Remove backgrounds from images using Meta's Segment Anything model. Upload your picture, and get back a clean image of the main subject with a transparent background!
Seamless Background Removal: Leverage the power of Meta's Segment Anything model for accurate segmentation.
ModelBit Deployment: Deploy the model to ModelBit for easy cloud inference (instructions included).
Streamlit UI: User-friendly interface built with Streamlit for a smooth user experience.
Research Exploration: Delve into the research behind the project in the research.py
file.
Future Feature: Stay tuned for upcoming WhatsApp sticker export functionality!
Customization: Edit your images exactly how you want, without limitations imposed by pre-defined backgrounds.
Control: Self-hosting or deploying the application yourself ensures your data privacy. No need to upload sensitive images to third-party services.
Ease of Use: Simple interface makes background removal accessible to anyone.
- Clone the repository.
- Install dependencies (
pip install -r requirements.txt
) - Deploy to ModelBit following the instructions in
research.ipynb
. - Update api endpoint and run the application (
streamlit run main.py
) - Or use
research.ipynb
to run locally