neural-style-pt
A PyTorch implementation of neural style transfer, combining the content of one image with the artistic style of another.
What is neural-style-pt?
neural-style-pt is a PyTorch implementation of the neural style transfer algorithm. It uses a convolutional neural network (like VGG-19) to separate and recombine the content and style of images, allowing users to create new images that have the content of a photograph and the artistic style of a painting. It solves the problem of algorithmically applying complex artistic textures and patterns to any given image.
Machine learning researchers, computer vision practitioners, digital artists, and developers interested in experimenting with generative AI and artistic image manipulation using PyTorch.
Developers choose this implementation for its faithful PyTorch port of the original algorithm, extensive feature set (like multi-style blending and GPU optimization), and the flexibility it offers for tuning and research compared to other implementations.
Overview
PyTorch implementation of neural style transfer algorithm
Use Cases
Best For
- Applying the style of famous paintings (like Starry Night) to personal photographs
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
