Hello, when I was running your code, the DWPOSE part was working fine, but there was an error in the controlnext part.

[wjxxyz]

                                                                                                                                                                                                                                                        | 0/25 [00:23<?, ?it/s]

Traceback (most recent call last):
File "/opt/data/private/wjx/ControlNeXt-main/ControlNeXt-SVD-v2/run_controlnext.py", line 262, in
video_frames = pipeline(
File "/opt/conda/envs/pytorch_wjx/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/opt/data/private/wjx/ControlNeXt-main/ControlNeXt-SVD-v2/pipeline/pipeline_stable_video_diffusion_controlnext.py", line 588, in call
noise_pred = self.unet(
File "/opt/conda/envs/pytorch_wjx/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/conda/envs/pytorch_wjx/lib/python3.9/site-packages/accelerate/hooks.py", line 170, in new_forward
output = module._old_forward(*args, **kwargs)
File "/opt/data/private/wjx/ControlNeXt-main/ControlNeXt-SVD-v2/models/unet_spatio_temporal_condition_controlnext.py", line 491, in forward
sample = upsample_block(
File "/opt/conda/envs/pytorch_wjx/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/conda/envs/pytorch_wjx/lib/python3.9/site-packages/diffusers/models/unets/unet_3d_blocks.py", line 1494, in forward
hidden_states = torch.cat([hidden_states, res_hidden_states], dim=1)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 6 but got size 5 for tensor number 1 in the list.

[wjxxyz]

Sizes of tensors must match except in dimension 1.