Is it able to integrate with animatediff?

[zevcc-gh]

I am following
https://github.com/huchenlei/ComfyUI-layerdiffuse/tree/main?tab=readme-ov-file#generate-foreground-rgb--alpha

But switched the model to animatediff, and the error is displayed on the Layer Diffusion Decode node.

RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 36 but got size 35 for tensor number 1 in the list.

[huchenlei]

Can you share your workflow?

[dummerfranz]

is working with animatediff. not sure if node order is important tho.

workflow (2).json

[zevcc-gh]

Here is my workflow:
test_animatediff.json
for the openposeXL2, im using this: https://huggingface.co/thibaud/controlnet-openpose-sdxl-1.0/tree/main

The video can be generate successfully, but failed on the postprocessing part, on the Layer Diffusion Decode node.

[huchenlei]

In the minimal animatediff workflow I cannot reproduce your issue:

ad.json

[zevcc-gh]

I have fixed my workflow but I don't know why.
I found that the image's width = 560 = 16*35, so I changed the width from 560 to 576 and it works...