Deep Learning and Computer Vision has evolved and done wonders time and again. Today I would like to introduce my new project ‘Toon-Me’ after the phenomenal success of ArtLine(Over 2.7k GitHub Stars), ‘Toon-Me’ uses deep learning algorithms to achieve fine quality line art portraits. It is currently the most trending
topic in both GitHub and paperswithcode.
https://github.com/vijishmadhavan/Toon-Me
The model has been built using an custom dataset using many different algorithms, derived from some research papers self-attention, progressive resizing and generator loss. It shows how stacking all the methods can generate high-quality results. Primarily PyTorch and Fastai libraries are used. It generates fine lines/edges in the sketch image, which is better than most existing methods. Try out the demo from the Colab Notebook provided in the Github repo with any portrait picture which is expected in an URL and then converted to image formats. You can clone the repository or tweak the code to use your local image file and within less than 2 minutes (executing with GPU).
Top comments (0)