Skip to content

Getting TypeError when running image to video generation #260

@NamanArora

Description

Error Trace

Traceback (most recent call last):
  File "/workspace/crazyvid/LTX-Video/inference.py", line 13, in <module>
    main()
  File "/workspace/crazyvid/LTX-Video/inference.py", line 9, in main
    infer(config=config)
  File "/workspace/crazyvid/LTX-Video/ltx_video/inference.py", line 632, in infer
    video.append_data(frame)
  File "/workspace/crazyvid/LTX-Video/env/lib/python3.12/site-packages/imageio/v2.py", line 226, in append_data
    return self.instance.write(im, **self.write_args)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/crazyvid/LTX-Video/env/lib/python3.12/site-packages/imageio/plugins/pyav.py", line 674, in write
    self.init_video_stream(codec, fps=fps, pixel_format=out_pixel_format)
  File "/workspace/crazyvid/LTX-Video/env/lib/python3.12/site-packages/imageio/plugins/pyav.py", line 887, in init_video_stream
    stream = self._container.add_stream(codec, fps)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "av/container/output.py", line 60, in av.container.output.OutputContainer.add_stream
  File "av/codec/codec.pyx", line 85, in av.codec.codec.Codec.__cinit__
TypeError: expected bytes, NoneType found

Ran this command
python inference.py --prompt "Make the image come to life" --conditioning_media_paths jewellery-1515647069.jpg --conditioning_start_frames 0 --height 384 --width 384 --num_frames 201 --seed 34234 --pipeline_config configs/ltxv-13b-0.9.8-distilled.yaml

I'm on python 3.12.12

Was able to repro this error on 2 different machines and on different models as well (13b and 2b)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions