AI-Powered Multi-Object Segmentation & Vector Conversion Service
Transform any image into a library of extractable design assets. Select individual objects and export them as transparent PNGs or scalable SVGs.
- Python 3.10+
- uv (recommended) or pip
# Clone the repository
git clone https://github.com/your-username/nuki.git
cd nuki
# Install uv (if not installed)
curl -LsSf https://astral.sh/uv/install.sh | sh
# Create virtual environment and install dependencies
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
uv pip install -r requirements.txt
# Install SAM 2 from GitHub
uv pip install git+https://github.com/facebookresearch/sam2.git# With activated virtual environment
streamlit run app.py
# Or using uv run
uv run streamlit run app.pyThe app will open at http://localhost:8501
- Automatic Object Detection: AI identifies all objects in your image
- Click-to-Select: Simply click on objects to select them
- Multi-Select: Select multiple objects for batch export
- Transparent PNG Export: Export with perfect transparency
- SVG Vectorization: Convert to scalable vector graphics
- Batch ZIP Download: Download all selected objects at once
- AI Models: Meta SAM 2 (Segment Anything Model 2)
- Framework: Streamlit
- Vectorization: vtracer
- Language: Python 3.10+
MIT License