run_inference error

[goalslee]

AnimateAnyone-reproduction$ python run_inference_release.py layers per block is 2 Loading pipeline components...: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:00<00:00, 5.83it/s] 0%| | 0/25 [00:01<?, ?it/s] Traceback (most recent call last): File "AnimateAnyone-reproduction/run_inference_release.py", line 236, in video_frames = pipeline(ref_image, validation_control_images[:num_frames], decode_chunk_size=2,num_frames=num_frames,motion_bucket_id=127.0, fps=7,controlnet_cond_scale=1.0, width=args['width'], height=args["height"], min_guidance_scale=3.5, max_guidance_scale=3.5, frames_per_batch=frames, num_inference_steps=25, overlap=4).frames[0] File ".venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, kwargs) File "AnimateAnyone-reproduction/pipeline_stable_video_diffusion_controlnet_long.py", line 569, in call noise_pred = self.unet( File ".venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File ".venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(args, kwargs) File ".venv/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward output = old_forward(*args, **kwargs) TypeError: UNetSpatioTemporalConditionModel.forward() got an unexpected keyword argument 'down_block_additional_residuals'

could you have a look about this issue?

[bendanzzc]

sorry for lots of import error, I have tested and its ok now, please pull the latest version

[bendanzzc]

fix the unet has wrong class, so I reload the unet when init @goalslee @Valentino-L