We have released our dataset for public use. The dataset can be downloaded through following links:

    Sketch-image pairs:

    Sketch with control color blocks:

    Orginal README

    It is the original implementation of the journal article: Auto-painter: Cartoon image generation from sketch by using conditional Wasserstein generative adversarial networks

    This project mean to make an end-to-end network for the sketch of cartoon to have color automatically.

    Try our demo here:

    Since the lab's server has temporarily expired, the demo is now unavailable. You can see the demo video and train your own model. Or you can build your demo page based on our provided models following this project:

    New model has been updated!~ The performance is much better than in the orginal paper! See the demo video:

    Have a try~

    The pre-trained model can be downloaded from the following link:

    My homepage:

    Welcome to contact me~




    Vgg model from:, if you use the loss_f)


    Color images: Collected on the Internet

    Sketch: Generated from the preprocessing/gen_sketch/

    Quick start

    Put you orginal data in the folder preprocessing/gen_sketch/pic_org

    Run the and you will get the training set in the preprocessing/gen_sketch/pic_sketch folder

    Download the pre-train weight of Vgg16, and put the model and the pretrian weight uder the folder of training&test/my_vgg

    Run the training command as:

    python --mode train --input_dir $TRAINING_SET --output_dir $OUTPUT --checkpoint None

    Run the testing command as:

    python --mode test --input_dir $TESTING_SET --output_dir $OUTPUT_TEST --checkpoint $OUTPUT


    🚀 Github 镜像仓库 🚀




    贡献者 3

    Y yifan liu @yifan liu
    D divyanshu964 @divyanshu964
    I irfanICMLL @irfanICMLL


    • Python 100.0 %