search

picobyte / stable-diffusion-webui-wd14-tagger

Labeling extension for Automatic1111's Web UI
580 stars 70 forks source link

WD14 moat tagger v2 and WD14 ConvNeXTV2 v1 are not working #33

Closed qxces closed 1 year ago

qxces commented 1 year ago

Traceback (most recent call last): File "D:\kal\sd\venv\lib\site-packages\gradio\routes.py", line 422, in run_predict output = await app.get_blocks().process_api( File "D:\kal\sd\venv\lib\site-packages\gradio\blocks.py", line 1326, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "D:\kal\sd\venv\lib\site-packages\gradio\blocks.py", line 1229, in postprocess_data self.validate_outputs(fn_index, predictions) # type: ignore File "D:\kal\sd\venv\lib\site-packages\gradio\blocks.py", line 1204, in validate_outputs raise ValueError( ValueError: An event handler (on_interrogate) didn't receive enough output values (needed: 6, received: 3). Wanted outputs: [html, html, label, label, label, html] Received outputs: [None, "", "

Fail: [ONNXRuntimeError] : 1 : FAIL : Load model from F:\hf\models--SmilingWolf--wd-v1-4-moat-tagger-v2\snapshots\8452cddf280b952281b6e102411c50e981cb2908\model.onnx failed:D:\a_work\1\s\onnxruntime\core/graph/model_load_utils.h:57 onnxruntime::model_load_utils::ValidateOpsetForDomain ONNX Runtime only guarantees support for models stamped with official released onnx opset versions. Opset 18 is under development and support for this is limited. The operator schemas and or other functionality may change before next ONNX release and in this case ONNX Runtime will not guarantee backward compatibility. Current official support for domain com.ms.internal.nhwc is till opset 17.

Time taken: 0.8 sec.

A: 2.19 GB, R: 2.20 GB, Sys: 4.0/6 GB (67.4%)

"]

picobyte commented 1 year ago

It is working here. Do you have the current git version? it could be due to more recent fixes.

Maybe you have something at your side, file corruption or so?

Does this file F:\hf\models--SmilingWolf--wd-v1-4-moat-tagger-v2\snapshots\8452cddf280b952281b6e102411c50e981cb2908\model.onnx exist on your system and is it ok?