Ryan Kelln's repositories
auto_video
Create a video from a set of files, each introduced with a title screen.
onsets-and-frames
A Pytorch implementation of Onsets and Frames (Hawthorne 2018)
5-directions
Five Directions ML & Art Tutorial series
Sound_Escapes
Source files for the visuals for the Sound Escapes concert
aphantasia
CLIP + FFT/DWT = text-to-image
big-sleep
A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN. Technique was originally created by https://twitter.com/advadnoun
conversational
Conversational AI so you can talk to your art projects
gdextension
GDExtension template that automatically builds into a self-contained addon for the Godot Asset Library.
GON-lightning
Gradient Origin Networks - a new type of generative model that is able to quickly learn a latent representation without an encoder
maua
Deep learning toolkit for image, video, and audio synthesis
maua-stylegan2
This is the repo for my experiments with StyleGAN2. There are many like it, but this one is mine. Contains code for the paper Audio-reactive Latent Interpolations with StyleGAN.
modest
A markdown CSS module that is rather modest.
node-export-server
Highcharts Node.js export server
open-interpreter
A natural language interface for computers
OptimalTextures
An implementation of "Optimal Textures: Fast and Robust Texture Synthesis and Style Transfer through Optimal Transport"
ReReVST-Code
Released code of Consistent Video Style Transfer via Relaxation and Regularization, TIP 2020
reveal.js-plugins
Plugins for reveal.js
stable-diffusion-vid2vid
Vid2vid script for stable diffusion webui
vimix
Live Video Mixer
WhisperLive
A nearly-live implementation of OpenAI's Whisper.
Zooming-Slow-Mo-CVPR-2020
Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)