Multiband diffusion not working.
Drommer-Kille opened this issue · 4 comments
After git pull to latest versio, the multiband diffusion does not work.
I lanch AudioCraft Plus, write TEST to prompt and hit generate. It takes quite some time to generate 10sec test. Then i go to settings and change decoder to multiband_diffusion and hit generate and get long list of errors that end to this line:
TypeError: issubclass() arg 1 must be a class
Files that give errors:
\Python\Python310\lib\site-packages\omegaconf\dictconfig.py
\Python\Python310\lib\site-packages\omegaconf_utils.py
Python\Python310\lib\site-packages\omegaconf\base.py
Python\Python310\lib\site-packages\omegaconf\dictconfig.py
Also, latest version seem quite slow. How can i de-bug that? It is using GPU as GPU goes 100% while generating. I have RTX3090 with 24gb VRAM.
Sadly I myself cannot play much with multiband as I do not owe a good enough graphics card, so my only way of testing is with the free version of google colab. Can you explain more on your issue? what duration did you try to generate? and what model? Ill try to replicate the issue
It happens even with 1sec duration and model is Large. But it seems that the problem is not in your end. I also git pulled the original repo and it gives the same error if multiband is selected.
Lesson learned: Never update if it works.
Edit. Tried also with Small model and same error happens if multiband is selected.
`loading MBD
Traceback (most recent call last):
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\dictconfig.py", line 303, in getattr
return self._get_impl(key=key, default_value=DEFAULT_VALUE_MARKER)
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\dictconfig.py", line 361, in _get_impl
node = self._get_node(key=key)
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\dictconfig.py", line 375, in _get_node
key = self._validate_and_normalize_key(key)
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\dictconfig.py", line 222, in _validate_and_normalize_key
return self._s_validate_and_normalize_key(self._metadata.key_type, key)
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\dictconfig.py", line 241, in _s_validate_and_normalize_key
elif issubclass(key_type, Enum):
TypeError: issubclass() arg 1 must be a class
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\queueing.py", line 388, in call_prediction
output = await route_utils.call_process_api(
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\route_utils.py", line 219, in call_process_api
output = await app.get_blocks().process_api(
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1437, in process_api
result = await self.call_function(
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1109, in call_function
prediction = await anyio.to_thread.run_sync(
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 867, in run
result = context.run(func, *args)
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 641, in wrapper
response = f(*args, **kwargs)
File "G:\AI\audiocraft-plus\audiocraft_plus\app.py", line 844, in predict_full
load_diffusion()
File "G:\AI\audiocraft-plus\audiocraft_plus\app.py", line 464, in load_diffusion
MBD = MultiBandDiffusion.get_mbd_musicgen()
File "G:\AI\audiocraft-plus\audiocraft_plus\audiocraft\models\multibanddiffusion.py", line 74, in get_mbd_musicgen models, processors, cfgs = load_diffusion_models(path, device=device)
File "G:\AI\audiocraft-plus\audiocraft_plus\audiocraft\models\loaders.py", line 130, in load_diffusion_models
model = builders.get_diffusion_model(cfg)
File "G:\AI\audiocraft-plus\audiocraft_plus\audiocraft\models\builders.py", line 213, in get_diffusion_model
channels = cfg.channels
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\dictconfig.py", line 305, in getattr
self._format_and_raise(key=key, value=None, cause=e)
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\base.py", line 95, in _format_and_raise
format_and_raise(
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf_utils.py", line 644, in format_and_raise
child_node = node._get_node(key, validate_access=False)
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\dictconfig.py", line 375, in _get_node
key = self._validate_and_normalize_key(key)
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\dictconfig.py", line 222, in _validate_and_normalize_key
return self._s_validate_and_normalize_key(self._metadata.key_type, key)
File "C:\Users\Tester\AppData\Local\Programs\Python\Python310\lib\site-packages\omegaconf\dictconfig.py", line 241, in _s_validate_and_normalize_key
elif issubclass(key_type, Enum):
TypeError: issubclass() arg 1 must be a class
`
Did it work for you on previous version? like v2.0.0?
Not sure what version, the version from say 6 weeks ago. I generated a lot with multiband, also with original repo as it generated both versions (=great for creating true stereo files).