You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have tried everything I could think of to make CAIN video frame interpolation work with the CAIN VFI node, but no matter what I do I get a Tensors must have same number of dimensions: got 4 and 3 error message.
The following log shows what happens when I try to pass a 23 frames long sequence to it.
It seems to be able to create the images, hence the Comfy-VFI done! 46 frames generated at resolution: torch.Size([1, 3, 512, 512]) message, but after that step the frames are not sent to the next node where they would get converted to video.
Comfy-VFI: Clearing cache... Done cache clearing
Comfy-VFI: Clearing cache... Done cache clearing
Comfy-VFI done! 46 frames generated at resolution: torch.Size([1, 3, 512, 512])
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\cain\__init__.py", line 62, in vfi
generic_frame_loop(frames, clear_cache_after_n_frames, multiplier, return_middle_frame, *args,
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_utils.py", line 194, in generic_frame_loop
out = torch.cat(output_frames, dim=0)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Tensors must have same number of dimensions: got 4 and 3
Prompt executed in 4.23 seconds
The text was updated successfully, but these errors were encountered:
I have tried everything I could think of to make CAIN video frame interpolation work with the CAIN VFI node, but no matter what I do I get a
Tensors must have same number of dimensions: got 4 and 3
error message.The following log shows what happens when I try to pass a 23 frames long sequence to it.
It seems to be able to create the images, hence the
Comfy-VFI done! 46 frames generated at resolution: torch.Size([1, 3, 512, 512])
message, but after that step the frames are not sent to the next node where they would get converted to video.The text was updated successfully, but these errors were encountered: