search

numz / sd-wav2lip-uhq

Wav2Lip UHQ extension for Automatic1111
Apache License 2.0
1.23k stars 163 forks source link

Unexpected version found while deserializing dlib::shape_predictor #13

Closed Lesteriax closed 1 year ago

Lesteriax commented 1 year ago

Any way to get around his error?

Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/gradio/routes.py", line 422, in run_predict output = await app.get_blocks().process_api( File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1323, in process_api result = await self.call_function( File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1051, in call_function prediction = await anyio.to_thread.run_sync( File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 867, in run result = context.run(func, *args) File "/storage/stable-diffusion/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/ui.py", line 46, in generate w2luhq.execute() File "/storage/stable-diffusion/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/wav2lip_uhq.py", line 173, in execute detector, predictor = self.initialize_dlib_predictor() File "/storage/stable-diffusion/stable-diffusion-webui/extensions/sd-wav2lip-uhq/scripts/wav2lip/wav2lip_uhq.py", line 146, in initialize_dlib_predictor predictor = dlib.shape_predictor(self.wav2lip_folder + "/predicator/shape_predictor_68_face_landmarks.dat") RuntimeError: Unexpected version found while deserializing dlib::shape_predictor.

T3-sudo commented 1 year ago

Hey Numz. First off thanks for compiling this for A1111. Lesteriax its most likely the broken shape_predictor_68_face_landmarks.dat in the first link. Just dl from one of the subsequent links listed and it should work. I had the same issue but then checked the size of the model and seemed too small.

numz commented 1 year ago

Hi

Thank you @T3-sudo!! Really appreciate 😀 I'll correct it later

@Lesteriax ,is that resolve the problem ?

Thank you guys!

Lesteriax commented 1 year ago

Thank you @T3-sudo, that did the trick.

@numz, yes I'm currently using it with no issues. Seems the first link has an issue or it might be an issue from my end while downloading it.

numz commented 1 year ago

Ok, cool. Thank you :) I close this issue