(.venv) diogoviannaaraujo@vogoiddesk beholder % python -m mlx_vlm.video_generate --model mlx-community/Qwen2-VL-2B-Instruct-4bit --max-tokens 100 --prompt "Describe this video" --video ./video1.mp4 --max-pixels 224 224 --fps 1.0
This is a beta version of the video understanding. It may not work as expected.
<frozen runpy>:128: RuntimeWarning: 'mlx_vlm.video_generate' found in sys.modules after import of package 'mlx_vlm', but prior to execution of 'mlx_vlm.video_generate'; this may result in unpredictable behaviour
This is a beta version of the video understanding. It may not work as expected.
Loading model: mlx-community/Qwen2-VL-2B-Instruct-4bit
Fetching 11 files: 100%|███████████████████████████████████████████████████████████████████████| 11/11 [00:00<00:00, 141092.80it/s]
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
numpy reader: video_path=./video1.mp4, total_frames=3585, video_fps=15.0, time=0.000s
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/Users/diogoviannaaraujo/Projects/beholder/.venv/lib/python3.12/site-packages/mlx_vlm/video_generate.py", line 602, in <module>
    main()
  File "/Users/diogoviannaaraujo/Projects/beholder/.venv/lib/python3.12/site-packages/mlx_vlm/video_generate.py", line 507, in main
    image_inputs, video_inputs, fps = process_vision_info(messages, True)
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/diogoviannaaraujo/Projects/beholder/.venv/lib/python3.12/site-packages/mlx_vlm/video_generate.py", line 333, in process_vision_info
    video_input, video_sample_fps = fetch_video(
                                    ^^^^^^^^^^^^
  File "/Users/diogoviannaaraujo/Projects/beholder/.venv/lib/python3.12/site-packages/mlx_vlm/video_generate.py", line 245, in fetch_video
    if max_pixels_supposed > max_pixels:
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: '>' not supported between instances of 'list' and 'int'