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
Hi guys,i got a problem, i cant download cogvideox models and stuff with it's normal way of dragging the workflow into the scene and get it to download the models, so i did all the manual work ( making folders with similar names and put the models and stuff into the related folder ( i also didnt download some big files twice or so as i saw some had been created on same day with the excct same size so i assumed they must be same and (correct me if i'm wrong)....long story shot, now i can't do shit with cogvideox lol, none of the workflows work and i'm getting frustrated so far has been downloading over 150 gig and still cant run a thing with it, every time get a differnt error and now this, pls help me to get it work i really need it guys,big apprecation !
Cannot load C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\models\CogVideo\CogVideoX-Fun-V1.1-5b-Control because patch_embed.proj.weight expected shape tensor(..., device='meta', size=(3072, 32, 2, 2)), but got torch.Size([3072, 33, 2, 2]). If you want to instead overwrite randomly initialized weights, please make sure to pass both low_cpu_mem_usage=False and ignore_mismatched_sizes=True. For more information, see also: huggingface/diffusers#1619 (comment) as an example.
ComfyUI Error Report
Error Details
Node ID: 449
Node Type: DownloadAndLoadCogVideoModel
Exception Type: ValueError
Exception Message: Cannot load C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\models\CogVideo\CogVideoX-Fun-V1.1-5b-Control because patch_embed.proj.weight expected shape tensor(..., device='meta', size=(3072, 32, 2, 2)), but got torch.Size([3072, 33, 2, 2]). If you want to instead overwrite randomly initialized weights, please make sure to pass both low_cpu_mem_usage=False and ignore_mismatched_sizes=True. For more information, see also: Adding additional input channels to model after intialization / Converting text2img to mask inpainting to resume training huggingface/diffusers#1619 (comment) as an example.
Stack Trace
File "C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 328, 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 "C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 203, 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 "C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-CogVideoXWrapper\model_loading.py", line 278, in loadmodel
transformer = CogVideoXTransformer3DModel.from_pretrained(base_path, subfolder=subfolder, attention_mode=attention_mode)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\models\modeling_utils.py", line 855, in from_pretrained
unexpected_keys = load_model_dict_into_meta(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\models\model_loading_utils.py", line 223, in load_model_dict_into_meta
raise ValueError(
Hi guys,i got a problem, i cant download cogvideox models and stuff with it's normal way of dragging the workflow into the scene and get it to download the models, so i did all the manual work ( making folders with similar names and put the models and stuff into the related folder ( i also didnt download some big files twice or so as i saw some had been created on same day with the excct same size so i assumed they must be same and (correct me if i'm wrong)....long story shot, now i can't do shit with cogvideox lol, none of the workflows work and i'm getting frustrated so far has been downloading over 150 gig and still cant run a thing with it, every time get a differnt error and now this, pls help me to get it work i really need it guys,big apprecation !
Cannot load C:\Users\hamid\Desktop\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\models\CogVideo\CogVideoX-Fun-V1.1-5b-Control because patch_embed.proj.weight expected shape tensor(..., device='meta', size=(3072, 32, 2, 2)), but got torch.Size([3072, 33, 2, 2]). If you want to instead overwrite randomly initialized weights, please make sure to pass both
low_cpu_mem_usage=Falseandignore_mismatched_sizes=True. For more information, see also: huggingface/diffusers#1619 (comment) as an example.ComfyUI Error Report
Error Details
low_cpu_mem_usage=Falseandignore_mismatched_sizes=True. For more information, see also: Adding additional input channels to model after intialization / Converting text2img to mask inpainting to resume training huggingface/diffusers#1619 (comment) as an example.Stack Trace
System Information
Devices
Logs
Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.
Additional Context
(Please add any additional context or steps to reproduce the error here)
The text was updated successfully, but these errors were encountered: