Skip to content
Neural Artistic Style Implementation in Tensorflow
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Neural Artistic Style Implementation in TensorFlow

By Yulun Tian []

(Illustration from "A Neural Algorithm of Artistic Style", Gatys et al. 2015)

Video demonstration []


This project replicates the results in "A Neural Algorithm of Artistic Style", Gatys et al. 2015. A neural network is trained to create new artistic images by recombining styles and contents from different inputs. Total variation denoising is also integrated to ensure the output image is visually coherent.

The original paper can be accessed here: []

The neural network used in this project is based on a VGG16 model pre-trained on ImageNet. The model is kindly provided by Davi Frossard: []

Run this project

To run this project, make sure you have TensorFlow installed. This project is currently compatible with TensorFlow 1.0.

Also, download the pre-trained VGG 16 model using this link, and place the downloaded vgg16_weights.npz file under vgg16/models/.

To run a demo, run the following in your terminal:


To see the full options, run:

python --help

You can’t perform that action at this time.