VisionTagger AI is an AI-powered image tagging and metadata generation tool that leverages Google's Gemini Vision Pro to automate the image annotation process. This system generates accurate, descriptive tags and structured metadata in JSON format, eliminating the need for manual image tagging.
Vision.Tagger.-.Made.with.Clipchamp.1.mp4
- 🏷️ Automatic Image Tagging – Extract meaningful tags for any image.
- 📝 JSON Metadata Generation – Get structured metadata for images.
- 🔍 AI-Powered Accuracy – Uses Google Gemini Vision Pro for precise results.
- 📂 Supports Multiple Image Formats – PNG, JPG, and more.
- 🌐 Web-Based Application – Simple and user-friendly UI.
- Frontend: HTML, CSS, JavaScript
- Backend: Python (Flask)
- API Used: Google Gemini Vision Pro (Paid API – using trial version)
- Install Python 3.x
- Install dependencies:
- pip install -r requirements.txt
🚀 Running the Application
- python app.py
- Then open http://localhost:5000 in your browser.
🔹 API Access ⚠ Note: We are using a paid API on a trial basis. If you encounter an API-related error, contact the developers for an updated API key.
🔹 Contributing Pull requests are welcome! Feel free to submit issues or feature requests.
🔹 License MIT License – Use it freely!