Fast Style Transfer in TensorFlow

Add styles from famous paintings to any photo in a fraction of a second!

It takes 100ms on a 2015 Titan X to style the MIT Stata Center (1024×680) like Udnie, by Francis Picabia.

Our implementation is based off of a combination of Gatys’ A Neural Algorithm of Artistic Style, Johnson’s Perceptual Losses for Real-Time Style Transfer and Super-Resolution, and Ulyanov’s Instance Normalization.
THe repository i based on

Image Stylization

We added styles from various paintings to a photo of Chicago. Click on thumbnails to see full applied style images.

Implementation Details

Our implementation uses TensorFlow to train a fast style transfer network. We use roughly the same transformation network as described in Johnson, except that batch normalization is replaced with Ulyanov’s instance normalization, and the scaling/offset of the output tanh layer is slightly different. We use a loss function close to the one described in Gatys, using VGG19 instead of VGG16 and typically using “shallower” layers than in Johnson’s implementation (e.g. we use relu1_1 rather than relu1_2). Empirically, this results in larger scale style features in transformations.

Virtual Environment Setup (Anaconda) – Windows/Linux

Tested on

Operating System Windows 10 Home
GPU Nvidia GTX 2080 TI
CUDA Version 11.0
Driver Version 445.75

Step 1:Install Anaconda

Step 2:Build a virtual environment

Run the following commands in sequence in Anaconda Prompt:

conda create -n tf-gpu tensorflow-gpu=2.1.0
conda activate tf-gpu

Run the following command in the notebook or just conda install the package:

!pip install moviepy==1.0.2

Follow the commands below to use fast-style-transfer


Training Style Transfer Networks

Use to train a new style transfer network. Run python to view all the possible parameters. Training takes 4-6 hours on a Maxwell Titan X. More detailed documentation here. Before you run this, you should run Example usage:

python --style path/to/style/img.jpg \
  --checkpoint-dir checkpoint/path \
  --test path/to/test/img.jpg \
  --test-dir path/to/test/dir \
  --content-weight 1.5e1 \
  --checkpoint-iterations 1000 \
  --batch-size 20

Evaluating Style Transfer Networks

Use to evaluate a style transfer network. Run python to view all the possible parameters. Evaluation takes 100 ms per frame (when batch size is 1) on a Maxwell Titan X. More detailed documentation here. Takes several seconds per frame on a CPU. Models for evaluation are located here. Example usage:

python --checkpoint path/to/style/model.ckpt \
  --in-path dir/of/test/imgs/ \
  --out-path dir/for/results/


You will need the following to run the above:

  • TensorFlow 0.11.0
  • Python 2.7.9, Pillow 3.4.2, scipy 0.18.1, numpy 1.11.2
  • If you want to train (and don’t want to wait for 4 months):
    • A decent GPU
    • All the required NVIDIA software to run TF on a GPU (cuda, etc)
  • ffmpeg 3.1.3 if you want to stylize video


View Github