When attempting to use the code to infer with a 512x320 images + video, I get this error:
File "/workspace/ToonCrafter_with_SketchGuidance/cldm/cldm.py", line 339, in forward
h += guided_hint
RuntimeError: The size of tensor a (16) must match the size of tensor b (49) at non-singleton dimension 0
Any ideas? Perhaps only specific resolutions are allowed? The example image and video does work for me.
When attempting to use the code to infer with a 512x320 images + video, I get this error:
Any ideas? Perhaps only specific resolutions are allowed? The example image and video does work for me.
My input files:
https://github.com/user-attachments/assets/d4dbeea4-c647-46c5-9631-deefe8ef0c46