Stability-AI / generative-models

Generative Models by Stability AI

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Already corrupted output vedio

qixuanwang-233 opened this issue · comments

When I open the output video, the player says we can't open 00001.mp4. This could be because the file type is not supported The file extension is incorrect or the file is corrupted. Clearly the output video is corrupted, what is going on, is there a solution?

I also got the same issue when I run the program on WSL on Windows11.
Generated things are 000000.jpg and 000000.mp4. I could open the jpg file correctly.
Can anyone tell me what the cause is from the following error?

xxx@xxx:/mnt/c/Users/xxx/generative-models$ python scripts/sampling/simple_video_sample.py --input_path "/mnt/c/Users/xxx/Downloads/00001-2141331527_2.png" --version sv3d_u
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
Initialized embedder #0: FrozenOpenCLIPImagePredictionEmbedder with 683800065 params. Trainable: False
Initialized embedder #1: VideoPredictionEmbedderWithEncoder with 83653863 params. Trainable: False
Initialized embedder #2: ConcatTimestepEmbedderND with 0 params. Trainable: False
Restored from checkpoints/sv3d_u.safetensors with 0 missing and 0 unexpected keys
/mnt/c/Users/xxx/generative-models/.pt2/lib/python3.10/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
  warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
xxx@xxx:/mnt/c/Users/xxx/generative-models$ lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description:    Ubuntu 22.04.3 LTS
Release:        22.04
Codename:       jammy

Same here. Running on Windows. The output mp4 is corrupted

Fixed it by installing imageio-ffmpeg & pyav.
pip install imageio-ffmpeg pyav

By running it with streamlit, I could generate a frame image when rotating an input image as a 3D model. The video is still corrupted, but you can make a video if you join the frame images yourself.

Fixed it by installing imageio-ffmpeg & pyav. pip install imageio-ffmpeg pyav

Wow me too! Thank you!

Fixed it by installing imageio-ffmpeg & pyav. pip install imageio-ffmpeg pyav

wow, thank you very much for your answer, it helped a lot.