more than one face in video

[Kruchemundo]

When using Live Portrait for video and have more than one face in "source_image_batch" can not set other order than large to small. I'm getting this message :
"More than one face detected in the image, only pick one face by rule large-small. cropper.py:139
Load from video file"
If I try to put Face Crop Info getting Error:
"Error occurred when executing FaceCropInfo:

Cannot handle this data type: (1, 1, 1920, 3), |u1

File "c:\AI_programs\Comfyui\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\AI_programs\Comfyui\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\AI_programs\Comfyui\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\AI_programs\Comfyui\ComfyUI\custom_nodes\comfyui-liveportrait\nodes\live_portrait.py", line 206, in run
pil_image=tensor2pil(source_image)
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\AI_programs\Comfyui\ComfyUI\custom_nodes\comfyui-liveportrait\nodes\live_portrait.py", line 24, in tensor2pil
return Image.fromarray(np.clip(255. * image.cpu().numpy().squeeze(), 0, 255).astype(np.uint8))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\AI_programs\Comfyui\python_embeded\Lib\site-packages\PIL\Image.py", line 3281, in fromarray
raise TypeError(msg) from e"
Is there other way to do it?
Thank you for your time.