Open Aleksoooxd opened 1 month ago
May be the models from buffalo_l are damaged? I have the similar problem when using the models downloaded by powershell. I fixed it by directly download the models from the official website.
Yep, that was it. Still getting a blue screen after couple second though :/
Figured out the models from buffalo_I are getting damaged after each blue screen. STOPCODE: IRQL_NOT_LESS_OR_EQUAL Source: ntoskrnl.exe
I am facing a similliar issue, my output is:
Deep-Live-Cam/models/inswapper_128_fp16.onnx failed:Protobuf parsing failed.
The live view is a black screen due to this issue.
我面临一个类似的问题,我的输出是:由于这个问题,实时视图是黑屏。
Deep-Live-Cam/models/inswapper_128_fp16.onnx failed:Protobuf parsing failed.
me too
mine was working fine then suddenly stopped working, the live feed halted but the ui was ok. after restarting the ui it gives me this error.
I had model files in modules folder(similar, but wrong) (Deep-Live-Cam-main\models is correct, Deep-Live-Cam-main\modules is incorrect)
Traceback (most recent call last): File "C:\Program Files\Python311\Lib\tkinter__init.py", line 1948, in call return self.func(*args) ^^^^^^^^^^^^^^^^ File "Deep-Live-Cam\venv\Lib\site-packages\customtkinter\windows\widgets\ctk_button.py", line 554, in _clicked self._command() File "Deep-Live-Cam\modules\ui.py", line 104, in
live_button = ctk.CTkButton(root, text='Live', cursor='hand2', command=lambda: webcam_preview())
^^^^^^^^^^^^^^^^
File "Deep-Live-Cam\modules\ui.py", line 281, in webcam_preview
source_image = get_one_face(cv2.imread(modules.globals.source_path))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Deep-Live-Cam\modules\face_analyser.py", line 20, in get_one_face
face = get_face_analyser().get(frame)
^^^^^^^^^^^^^^^^^^^
File "Deep-Live-Cam\modules\face_analyser.py", line 14, in get_face_analyser
FACE_ANALYSER = insightface.app.FaceAnalysis(name='buffalo_l', providers=modules.globals.execution_providers)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Deep-Live-Cam\venv\Lib\site-packages\insightface\app\face_analysis.py", line 31, in init
model = model_zoo.get_model(onnx_file, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Deep-Live-Cam\venv\Lib\site-packages\insightface\model_zoo\model_zoo.py", line 96, in get_model
model = router.get_model(providers=providers, provider_options=provider_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Deep-Live-Cam\venv\Lib\site-packages\insightface\model_zoo\model_zoo.py", line 40, in get_model
session = PickableInferenceSession(self.onnx_file, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Deep-Live-Cam\venv\Lib\site-packages\insightface\model_zoo\model_zoo.py", line 25, in init
super().init(model_path, **kwargs)
File "Deep-Live-Cam\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 419, in init__
self._create_inference_session(providers, provider_options, disabled_optimizers)
File "Deep-Live-Cam\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 452, in _create_inference_session
sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
onnxruntime.capi.onnxruntime_pybind11_state.InvalidProtobuf: [ONNXRuntimeError] : 7 : INVALID_PROTOBUF : Load model from User/.insightface\models\buffalo_l\1k3d68.onnx failed:Protobuf parsing failed.
At first i forgot to install ffmpeg so while waiting for it to install i ran the program after I've commented the pre_check line which responds for checking if ffmpeg is installed. It worked fine, besides the fact that i had a black square instead of the face i wantet and it was quite laggy but after a few second i got a blue screen. So now I finally installed ffmpeg and while the "launcher" works just fine the preview obviously doesnt really load as the error would suggest. Anyone had a similar problem/ knows the fix to this issue?