Multi-style Generative Network for Real-time Transfer
Clone or download
Latest commit 6bc8140 Nov 11, 2017
Type Name Latest commit message Commit time
Failed to load latest commit information.
cmake cmake Mar 28, 2017
experiments rm filter May 26, 2017
images demo May 28, 2017
modules module Mar 24, 2017
.editorconfig init Mar 21, 2017
.gitignore code Mar 24, 2017
CMakeLists.txt code Mar 24, 2017 Update Oct 6, 2017 training May 26, 2017
init.lua code Mar 24, 2017
texture-scm-1.rockspec code Mar 24, 2017

Multi-style Generative Network for Real-time Transfer [arXiv] [project]
Hang Zhang, Kristin Dana
	title={Multi-style Generative Network for Real-time Transfer},
	author={Zhang, Hang and Dana, Kristin},
	journal={arXiv preprint arXiv:1703.06953},


We also provide PyTorch implementation and MXNet implementation. Please install Torch7 with cuda and cudnn support. The code has been tested on Ubuntu 16.04 with Titan X Pascal and Maxwell.

luarocks install

Test and Demo

  1. Clone the repo and download pre-trained models
    git clone
    cd MSG-Net/experiments
    bash models/ 
  2. Web Camera Demo
    qlua webcam.lua
  3. Test on Image
    th test.lua -input_image images/content/venice-boat.jpg -image_size 1024
    eog stylized

[More Example Results]

Train Your Own Model

Please follow this tutorial to train a new model.

Release Timeline

  • 03/20/2017 we have released the demo video.
  • 03/24/2017 We have released ArXiv paper and test code with pre-trained models.
  • 04/09/2017 We have released the training code.
  • 04/24/2017 Please checkout our PyTorch implementation.


The code benefits from outstanding prior work and their implementations including: