README.md

metadata

title: Generative Video Editor
short_description: Uses natural language to generate and control edits
emoji: 💻
colorFrom: green
colorTo: green
sdk: gradio
sdk_version: 6.2.0
app_file: app.py
pinned: true
disable_embedding: false
models:
  - zai-org/GLM-4.7-Flash
tags:
  - ffmpeg
  - video-editing
  - natural-language
  - ai-video
  - no-code
  - video-processing
  - media-converter
  - slideshow-maker
  - video-merger
  - command-generator
  - waveform-visualization
  - audio-to-video
  - image-to-video

🏞 AI Video Composer - FFMPEG in Plain English

Describe what you want in plain English, like "create a slideshow from these images with background music" or "add a waveform visualization to this audio", and AI generates the exact FFMPEG command to make it happen.

How It Works

1. Upload Media Files:

   • Supports multiple file formats including:
     • Images: .png, .jpg, .jpeg, .tiff, .bmp, .gif, .svg
     • Audio: .mp3, .wav, .ogg
     • Video: .mp4, .avi, .mov, .mkv, .flv, .wmv, .webm, and more
   • File size limit: 10MB per file
   • Video duration limit: 2 minutes

2. Provide Instructions:

   • Write natural language instructions describing how you want to process your media
   • Examples:
     • "Convert these images into a slideshow with 1 second per image"
     • "Add this audio track to the video"
     • "Make the video play 2x faster"
     • "Create a waveform visualization for this audio file"

3. Advanced Parameters:

   • Top-p (nucleus sampling): Controls diversity of generated commands (0-1)
   • Temperature: Controls randomness in command generation (0-5)

4. Processing:

   • The app analyzes your files and instructions
   • Generates an optimized FFmpeg command using your chosen AI model
   • Executes the command and returns the processed video
   • Displays the generated FFmpeg command for transparency

Features

• Smart Command Generation: Automatically generates optimal FFmpeg commands based on natural language input
• Error Handling: Validates commands before execution and retries with alternative approaches if needed
• Multiple Asset Support: Process multiple media files in a single operation
• Waveform Visualization: Special support for audio visualization with customizable parameters
• Image Sequence Processing: Efficient handling of image sequences for slideshow creation
• Format Conversion: Support for various input/output format conversions
• Example Gallery: Built-in examples demonstrating common use cases

Technical Details

• Built with Gradio for the user interface
• Uses FFmpeg for media processing
• Powered by GLM-4.7 or Kimi-K2 for command generation
• Implements robust error handling and command validation
• Processes files in a temporary directory for safety
• Supports both simple operations and complex media transformations

Limitations

• Maximum file size: 10MB per file
• Maximum video duration: 2 minutes
• Output format: Always MP4
• Processing time may vary based on input complexity