Run error：num_view

[juntaosun]

Processing videos: 0%| | 0/1 [00:13<?, ?it/s] rollingdepth\rollingdepth_pipeline.py", line 652, in single_step TypeError: UNet2DConditionModel.forward() got an unexpected keyword argument 'num_view'

[markkua]

This line is commented out so shouldn’t have any impact.

[juntaosun]

@markkua It always reports an error here and cannot continue.

rollingdepth\rollingdepth_pipeline.py", line 652, in single_step noise_pred = self.unet( File "site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "site-packages\torch\nn\modules\module.py", line 1562, in _call_impl return forward_call(args, **kwargs) TypeError: UNet2DConditionModel.forward() got an unexpected keyword argument 'num_view'

[markkua]

Please install the our modified diffusers bash script/install_diffusers_dev.sh

[juntaosun]

@markkua Thanks, now it works.