Error occurred when executing Pops_Prior_Embedding: Cannot load F:/ComfyUI-aki-v1.3/models/diffusers/kandinsky-community/kandinsky-2-2-prior because clip_mean expected shape tensor(..., device='meta', size=(1, 768)), but got torch.Size([1, 1280]). 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: https://github.com/huggingface/diffusers/issues/1619#issuecomment-1345604389 as an example. #4
`Error occurred when executing Pops_Prior_Embedding:
Cannot load F:/ComfyUI-aki-v1.3/models/diffusers/kandinsky-community/kandinsky-2-2-prior because clip_mean expected shape tensor(..., device='meta', size=(1, 768)), but got torch.Size([1, 1280]). 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: https://github.com/huggingface/diffusers/issues/1619#issuecomment-1345604389 as an example.
File "F:\ComfyUI-aki-v1.3\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "F:\ComfyUI-aki-v1.3\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "F:\ComfyUI-aki-v1.3\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(*slice_dict(input_data_all, i)))
File "F:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI_Pops\ComfyUI_Pops.py", line 415, in apply_condition
decoder,prior,prior_pipeline,positive, negative,input_hidden_state,img_emb_file= get_embedding(kandinsky_prior_repo, prior_repo,
File "F:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI_Pops\ComfyUI_Pops.py", line 129, in get_embedding
prior = PriorTransformer.from_pretrained(
File "F:\ComfyUI-aki-v1.3\python\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(args, **kwargs)
File "F:\ComfyUI-aki-v1.3\python\lib\site-packages\diffusers\models\modeling_utils.py", line 667, in from_pretrained
unexpected_keys = load_model_dict_into_meta(
File "F:\ComfyUI-aki-v1.3\python\lib\site-packages\diffusers\models\modeling_utils.py", line 152, in load_model_dict_into_meta
raise ValueError(`
smthemex
commented
4 weeks ago
`Error occurred when executing Pops_Prior_Embedding:
Cannot load F:/ComfyUI-aki-v1.3/models/diffusers/kandinsky-community/kandinsky-2-2-prior because clip_mean expected shape tensor(..., device='meta', size=(1, 768)), but got torch.Size([1, 1280]). 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: https://github.com/huggingface/diffusers/issues/1619#issuecomment-1345604389 as an example.File "F:\ComfyUI-aki-v1.3\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "F:\ComfyUI-aki-v1.3\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "F:\ComfyUI-aki-v1.3\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(*slice_dict(input_data_all, i))) File "F:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI_Pops\ComfyUI_Pops.py", line 415, in apply_condition decoder,prior,prior_pipeline,positive, negative,input_hidden_state,img_emb_file= get_embedding(kandinsky_prior_repo, prior_repo, File "F:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI_Pops\ComfyUI_Pops.py", line 129, in get_embedding prior = PriorTransformer.from_pretrained( File "F:\ComfyUI-aki-v1.3\python\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn return fn(args, **kwargs) File "F:\ComfyUI-aki-v1.3\python\lib\site-packages\diffusers\models\modeling_utils.py", line 667, in from_pretrained unexpected_keys = load_model_dict_into_meta( File "F:\ComfyUI-aki-v1.3\python\lib\site-packages\diffusers\models\modeling_utils.py", line 152, in load_model_dict_into_meta raise ValueError(`
大神，这个报错是什么意思？