vcan / selfie2anime-site

What do YOU look like in Anime? Here's the source of selfie2anime.com

   

Selfie2Anime

What do YOU look like in ANIME?

This repository contains the source code for the selfie2anime.com website. Upload a selfie and find out what you look like as an anime character!

How Does it Work?

Using machine learning techniques combined with a Generative Adversarial Network (GAN) makes it possible to generate anime-style characters based on real people. With this website, you can generate your own anime alter ego!

The GAN we are using is based on original work by Junho Kim, Minjae Kim, Hyeonwoo Kang, and Kwanghee Lee. More information can be found in their awesome repository, which is available here, or in their research paper.

Sample Photos

Recent anime selfies are being published on Twitter @RicoBeti.

Here is a bunch of images that have been generated...

...and here are some of Australia's Prime Ministers

Development

(More detailed instructions will follow later)

• Install dependencies:

  npm install

• Pull submodules (the blog):

  git submodule update --init --recursive

• Set correct values for environment variables in the .env files.

• Run a quick build to generate all assets needed for development:

  DISABLE_IMAGE_OPTIMIZATION=1 npm run build

• Run development server:

  npm run serve

• Alternatively, build the release version:

  npm run build

  Building a release version may take a long time due to generation of the portfolio and due to image optimizations being performed. In case the portfolio has not changed, set DISABLE_PORTFOLIO_BUILD=1 to suppress regeneration of the images.

  For development and testing, set DISABLE_IMAGE_OPTIMIZATION=1 to avoid wasting time on image compression.

License

MIT, see LICENSE.txt.