Style2paints V4 is an AI driven lineart colorization tool.

Different from previous end-to-end image-to-image translation methods, style2paints V4 is the first system to colorize a lineart in real-life human workflow, and the outputs are layered.

Inputs:

● Linearts
● (with or without) Human hints
● (with or without) Color style reference images
● (with or without) Light location and color

Outputs:

● Automatic color flattening without lines (solid/flat/inherent/固有色/底色 color layer)
● Automatic color flattening with black lines
● Automatic colorization without lines
● Automatic colorization with black lines
● Automatic colorization with colored lines
● Automatic rendering (separated layer)
● Automatic rendered colorization

Style2paints V4 gives you results of the current highest quality. You are able to get separated layers from our system. These layers can be directly used in your painting workflow. Different from all previous AI driven colorization tools, our results are not single 'JPG/PNG' images, and in fact, our results are 'PSD' layers.

User Instruction: https://style2paints.github.io/

And we also have an official Twitter account.

Most human artists are familiar with this workflow:

sketching -> color filling/flattening -> gradients/details adding -> shading

And the corresponding layers are:

lineart layers + flat color layers + gradient layers + shading layers

Style2paints V4 is designed for this standard coloring workflow! In style2paints V4, you can automatically get separated results from each step!

Here we present some results in this ABCD format. Users only need to upload their sketch, select a style, and put a light source.

When the result is achieved immediately without any human color correction, we regard this result as fully automatic result. When the result needs some color correction, human can easily put some color hints on the canvas to guide the AI coloring process. In this case, we regard these results as semi-automatic results. If a result is semi-automatic, but the quantity of human color hint points is smaller than 10, we regard these results as almost automatic result. In this section, about half of the presented results are fully automatic result, and the others are all almost automatic result. Do notice that all the below results can be achieved with less than 15 clicks!

ACPR 2017:

@Article{ACPR2017ZLM,
  author  = {LvMin Zhang, Yi Ji and ChunPing Liu},
  title   = {Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN},
  conference = {Asian Conference on Pattern Recognition (ACPR)},
  year    = {2017},
}

paper

No Publications.

TOG 2018:

@Article{ACMTOGTSC2018,
  author  = {LvMin Zhang, Chengze Li, Tien-Tsin Wong, Yi Ji and ChunPing Liu},
  title   = {Two-stage Sketch Colorization},
  journal = {ACM Transactions on Graphics},
  year    = {2018},
  volume  = {37},
  number  = {6},
  month   = nov,
  doi     = {https://doi.org/10.1145/3272127.3275090},
}

paper

No Publications.

CVPR2021

@InProceedings{Filling2021zhang,
  author={Lvmin Zhang and Chengze Li and Edgar Simo-Serra and Yi Ji and Tien-Tsin Wong and Chunping Liu}, 
  booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, 
  title={User-Guided Line Art Flat Filling with Split Filling Mechanism}, 
  year={2021}, 
}