» Waifu Synthesis- real time generative anime
This site relies heavily on Javascript. You should enable it if you want the full experience. Learn more.

Waifu Synthesis- real time generative anime

Watch on Vimeo

http://everyoneishappy.com
https://www.instagram.com/everyoneishappy/
Bit of a playful project investigating real-time generation of singing anime characters, a neural mashup if you will.

All of the animation is made in real-time using a StyleGan neural network trained on the Danbooru2018 dataset, a large scale anime image database with 3.33m+ images annotated with 99.7m+ tags.

Lyrics were produced with GPT-2, a large scale language model trained on 40GB of internet text. I used the recently released 345 million parameter version- the full model has 1.5 billion parameters, and has currently not been released due to concerns about malicious use (think fake news).

Music was made in part using models from Magenta, a research project exploring the role of machine learning in the process of creating art and music.

Setup is using vvvv, Python and Ableton Live.

StyleGan, Danbooru2018, GPT-2 and Magenta were developed by Nvidia, gwern.net/Danbooru2018, OpenAI and Google respectively.

Kyle McLean, Wednesday, Aug 7th 2019 Digg | Tweet | Delicious comments on vimeo  
  • 1

anonymous user login

Shoutbox

~3d ago

microdee: 2 seconds later: I asked before googling, but why do you need OS support for texture compression?

~3d ago

microdee: what's BC7?

~3d ago

antokhio: https://aka.ms/AA65g28 upvote pls for bc7 support in windows

~5d ago

joreg: PSA: forum is back up and running!

~5d ago

manuel: that shaderFX looks great

~5d ago

joreg: PSA: the forum is currently down for maintainance. if all goes well it will be back up shortly..