Need help with fast-neural-style?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

200 Stars 52 Forks 15 Commits 2 Opened issues


Fast neural style in tensorflow based on

Services available


Need anything else?

Contributors list

Fast neural style transfer

A short writeup and example images are up on my blog.

In an attempt to learn Tensorflow I've implemented an Image Transformation Network as described in Perceptual Losses for Real-Time Style Transfer and Super-Resolution by Johnson et al.

This technique uses loss functions based on a perceptual similarity and style similarity as described by Gatys et al to train a transformation network to synthesize the style of one image with the content of arbitrary images. After it's trained for a particular style it can be used to generate stylized images in one forward pass through the transformer network as opposed to 500-2000 forward + backward passes through a pretrained image classification net which is the direct approach.

Update Oct 23rd

  • Changed upscale method to the one mentioned in
  • Better padding befoer each convolution to avoid border effects
  • For some reason, padding the original image before the transformation image removes a lot of noise.
  • "Instance normalization" instead of batch normalization as mentioned in Instance Normalization: The Missing Ingredient for Fast Stylization
  • No longer python3.

While the results are now much better, I'm still not sure why the original implementation didn't perform as well as Johnsons original work (Now published here)


First get the dependecies (COCO training set images and VGG model weights):


To generate an image directly from style and content, typically to explore styles and parameters:

python --CONTENT_IMAGE content.png --STYLE_IMAGES style.png

Also see other settings and hyperparameters in

To train a model for fast stylizing first download dependences (training images and VGG model weights):


Then start training:

python --STYLE_IMAGES style.png --NAME=my_model


points to a directory of JPEGs to train the model.
is used for tensorboard statistics and file name of model weights. The paper uses the COCO image dataset (13GB).

To generate images fast with an already trained model:

python --IMAGE_PATH=my_content.jpg --NAME=my_model



  • Add a pretrained model
  • Add example pictures / videos


We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.