Transform your photos into artwork using deep learning and pre-trained models like oil painting,candy, udnie, rain_princess, and more — all powered by PyTorch and Flask with a beautiful user interface.
- Upload your own image and apply different artistic styles
- Choose from multiple
.pthstyle models - RGB glowing buttons and smooth animations
- Sparkle + buffer effect during image processing
- Clean, mobile-friendly design
- Download your stylized image instantly
neural-style-transfer-app/
├── app_multiple_styles.py # Flask backend logic
├── model.py # TransformerNet model definition
├── templates/
│ └── index.html # Frontend HTML page
├── static/
│ ├── style.css # (Optional) Additional CSS
│ └── logo.png # App branding logo
├── saved_models/
│ ├── candy.pth
│ ├── oil_painting.pth
│ ├── rain_princess.pth
│ └── udnie.pth
└── requirements.txt # Required Python packages
candy.pthoil_painting.pthrain_princess.pthudnie.pth
You can download more .pth models from:
- https://github.com/gnsmrky/pytorch-fast-neural-style-for-web
- https://github.com/pytorch/examples/tree/main/fast_neural_style
- Clone the repository:
git clone https://github.com/yourusername/neural-style-transfer-app.git
cd neural-style-transfer-app- Create a virtual environment and install dependencies:
python -m venv venv
Windows: venv\Scripts\activate # Linux source venv/bin/activate
pip install -r requirements.txt- Run the app:
python app_multiple_styles.pyVisit http://127.0.0.1:5000 in your browser.
- Upload a content image.
- Select a style model.
- Click "✨ Stylize Image" — the image is sent to the backend.
- The selected model applies style transfer using
TransformerNet. - The stylized output is shown with the option to download.
- Flask
- Torch
- torchvision
- Pillow
Install via:
pip install -r requirements.txt
***
MIT License © 2025 Vignesh M