Error occurred when executing INPAINT_ApplyFooocusInpaint: Sizes of tensors must match except in dimension 1. Expected size 1 but got size 2 for tensor number 1 in the list.

[meetedlike]

Error occurred when executing INPAINT_ApplyFooocusInpaint:

Sizes of tensors must match except in dimension 1. Expected size 1 but got size 2 for tensor number 1 in the list.

File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\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 "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, 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-inpaint-nodes\nodes.py", line 155, in patch feed = torch.cat([latent_mask, latent_pixels], dim=1)

[meetedlike]

Hello author, you have not replied to or addressed the question I raised. Is it because it is very difficult to handle?

[Acly]

It looks related to batch frame (video) generation. There are few other issues about it. It probably requires special support, I haven't had time or incentive to look into videos so far.

[meetedlike]

You are right, because I want to expand the image of the video, so I think the effect you have is the best when I use it on a single image. So I was wondering if it can be applied to the video. However, I found that the current processing logic is not suitable when it is used on the video because it cannot handle batch images. I hope you can do this when you have time. I think the effect will also be very good, especially when combined with animatediff, the effect is even better. Thank you for your plugin