Skip to content

A Deep Learning based project for creating line art portraits.

License

Notifications You must be signed in to change notification settings

vijishmadhavan/ArtLine

Repository files navigation

ArtLine

You can sponsor me to support my open source work 💖 sponsor

The main aim of the project is to create amazing line art portraits.

Exciting update

ControlNet + ArtLine for portraits, Try colab!!

ControlNet + ArtLine

The model is designed to take in a portrait image and a corresponding written instruction, and then use that instruction to adjust the style of the image.

model

model

model

Shahrukh

Highlights

Example Images

bohemian rhapsody movie , Rami Malek American actor

bohemian

Photo by Maxim from Pexels

Imgur

Keanu Reeves, Canadian actor.

Keanu

Photo by Anastasiya Gepp from Pexels

Imgur

Interstellar

Interstellar

Pexels Portrait, Model

Imgur

Beyoncé, American singer

Beyoncé

Model-(Smooth)

Model-(Quality)

Open in RunwayML Badge

Click on the below image to know more about colab demo, credits to Bhavesh Bhatt for the amazing Youtube video.

Line Art

The amazing results that the model has produced has a secret sauce to it. The initial model couldn't create the sort of output I was expecting, it mostly struggled with recognizing facial features. Even though (https://github.com/yiranran/APDrawingGAN) produced great results it had limitations like (frontal face photo similar to ID photo, preferably with clear face features, no glasses and no long fringe.) I wanted to break-in and produce results that could recognize any pose. Achieving proper lines around the face, eyes, lips and nose depends on the data you give the model. APDrawing dataset alone was not enough so I had to combine selected photos from Anime sketch colorization pair dataset. The combined dataset helped the model to learn the lines better.

Movie Poster created using ArtLine.

The movie poster was created using ArtLine in no time , it's not as good as it should be but I'm not an artist.

Poster

Poster

Technical Details

Surprise!! No critic,No GAN. GAN did not make much of a difference so I was happy with No GAN.

The mission was to create something that converts any personal photo into a line art. The initial efforts have helped to recognize lines, but still the model has to improve a lot with shadows and clothes. All my efforts are to improve the model and make line art a click away.

Imgur

Dataset

APDrawing dataset

Anime sketch colorization pair dataset

APDrawing data set consits of mostly close-up portraits so the model would struggle to recogonize cloths,hands etc. For this purpose selected images from Anime sketch colorization pair were used.

Going Forward

I hope I was clear, going forward would like to improve the model further as it still struggles with random backgrounds(I'm creating a custom dataset to address this issue).

I will be constantly upgrading the project for the foreseeable future.

Getting Started Yourself

The easiest way to get started is to simply try out on Colab: https://colab.research.google.com/github/vijishmadhavan/Light-Up/blob/master/ArtLine(Try_it_on_Colab).ipynb

Installation Details

This project is built around the wonderful Fast.AI library.

  • fastai==1.0.61 (and its dependencies). Please dont install the higher versions
  • PyTorch 1.6.0 Please don't install the higher versions

Limitations

  • Getting great output depends on Lighting, Backgrounds,Shadows and the quality of photos. You'll mostly get good results in the first go but there are chances for issues as well. The model is not there yet, it still needs to be tweaked to reach out to all the consumers. It might be useful for "AI Artisits/ Artists who can bring changes to the final output.

  • The model confuses shadows with hair, something that I'm trying to solve.

  • It does bad with low quality images(below 500px).

  • I'm not a coder, bear with me for the bad code and documentation. Will make sure that I improve with upcoming updates.

Updates

Get more updates on Twitter

Mail me @ [email protected]

Acknowledgments

License

All code in this repository is under the MIT license as specified by the LICENSE file.