comfyanonymous / ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
https://www.comfy.org/
GNU General Public License v3.0
52.13k stars 5.49k forks source link

Image Blend Node error #2594

Open kakachiex2 opened 8 months ago

kakachiex2 commented 8 months ago

Hi, I'm traying to blend two videos one as a background and another as an overlay is a Hud animation but I'm getting this error it supposed to process the video no matter their frame count or size just process it as a layer on top of another. Error occurred when executing ImageBlend:

The size of tensor a (63) must match the size of tensor b (278) at non-singleton dimension 0

File "K:\ComfyUI\ComfyUI\execution.py", line 153, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI\execution.py", line 83, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI\execution.py", line 76, in map_node_over_list results.append(getattr(obj, func)(*slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI\comfy_extras\nodes_post_processing.py", line 41, in blend_images blended_image = self.blend_mode(image1, image2, blend_mode) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI\comfy_extras\nodes_post_processing.py", line 52, in blend_mode return 1 - (1 - img1) (1 - img2)

kakachiex2 commented 8 months ago

Here is a preview of what I want to achieve.

https://github.com/comfyanonymous/ComfyUI/assets/1762112/c47daf33-cd07-4f30-b7d5-341203250fcd

jeffyspoke commented 6 months ago

Were you able to resolve this?