Skip to main content

Video Highlight Generator

Video Highlight Generator is a powerful, standalone AI tool that automatically creates engaging highlight videos from your photo collections. It combines state-of-the-art image analysis, face detection, and smart audio syncing to turn your memories into movies.

🚀 Features

  • 🧠 Smart Image Analysis: Uses MobileNetV3 to score image quality (sharpness, composition) and classify content.
  • 👤 Face Detection & Clustering: Detects faces and groups them by person, allowing you to create person-specific highlight reels.
  • 🔍 Theme Detection: Automatically identifies themes in your photos (e.g., "nature", "people", "urban").
  • 🎵 Audio Studio:
    • Waveform Editor: Visual audio trimmer to select the perfect segment.
    • Custom Audio: Import your own music tracks.
    • Smart Looping: Automatically loops audio to match video duration.
  • 📱 Multi-Format Export: Generate videos optimized for PC/TV (16:9) or Smartphone (9:16).
  • 📊 Progress Tracking: Real-time visual progress bars for both image analysis and video generation.
  • ✨ Cinematic Effects: Smooth cross-fade transitions and custom image duration.
  • 📝 Title Overlay: Add a custom title to your video.
  • ⚡ Ultra-Fast Caching: SQLite-based caching ensures instant re-scans and crash resilience.
  • 🎨 Modern Web Interface: A sleek, dark-mode React frontend for easy folder selection and project management.

App Screenshot

📦 Installation

This tool is packaged as a single Python Wheel file for easy installation.

Install via PIP: pip install video-highlight-generator

📚 Documentation

🎮 Usage

  1. Start the Application: Run the following command in your terminal:

    video-highlight-generator
    
  2. Open the Web Interface: Open your browser and navigate to: http://localhost:8000

  3. Create Your Highlight:

    • Analyze: Select your photo folders and click "Analyze Images". Watch the progress bar as it scans.
    • Review: See the detected images, identified people, and themes.
    • Generate:
      • Select images (smart selection automatically picks the best ones).
      • Choose output resolution (1080p or 9:16).
      • Add custom audio and trim it using the waveform editor.
      • Click "Generate Video" and watch the progress.

🔧 Development

To develop on this project:

  1. Backend:

    • Install dependencies: pip install -r requirements.txt (or manually install from setup.py)
    • Run dev server: uvicorn video_highlight_generator.main:app --reload
  2. Frontend:

    • Navigate to frontend/
    • Install dependencies: npm install
    • Run dev server: npm run dev

📝 License

GNU General Public License v3.0

Metadata

Release files for video-highlight-generator 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for video-highlight-generator 0.1.2
File Size Uploaded
video_highlight_generator-0.1.2.tar.gz 195.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for video-highlight-generator 0.1.2
File Interpreter ABI Platform
video_highlight_generator-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 392.6 kB

Release files / video_highlight_generator-0.1.2.tar.gz

Download URL video_highlight_generator-0.1.2.tar.gz
Size 195.6 kB
Tags Source
SHA-256 checksum
How to use checksums
26ff70c26c1e4b5bf6e88376fc1ff57ce4cb7308d90885d9ad26e1ce46f090ba
BLAKE2b-256 checksum
How to use checksums
7b0e7878e51cd3b248eb34ead8344bcc025d2546c209282c0cf36634e47224f0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.10.11

Release files / video_highlight_generator-0.1.2-py3-none-any.whl

Download URL video_highlight_generator-0.1.2-py3-none-any.whl
Size 197.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
97f09a8e9ac4fa3965329de049dfd21919d0baa0b748b378cf5ce9ab6f330796
BLAKE2b-256 checksum
How to use checksums
e6e9ec75b5284532065e211c30da80c9e68e5c4c6c0ad90412d213ef713f372a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.10.11

Release history Release notifications | RSS feed

This release

0.1.2 This release

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page