The size of tensor a (256) must match the size of tensor b (729) at non-singleton dimension 1

[JiajunDou]

Traceback (most recent call last):
File "D:\ComfyUI-aki-v1.4\execution.py", line 324, 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 "D:\ComfyUI-aki-v1.4\execution.py", line 199, 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 "D:\ComfyUI-aki-v1.4\execution.py", line 170, in _map_node_over_list
process_inputs(input_dict, i)
File "D:\ComfyUI-aki-v1.4\execution.py", line 159, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "D:\ComfyUI-aki-v1.4\custom_nodes\x-flux-comfyui\nodes.py", line 599, in applymodel
out = clip(pixel_values=pixel_values)
File "D:\ComfyUI-aki-v1.4\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\ComfyUI-aki-v1.4\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\ComfyUI-aki-v1.4\comfy\clip_model.py", line 216, in forward
x = self.vision_model(*args, **kwargs)
File "D:\ComfyUI-aki-v1.4\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\ComfyUI-aki-v1.4\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\ComfyUI-aki-v1.4\comfy\clip_model.py", line 195, in forward
x = self.embeddings(pixel_values)
File "D:\ComfyUI-aki-v1.4\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\ComfyUI-aki-v1.4\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\ComfyUI-aki-v1.4\comfy\clip_model.py", line 171, in forward
return embeds + comfy.ops.cast_to_input(self.position_embedding.weight, embeds)
RuntimeError: The size of tensor a (256) must match the size of tensor b (729) at non-singleton dimension 1

[labpar000-debug]

same

[Misty1113]

可能是使用了不兼容的模型或模型有损。我也遇到了同样报错，换了个模型就解决了。