An automated video thumbnail generation tool powered by AI and computer vision. It analyzes video frames, detects key objects, and generates visually appealing thumbnails enriched with metadata and AI-generated prompts. It supports both GPU-accelerated and CPU-based processing, ensuring compatibility across diverse systems.
- AI-Powered Object Detection: Identifies key elements in video frames to generate contextual thumbnails.
- Customizable Metadata Integration: Incorporates metadata for personalized and relevant outputs.
- GPU and CPU Support: Automatically adapts to your system's capabilities for seamless performance.
- Easy-to-Use: Intuitive functionality for both beginners and advanced users.
- Scalable Design: Handles videos of varying lengths and resolutions efficiently.
- To set up the project, install the required libraries by running:
pip install -r requirements.txt- Install FFmpeg, This package requires FFmpeg to be installed on your system. Follow the instructions below based on your operating system:
- Download FFmpeg from the official website: FFmpeg Download
- Choose the Windows version and download the zip file.
- Extract the zip file to this directory
(C:\ffmpeg).
On Ubuntu/Debian-based systems, install FFmpeg via APT:
sudo apt update
sudo apt install ffmpeg- Run the main script:
python main.py-
When prompted, provide the path to the video file you want to process.
-
The tool will analyze the video, generate thumbnails, and save them to the
Outputfolder.