I can't use wd14-tagger，install onnxruntime-gpu error

[1998-BossLee]

macbook pro m1

I never used github until I used stable diffusion. I am in China，but I can access the Internet。 so it's probably not the net problem。I've tried many times, but I keep getting this error msg.

Can someone help me? Thank you。

the error msg is

Loading wd14-vit-v2-git model file from SmilingWolf/wd-v1-4-vit-tagger-v2
Installing onnxruntime
Error completing request
Arguments: (<PIL.Image.Image image mode=RGB size=512x512 at 0x3946DDF90>, '', False, '', '[name].[output_extension]', 'ignore', False, False, 'wd14-vit-v2-git', 0.35, '', '', False, False, True, '0_0, (o)_(o), +_+, +_-, ._., <o>_<o>, <|>_<|>, =_=, >_<, 3_3, 6_9, >_o, @_@, ^_^, o_o, u_u, x_x, |_|, ||_||', False, False) {}
Traceback (most recent call last):
  File "/Users/liyangjin/Desktop/AIDraw/stable-diffusion-webui/modules/call_queue.py", line 57, in f
    res = list(func(*args, **kwargs))
  File "/Users/liyangjin/Desktop/AIDraw/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/Users/liyangjin/Desktop/AIDraw/stable-diffusion-webui/extensions/stable-diffusion-webui-wd14-tagger/tagger/ui.py", line 69, in on_interrogate
    ratings, tags = interrogator.interrogate(image)
  File "/Users/liyangjin/Desktop/AIDraw/stable-diffusion-webui/extensions/stable-diffusion-webui-wd14-tagger/tagger/interrogator.py", line 275, in interrogate
    self.load()
  File "/Users/liyangjin/Desktop/AIDraw/stable-diffusion-webui/extensions/stable-diffusion-webui-wd14-tagger/tagger/interrogator.py", line 250, in load
    run_pip(f'install {package}', 'onnxruntime')
  File "/Users/liyangjin/Desktop/AIDraw/stable-diffusion-webui/launch.py", line 143, in run_pip
    return run(f'"{python}" -m pip {command} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}", live=live)
  File "/Users/liyangjin/Desktop/AIDraw/stable-diffusion-webui/launch.py", line 111, in run
    raise RuntimeError(message)
RuntimeError: Couldn't install onnxruntime.
Command: "/Library/Frameworks/Python.framework/Versions/3.10/bin/python3.10" -m pip install onnxruntime-gpu --prefer-binary
Error code: 1
stdout: <empty>
stderr: ERROR: Could not find a version that satisfies the requirement onnxruntime-gpu (from versions: none)
ERROR: No matching distribution found for onnxruntime-gpu



Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/gradio/routes.py", line 408, in run_predict
    output = await app.get_blocks().process_api(
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/gradio/blocks.py", line 1318, in process_api
    data = self.postprocess_data(fn_index, result["prediction"], state)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/gradio/blocks.py", line 1221, in postprocess_data
    self.validate_outputs(fn_index, predictions)  # type: ignore
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/gradio/blocks.py", line 1196, in validate_outputs
    raise ValueError(
ValueError: An event handler (f) didn't receive enough output values (needed: 4, received: 3).
Wanted outputs:
    [textbox, label, label, html]
Received outputs:
    [None, "", "<div class='error'>RuntimeError: Couldn&#x27;t install onnxruntime.
Command: &quot;/Library/Frameworks/Python.framework/Versions/3.10/bin/python3.10&quot; -m pip install onnxruntime-gpu --prefer-binary
Error code: 1
stdout: &lt;empty&gt;
stderr: ERROR: Could not find a version that satisfies the requirement onnxruntime-gpu (from versions: none)
ERROR: No matching distribution found for onnxruntime-gpu

</div><div class='performance'><p class='time'>Time taken: <wbr>5.51s</p></div>"]

[wh1te-moon]

Me too

[Bavoch]

same problem

[venshine]

same

[y-tsubuku]

I had the same issue on M1 chip.
I checked the cause, and apparently there was no onnxruntime corresponding to the M1 chip.
So, I resolved the issue with following steps.
I hope this will help someone.

# at the root of stable-diffusion-webui
# activate venv 
$ source venv/bin/activate

# install  onnxruntime for apple silicon
$ pip install onnxruntime-silicon

# start server as usual
$ ./webui.sh

[1998-BossLee]

thanks,I got help in the community for the first time and I will try to help others in the future

[qinguoliang]

这么说很好听

[HarrisonXLin]

thanky,It 's useful!

[1998-BossLee]

这么说很好听

当时是我第一次在github与人交流并且获得帮助，很激动。

[blessyul]

Hi there,
Im having trouble downloading the tagger models from huggingface, can you tell me the directionary of pasting the models to (such as wd-v1-4-vit-tagger-v2) that i can run wd14-tagger successfully?
That would be huuuuge help, thanks!!!;)