Brackets break TextEncodeQwenImageEdit

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

Prompt with brackets as normal text:
`A girl with empty hands (one of them is wearing a glove) stands outside.`
Working.

### Actual Behavior

Prompt with brackets as normal text:
`A girl with empty hands (one of them is wearing a glove) stands outside.`
Error:
```
TextEncodeQwenImageEdit
Sizes of tensors must match except in dimension 0. Expected size 14## but got size 9# for tensor number 1 in the list.
```

### Steps to Reproduce

Use brackets with text inside in prompt.
Brackets without a letter () work. =)

### Debug Logs

```powershell
!!! Exception during processing !!! Sizes of tensors must match except in dimension 0. Expected size 1465 but got size 97 for tensor number 1 in the list.
Traceback (most recent call last):
File "F:\NN\Comfy\ComfyUI\execution.py", line 496, 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 "F:\NN\Comfy\ComfyUI\execution.py", line 315, 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 "F:\NN\Comfy\ComfyUI\execution.py", line 289, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "F:\NN\Comfy\ComfyUI\execution.py", line 277, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "F:\NN\Comfy\ComfyUI\comfy_extras\nodes_qwen.py", line 55, in encode
conditioning = clip.encode_from_tokens_scheduled(tokens)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\NN\Comfy\ComfyUI\comfy\sd.py", line 170, in encode_from_tokens_scheduled
pooled_dict = self.encode_from_tokens(tokens, return_pooled=return_pooled, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\NN\Comfy\ComfyUI\comfy\sd.py", line 232, in encode_from_tokens
o = self.cond_stage_model.encode_token_weights(tokens)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\NN\Comfy\ComfyUI\comfy\text_encoders\qwen_image.py", line 51, in encode_token_weights
out, pooled, extra = super().encode_token_weights(token_weight_pairs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\NN\Comfy\ComfyUI\comfy\sd1_clip.py", line 686, in encode_token_weights
out = getattr(self, self.clip).encode_token_weights(token_weight_pairs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\NN\Comfy\ComfyUI\comfy\sd1_clip.py", line 45, in encode_token_weights
o = self.encode(to_encode)
^^^^^^^^^^^^^^^^^^^^^^
File "F:\NN\Comfy\ComfyUI\comfy\sd1_clip.py", line 291, in encode
return self(tokens)
^^^^^^^^^^^^
File "F:\NN\Comfy\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\NN\Comfy\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\NN\Comfy\ComfyUI\comfy\sd1_clip.py", line 253, in forward
embeds, attention_mask, num_tokens, embeds_info = self.process_tokens(tokens, device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\NN\Comfy\ComfyUI\comfy\sd1_clip.py", line 249, in process_tokens
return torch.cat(embeds_out), torch.tensor(attention_masks, device=device, dtype=torch.long), num_tokens, embeds_info
^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Sizes of tensors must match except in dimension 0. Expected size 1465 but got size 97 for tensor number 1 in the list.
```

### Other

_No response_