🖼️ OptiCaption - AI Image Captioning Application

OptiCaption is an AI-powered image captioning application that generates natural language descriptions from uploaded images. Built with Streamlit, Hugging Face Transformers, and Microsoft's Florence-2 vision-language model, the application provides accurate, context-aware captions in real time.

🚀 Features

• Upload images in multiple formats (JPG, PNG, JPEG, WEBP)
• Generate AI-powered image captions instantly
• Clean and interactive Streamlit interface
• State-of-the-art Vision Language Model (Florence-2)
• Fast and easy deployment
• Supports CPU and GPU execution

🛠️ Tech Stack

• Python
• Streamlit
• Hugging Face Transformers
• PyTorch
• Pillow
• Florence-2 Large

📂 Project Structure

OptiCaption/
│
├── app.py
├── requirements.txt
├── README.md
├── .gitignore
├── assets/
└── screenshots/

⚙️ Installation

1. Clone the Repository

git clone https://github.com/your-username/OptiCaption.git
cd OptiCaption

2. Create a Virtual Environment

python -m venv venv

3. Activate Virtual Environment

Windows:

venv\Scripts\activate

Linux/Mac:

source venv/bin/activate

4. Install Dependencies

pip install -r requirements.txt

5. Run the Application

streamlit run app.py

The application will open automatically in your browser.

🎯 How It Works

1. Upload an image.
2. The image is processed using the Florence-2 Vision-Language Model.
3. The model analyzes visual content and context.
4. A descriptive caption is generated and displayed.

📸 Example

Input: Image of a dog playing with a ball in a park.

Generated Caption:

"A brown dog playing with a red ball on a grassy field."

🔥 Future Improvements

• Multi-language caption generation
• Voice narration of captions
• Image tagging and object detection
• Caption customization options
• Cloud deployment with AWS

🤝 Contributing

Contributions are welcome. Feel free to fork the repository and submit pull requests.

📜 License

This project is licensed under the MIT License.

👨‍💻 Author

Tufan Chowdhury

B.Tech CSE Student | Cloud & AI Enthusiast

Connect with me on LinkedIn and GitHub for collaboration and project discussions.