\serialization.py", line 166, in validate_cuda_device
    raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

the model I'm trying to convert is https://huggingface.co/joujiboi/Weri-Diffusion

[azuritecoin]

You need to modify one line in the convert_original_stable_diffusion_to_diffusers.py script. On line 798 in the conversion script change this:
checkpoint = torch.load(args.checkpoint_path)
to this:
checkpoint = torch.load(args.checkpoint_path, map_location=torch.device('cpu'))

That should bypass the error.