This project focuses on Neural Style Transfer (NST), a technique that applies the style of one image to the content of another image, creating a new, stylized image. NST leverages deep learning models, particularly Convolutional Neural Networks (CNNs), to extract and combine the content and style features of images. This project will guide you through setting up, training, and using a neural style transfer model to create beautiful artistic images.
- Content and Style Image Processing: Load and preprocess images.
- Style Transfer Model: A CNN model for NST.
- Training Script: Train the model with content and style images.
- Image Generation Script: Generate new stylized images.
- Results Visualization: Visualize and save stylized images.
-
Clone the repository
git clone https://github.com/SreeEswaran/NST-for-Artistic-Image-Creation.git cd NST-for-Artistic-Image-Creation
-
Install the dependencies
pip install -r requirements.txt
python script/train.py
# or
python scripts/train.py --content_path data/content/content_image.jpg --style_path data/style/style_image.jpg --output_path outputs/stylized_images
python scripts/generate.py
(or)
python scripts/generate.py --content_path data/content/content_image.jpg --style_path data/style/style_image.jpg --output_path outputs/stylized_images