[BUG]image-to-video has a ERROR

[lckj2009]

streamlit run scripts/demo/video_sampling.py --server.port 8861 The error is as follows:

/laion/CLIP-ViT-H-14-laion2B-s32B-b79K/resolve/main/open_clip_pytorch_model.bin
Initialized embedder #0: FrozenOpenCLIPImagePredictionEmbedder with 683800065 params. Trainable: False
Initialized embedder #1: ConcatTimestepEmbedderND with 0 params. Trainable: False
Initialized embedder #2: ConcatTimestepEmbedderND with 0 params. Trainable: False
Initialized embedder #3: VideoPredictionEmbedderWithEncoder with 83653863 params. Trainable: False
Initialized embedder #4: ConcatTimestepEmbedderND with 0 params. Trainable: False
Loading model from checkpoints/svd_image_decoder.safetensors
imgimgimgimgimgimgimgimgimgimgimg None
2023-12-06 17:01:10.503 Uncaught app exception
Traceback (most recent call last):
File "/root/anaconda3/envs/pt2/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 534, in _run_script
exec(code, module.dict)
File "/root/generative-models/scripts/demo/video_sampling.py", line 144, in
value_dict["cond_frames"] = img + cond_aug * torch.randn_like(img)
TypeError: randn_like(): argument 'input' (position 1) must be Tensor, not NoneType

The 'video_sampling.py' code is shown in the following figure:

After testing, I found that the 'img' object is none, which should be a bug. I hope the author can solve it, thank you.