Looking for help after "install"

[MarkusAmbrus]

Describe the bug
I followed the steps to get the repo but when starting the .bat file I get some error and the sd-webui does not start.
Maybe some experienced guys can point me into the right direction (and even tell me, if this is the right place to ask for such help smile)
Thanks for your time.

To Reproduce
The error output...

venv "E:...\WebUI\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: 3f41756
Installing requirements for Web UI
Launching Web UI with arguments: --medvram
Warning: LDSR not found at path E:...\WebUI\stable-diffusion-webui\repositories\latent-diffusion\LDSR.py
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla' with 512 in_channels
Traceback (most recent call last):
File "E:...\WebUI\stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py", line 392, in load_state_dict
return torch.load(checkpoint_file, map_location="cpu")
File "E:...\WebUI\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 705, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
File "E:...\WebUI\stable-diffusion-webui\venv\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 "E:...\WebUI\stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py", line 396, in load_state_dict
if f.read().startswith("version"):
File "C:...\AppData\Local\Programs\Python\Python310\lib\encodings\cp1252.py", line 23, in decode
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 2077: character maps to

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "E:...\WebUI\stable-diffusion-webui\launch.py", line 139, in
start_webui()
File "E:...\WebUI\stable-diffusion-webui\launch.py", line 135, in start_webui
import webui
File "E:...\WebUI\stable-diffusion-webui\webui.py", line 77, in
shared.sd_model = modules.sd_models.load_model()
File "E:...\WebUI\stable-diffusion-webui\modules\sd_models.py", line 146, in load_model
sd_model = instantiate_from_config(sd_config.model)
File "E:...\WebUI\stable-diffusion-webui\repositories\stable-diffusion\ldm\util.py", line 85, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "E:...\WebUI\stable-diffusion-webui\repositories\stable-diffusion\ldm\models\diffusion\ddpm.py", line 461, in init
self.instantiate_cond_stage(cond_stage_config)
File "E:...\WebUI\stable-diffusion-webui\repositories\stable-diffusion\ldm\models\diffusion\ddpm.py", line 519, in instantiate_cond_stage
model = instantiate_from_config(config)
File "E:...\WebUI\stable-diffusion-webui\repositories\stable-diffusion\ldm\util.py", line 85, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "E:...\WebUI\stable-diffusion-webui\repositories\stable-diffusion\ldm\modules\encoders\modules.py", line 142, in init
self.transformer = CLIPTextModel.from_pretrained(version)
File "E:...\WebUI\stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py", line 1978, in from_pretrained
state_dict = load_state_dict(resolved_archive_file)
File "E:...\WebUI\stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py", line 408, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for 'C:\Users\marku/.cache\huggingface\transformers\c506559a5367a918bab46c39c79af91ab88846b49c8abd9d09e699ae067505c6.6365d436cc844f2f2b4885629b559d8ff0938ac484c01a6796538b2665de96c7' at 'C:\Users\marku/.cache\huggingface\transformers\c506559a5367a918bab46c39c79af91ab88846b49c8abd9d09e699ae067505c6.6365d436cc844f2f2b4885629b559d8ff0938ac484c01a6796538b2665de96c7'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
Press any key to continue . . .

[MarkusAmbrus]

As you can see from the output - it is trying to find/run LDSR ... so there might be something pointing into the wrong direction?

[MarkusAmbrus]

I am running a system with core i7, 16gb ram, nvidia gtx1050 ti 4gb vram, with windows 10

[dovezp]

OSError: Unable to load weights from pytorch checkpoint file for 'C:\Users\marku/.cache\huggingface\transformers\
Try to install transformers again via pip https://huggingface.co/docs/transformers/installation

[dovezp]

As you can see from the output - it is trying to find/run LDSR ... so there might be something pointing into the wrong direction?

Refer to #1406 for storing the LDSR model.

[akx]

Closing as stale.