lucataco / bulk-video-caption

Video Preprocessing tool for captioning multiple videos using GPT, Claude or Gemini

  • Public
  • 111 runs
  • CPU
  • GitHub
  • License
  • Prediction

    lucataco/bulk-video-caption:bd610b3c
    ID
    4weatz1zs9rg80ckr7m83bz2k4
    Status
    Succeeded
    Source
    Web
    Hardware
    CPU
    Total duration
    Created

    Input

    model
    gpt-4o
    include_csv
    system_prompt
    Analyze these frames from a video and write a detailed caption. Describe the type of video (e.g., animation, live-action footage, etc.). Focus on consistent elements across frames and any notable motion or action. Describe the main subjects, setting, and overall mood of the video. Use clear, descriptive language suitable for text-to-video generation.
    caption_prefix
     
    caption_suffix
     
    openai_api_key
    ████████████████████

    This value was redacted after being sent to the model.

    frames_to_extract
    2
    video_zip_archive
    vhs-segmented.zip

    Output

    Generated in
  • Prediction

    lucataco/bulk-video-caption:bd610b3c
    ID
    8ma06swr21rg80ckr7rt2krra4
    Status
    Succeeded
    Source
    Web
    Hardware
    CPU
    Total duration
    Created

    Input

    model
    claude-3-5-sonnet-20240620
    include_csv
    system_prompt
    Analyze these frames from a video and write a detailed caption. Describe the type of video (e.g., animation, live-action footage, etc.). Focus on consistent elements across frames and any notable motion or action. Describe the main subjects, setting, and overall mood of the video. Use clear, descriptive language suitable for text-to-video generation.
    caption_prefix
     
    caption_suffix
     
    anthropic_api_key
    ████████████████████

    This value was redacted after being sent to the model.

    frames_to_extract
    1
    video_zip_archive
    disney-12.zip

    Output

    Generated in
  • Prediction

    lucataco/bulk-video-caption:bd610b3c
    ID
    ah7ykc0gxxrg80ckr7tty5xvc8
    Status
    Succeeded
    Source
    Web
    Hardware
    CPU
    Total duration
    Created

    Input

    model
    gpt-4o
    include_csv
    system_prompt
    Analyze these frames from a video and write a detailed caption. Describe the type of video (e.g., animation, live-action footage, etc.). Focus on consistent elements across frames and any notable motion or action. Describe the main subjects, setting, and overall mood of the video. Use clear, descriptive language suitable for text-to-video generation.
    caption_prefix
     
    caption_suffix
    melty.
    openai_api_key
    ████████████████████

    This value was redacted after being sent to the model.

    frames_to_extract
    1
    video_zip_archive
    melty-seg-3.zip

    Output

    Generated in

Want to make some of these yourself?

Run this model