# lengstrom/fast-style-transfer

**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/lengstrom-fast-style-transfer).**

10,963 stars · 2,553 forks · Python

## Links

- GitHub: https://github.com/lengstrom/fast-style-transfer
- awesome-repositories: https://awesome-repositories.com/repository/lengstrom-fast-style-transfer.md

## Topics

`deep-learning` `neural-networks` `neural-style` `style-transfer`

## Description

This project is a TensorFlow-based neural style transfer framework designed to apply the artistic textures and colors of a painting to images and videos. It utilizes a feed-forward image stylizer that transforms visual appearance in a single pass, avoiding the need for iterative optimization.

The system includes a deep learning training pipeline that teaches convolutional neural networks to replicate specific styles using perceptual loss functions. It also features a video frame processor that decomposes video files into individual images for sequential stylization and reassembly.

The software covers a broad range of capabilities including batch image processing, style transfer network training, and temporal frame processing for videos. It supports checkpoint-based model loading to restore trained network weights for immediate application and provides tools for style output verification.

## Tags

### Artificial Intelligence & ML

- [CNN Image Stylizers](https://awesome-repositories.com/f/artificial-intelligence-ml/cnn-image-stylizers.md) — Provides a CNN-based image stylizer that transforms visual appearance in a single feed-forward pass.
- [Convolutional Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks.md) — Utilizes convolutional neural network architectures to process image data for artistic transformation.
- [Deep Learning Training Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-learning-training-pipelines.md) — Provides a complete deep learning training pipeline to teach models to replicate specific artistic styles.
- [Feed-Forward Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/feed-forward-neural-networks.md) — Employs a feed-forward neural network to apply styles in a single pass without iterative optimization.
- [Loss Functions](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/neural-network-components/loss-functions.md) — Optimizes network weights using loss functions that measure differences between style and content representations.
- [Perceptual Loss](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/neural-network-components/loss-functions/perceptual-loss.md) — Uses perceptual loss functions to minimize the difference between generated images and target artistic styles.
- [Neural Style Transfers](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-style-transfers.md) — Implements a neural style transfer framework using TensorFlow to apply artistic textures to media.
- [Style Network Training](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-style-transfers/style-network-training.md) — Implements a training process for convolutional networks to learn and replicate specific artistic styles. ([source](https://github.com/lengstrom/fast-style-transfer/blob/master/docs.md))
- [Vision Model Weight Loading](https://awesome-repositories.com/f/artificial-intelligence-ml/large-scale-model-training/vision-transformer-pre-training/pre-trained-model-checkpoints/vision-model-weight-loading.md) — Supports loading pre-trained weight checkpoints for computer vision architectures to enable immediate stylization.
- [Model Checkpoints](https://awesome-repositories.com/f/artificial-intelligence-ml/model-checkpoints.md) — Provides utilities for loading pre-trained model weights from checkpoints for immediate use.
- [TensorFlow Graph Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/tensorflow-graph-execution.md) — Performs high-speed image tensor transformations using TensorFlow's hardware-accelerated graph execution.
- [TensorFlow Model Development](https://awesome-repositories.com/f/artificial-intelligence-ml/tensorflow-model-development.md) — Leverages the TensorFlow ecosystem for developing and executing the style transfer model.

### Part of an Awesome List

- [Visual Feature Extractors](https://awesome-repositories.com/f/awesome-lists/devtools/feature-extraction/visual-feature-extractors.md) — Implements convolutional layers to extract spatial textures and colors from source images.
- [Video-to-Video Stylization](https://awesome-repositories.com/f/awesome-lists/ai/video-and-animation/video-to-video-stylization.md) — Transforms existing video footage into artistic styles through frame-by-frame neural processing.

### Development Tools & Productivity

- [Batch Image Stylization](https://awesome-repositories.com/f/development-tools-productivity/batch-image-stylization.md) — Enables batch processing of image directories to apply consistent artistic styles. ([source](https://github.com/lengstrom/fast-style-transfer/blob/master/docs.md))

### Graphics & Multimedia

- [Video File Processors](https://awesome-repositories.com/f/graphics-multimedia/media-processing-analysis/media-manipulation/media-processing/video-analysis-processing/video-file-processors.md) — Includes a video file processor that decomposes clips into frames for sequential stylization.
- [Sequential Frame Processing](https://awesome-repositories.com/f/graphics-multimedia/media-processing-analysis/media-manipulation/video-processing-tools/video-frame-navigators/array-based-frame-processing/sequential-frame-processing.md) — Implements a processing loop that applies artistic style filters to a sequence of video frames. ([source](https://github.com/lengstrom/fast-style-transfer#readme))