# jcjohnson/fast-neural-style

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/jcjohnson-fast-neural-style).**

4,354 stars · 808 forks · Lua

## Links

- GitHub: https://github.com/jcjohnson/fast-neural-style
- awesome-repositories: https://awesome-repositories.com/repository/jcjohnson-fast-neural-style.md

## Description

This project is a neural style transfer framework that provides a suite of computer vision tools for applying artistic styles to images and video. It functions as a system for training feedforward neural networks, an iterative style optimizer, and a real-time video stylizer.

The framework supports two primary methods of stylization: a feedforward model that applies styles in a single pass and an iterative optimization method that generates stylized images by minimizing content and style loss without a pre-trained model. It also enables real-time processing of live webcam feeds using trained models.

The project covers several capability areas, including artistic image processing, style transfer model training through perceptual loss minimization, and dataset preparation utilities to format image folders into compatible training sets.

## Tags

### Artificial Intelligence & ML

- [Neural Style Transfers](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-style-transfers.md) — Implements deep learning techniques to transform the appearance of images to match specific artistic styles. ([source](https://github.com/jcjohnson/fast-neural-style/blob/master/doc/flags.md))
- [CNN Image Stylizers](https://awesome-repositories.com/f/artificial-intelligence-ml/cnn-image-stylizers.md) — Uses convolutional neural networks to apply trained artistic styles to single images or image directories. ([source](https://github.com/jcjohnson/fast-neural-style#readme))
- [Iterative Image Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/iterative-image-optimizers.md) — Generates stylized images by refining pixels through iterative gradient descent to minimize content and style loss.
- [Style Application Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-building-blocks/feedforward-architectures/style-application-networks.md) — Implements a feedforward neural network that applies a visual style to an image in a single pass.
- [Style Transfer Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/style-transfer-frameworks.md) — Offers a comprehensive system for managing the transfer of artistic styles across images and video.
- [Perceptual Loss](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/neural-network-components/loss-functions/perceptual-loss.md) — Trains models by minimizing perceptual loss, comparing high-level feature maps of stylized and target images.
- [Style Transfer Training](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-building-blocks/feedforward-architectures/style-transfer-training.md) — Provides tools for creating and optimizing neural networks to apply specific visual styles efficiently.
- [Style Network Training](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-style-transfers/style-network-training.md) — Trains networks to learn artistic styles from reference images using a pre-trained loss network.

### Graphics & Multimedia

- [Artistic Image Processing](https://awesome-repositories.com/f/graphics-multimedia/artistic-image-processing.md) — Converts photos and image directories into stylized artwork using trained machine learning architectures.
- [Frame-By-Frame Stream Processing](https://awesome-repositories.com/f/graphics-multimedia/frame-by-frame-stream-processing.md) — Transforms live video by processing the stream as a sequence of discrete frames for real-time stylization.
- [Real-Time Video Filtering](https://awesome-repositories.com/f/graphics-multimedia/real-time-video-filtering.md) — Performs low-latency processing of live webcam streams to apply neural artistic styles in real time. ([source](https://github.com/jcjohnson/fast-neural-style/blob/master/doc/flags.md))