PytorchStreamReader failed reading zip archive:failed finding central directory

[MonsterMill]

Describe the bug

Hi,I'm following this video https://www.youtube.com/watch?v=Th-0oZjpDtk to deploy this diffuser on my AMD-GPU laptop,(python 3.10.8,Radeon 5600M),I started "save_onnx.py" and after it fetched 17 files,errors occurred(as reproduction)
Is this mean that I need to change the model? (now using waifu-diffusion from hugging face)
but, it also reports an UnicodeDecodeError mentioning that there exists an utf8 decode error.
thanks a lot for any replies.

Reproduction

Traceback (most recent call last):
File "F:\aihh\stable-diffusion-amd\diffusers-dml\src\diffusers\modeling_utils.py", line 71, in load_state_dict
return torch.load(checkpoint_file, map_location="cpu")
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 705, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 242, in init
super(_open_zipfile_reader, self).init(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "F:\aihh\stable-diffusion-amd\diffusers-dml\src\diffusers\modeling_utils.py", line 75, in load_state_dict
if f.read().startswith("version"):
UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 64: illegal multibyte sequence

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "F:\aihh\stable-diffusion-amd\diffusers-dml\examples\inference\save_onnx.py", line 16, in
pipe = StableDiffusionPipeline.from_pretrained("hakurei/waifu-diffusion", scheduler=lms, use_auth_token=True)
File "F:\aihh\stable-diffusion-amd\diffusers-dml\src\diffusers\pipeline_utils.py", line 248, in from_pretrained
loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
File "F:\aihh\stable-diffusion-amd\diffusers-dml\src\diffusers\modeling_utils.py", line 417, in from_pretrained
state_dict = load_state_dict(model_file)
File "F:\aihh\stable-diffusion-amd\diffusers-dml\src\diffusers\modeling_utils.py", line 87, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for 'C:\Users\dell/.cache\huggingface\diffusers\models--hakurei--waifu-diffusion\snapshots\cc452ee4c493761a0c5d6e92394729dbdcd2cb28\unet\diffusion_pytorch_model.bin' at 'C:\Users\dell/.cache\huggingface\diffusers\models--hakurei--waifu-diffusion\snapshots\cc452ee4c493761a0c5d6e92394729dbdcd2cb28\unet\diffusion_pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

Logs

No response

System Info

latest diffuser, python 3.10.8, AMD Radeon 5600M Graphics Card, Windows 11

[YehorI]

I have the same issue RX 5700XT ryzen 3600, python 3.10.6

Traceback (most recent call last):
File "F:\SD\diffusers-dml\src\diffusers\modeling_utils.py", line 71, in load_state_dict
return torch.load(checkpoint_file, map_location="cpu")
File "F:\SD\diffenv\lib\site-packages\torch\serialization.py", line 777, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
File "F:\SD\diffenv\lib\site-packages\torch\serialization.py", line 282, in init
super(_open_zipfile_reader, self).init(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "F:\SD\diffusers-dml\src\diffusers\modeling_utils.py", line 75, in load_state_dict
if f.read().startswith("version"):
File "F:\SD\diffenv\lib\encodings\cp1251.py", line 23, in decode
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
UnicodeDecodeError: 'charmap' codec can't decode byte 0x98 in position 2235: character maps to

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "F:\SD\diffusers-dml\examples\inference\save_onnx.py", line 16, in
pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", scheduler=lms, use_auth_token=True)
File "F:\SD\diffusers-dml\src\diffusers\pipeline_utils.py", line 248, in from_pretrained
loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
File "F:\SD\diffusers-dml\src\diffusers\modeling_utils.py", line 417, in from_pretrained
state_dict = load_state_dict(model_file)
File "F:\SD\diffusers-dml\src\diffusers\modeling_utils.py", line 87, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for 'C:\Users\Egor/.cache\huggingface\diffusers\models--CompVis--stable-diffusion-v1-4\snapshots\f15bc7606314c6fa957b4267bee417ee866c0b84\unet\diffusion_pytorch_model.bin' at 'C:\Users\Egor/.cache\huggingface\diffusers\models--CompVis--stable-diffusion-v1-4\snapshots\f15bc7606314c6fa957b4267bee417ee866c0b84\unet\diffusion_pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

[YehorI]

I redownload files and it fixed

[MonsterMill]

I redownload files and it fixed

thanks for the reply, I redownloaded it again and again and found it working on my vega 8 but not 5600M, it ran for seconds and my ram exploded(5600M‘s GPU-RAM does not have any occupation), seems that I can not choose which graphics card to run, poor AMD-GPU laptop : (