diffrhythm Error(s) in loading state_dict for Embedding: size mismatch for weight

[Deforro]

The "DiffRhythm Nodes for ComfyUI" node is installed. An error occurs after running this workflow or workflow-examples.

Prompt executed in 9.18 seconds
got prompt
Loading weights from local directory
You are using a model of type diffrhythm to instantiate a model of type xlm-roberta. This is not supported for all configurations of models and can yield errors.
!!! Exception during processing !!! Error(s) in loading state_dict for Embedding:
size mismatch for weight: copying a param with shape torch.Size([514, 768]) from checkpoint, the shape in current model is torch.Size([512, 768]).
Traceback (most recent call last):
File "C:\ComfyUI_Port\ComfyUI\execution.py", line 498, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\ComfyUI\execution.py", line 316, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\ComfyUI\execution.py", line 290, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "C:\ComfyUI_Port\ComfyUI\execution.py", line 278, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "C:\ComfyUI_Port\ComfyUI\custom_nodes\diffrhythm_mw\DiffRhythmNode.py", line 230, in diffrhythmgen
CFM, TOKENIZER, MUQ, VAE, EVAL_MODEL, EVAL_MUQ = prepare_model(max_frames, self.device, model)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\ComfyUI\custom_nodes\diffrhythm_mw\infer_utils.py", line 256, in prepare_model
muq = MuQMuLan(config=config_obj, hf_hub_cache_dir=None)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\muq\muq_mulan\muq_mulan.py", line 71, in init
self.mulan = self.create_MuLan_from_config(config, hf_hub_cache_dir)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\muq\muq_mulan\muq_mulan.py", line 105, in create_MuLan_from_config
text_transformer = TextTransformerPretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\muq\muq_mulan\models\text.py", line 137, in init
self.model = self._init_pretrained_model()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\muq\muq_mulan\models\text.py", line 171, in _init_pretrained_model
model = XLMRobertaModel.from_pretrained(self.model_name, trust_remote_code=True, cache_dir=self.hf_hub_cache_dir)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\transformers\modeling_utils.py", line 277, in _wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\transformers\modeling_utils.py", line 5048, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\transformers\modeling_utils.py", line 5468, in _load_pretrained_model
_error_msgs, disk_offload_index = load_shard_file(args)
^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\transformers\modeling_utils.py", line 843, in load_shard_file
disk_offload_index = _load_state_dict_into_meta_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\transformers\modeling_utils.py", line 770, in _load_state_dict_into_meta_model
_load_parameter_into_model(model, param_name, param.to(param_device))
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\transformers\modeling_utils.py", line 667, in _load_parameter_into_model
module.load_state_dict({param_type: tensor}, strict=False, assign=True)
File "C:\ComfyUI_Port\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2593, in load_state_dict
raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for Embedding:
size mismatch for weight: copying a param with shape torch.Size([514, 768]) from checkpoint, the shape in current model is torch.Size([512, 768]).

All files and models were downloaded from
https://github.com/billwuhao/ComfyUI_DiffRhythm