You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The following problem: When I start the workflow, I get the following error message:
DownloadAndLoadHyVideoTextEncoder No package metadata was found for bitsandbytes
The download should actually start automatically. I then manually downloaded the folder “llava-llama-3-8b-text-encoder-tokenizer” from huggingface and packed it in /models/LLM/. But that doesn't help either.
Here is the complete log:
2024-12-10T11:21:12.872354 - got prompt
2024-12-10T11:21:12.909389 - !!! Exception during processing !!! No package metadata was found for bitsandbytes
2024-12-10T11:21:12.910391 - Traceback (most recent call last):
File "importlib\metadata\__init__.py", line 563, in from_name
StopIteration
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "E:\StableDiffusion\ComfyUI\ComfyUI\execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\StableDiffusion\ComfyUI\ComfyUI\execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\StableDiffusion\ComfyUI\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "E:\StableDiffusion\ComfyUI\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\StableDiffusion\ComfyUI\ComfyUI\custom_nodes\ComfyUI-HunyuanVideoWrapper\nodes.py", line 434, in loadmodel
quantization_config = BitsAndBytesConfig(
^^^^^^^^^^^^^^^^^^^
File "E:\StableDiffusion\ComfyUI\python_embeded\Lib\site-packages\transformers\utils\quantization_config.py", line 402, in __init__
self.post_init()
File "E:\StableDiffusion\ComfyUI\python_embeded\Lib\site-packages\transformers\utils\quantization_config.py", line 460, in post_init
if self.load_in_4bit and not version.parse(importlib.metadata.version("bitsandbytes")) >= version.parse(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "importlib\metadata\__init__.py", line 1009, in version
File "importlib\metadata\__init__.py", line 982, in distribution
File "importlib\metadata\__init__.py", line 565, in from_name
importlib.metadata.PackageNotFoundError: No package metadata was found for bitsandbytes
The text was updated successfully, but these errors were encountered:
The bnb_nf4 quantization option requires bitsandbytes library installed, I didn't want to make that automatic as that package sometimes has issues and is preferable to be installed manually.
For portable that can be done by running this command in the ComfyUI_windows_portable\python_embeded -folder:
The following problem: When I start the workflow, I get the following error message:
DownloadAndLoadHyVideoTextEncoder No package metadata was found for bitsandbytes
The download should actually start automatically. I then manually downloaded the folder “llava-llama-3-8b-text-encoder-tokenizer” from huggingface and packed it in /models/LLM/. But that doesn't help either.
Here is the complete log:
The text was updated successfully, but these errors were encountered: