AI-Powered Image Analysis with BLIP + Dominant Color Detection
Instantly understand any photo using state-of-the-art vision-language models.
- Natural Language Description using Salesforce BLIP (top-tier image captioning model)
- Dominant Color Detection with RGB values & color name
- Stunning 2025-level glassmorphic UI with gradient backgrounds and smooth animations
- Zero setup – just upload and get results in seconds
- Fully responsive & mobile-friendly
| Technology | Purpose |
|---|---|
| Streamlit | Beautiful web interface |
| Hugging Face Transformers | BLIP model for captioning |
| PyTorch | Deep learning backend |
| PIL + scikit-learn | Dominant color extraction (KMeans) |
| Custom CSS | Modern gradient & glassmorphic design |
git clone https://github.com/yourusername/smart-image-vision.git
cd smart-image-vision
# Create virtual environment (recommended)
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Run the app
streamlit run ap.pystreamlit>=1.32.0
torch>=2.0.0
transformers>=4.35.0
pillow>=10.0.0
scikit-learn>=1.3.0
numpy>=1.21.0Run this command to generate it automatically:
pip freeze > requirements.txtPull requests are welcome! For major changes, please open an issue first.
Asad Aziz
MIT License – feel free to use, modify, and share!
⭐ Star this repo if you found it useful!