This repostiroy for the paper Genny: Designing and Exploring a Live Coding Interface for Generative Models authored by Junichi Shimizu and Rebecca Fiebrink. This paper was presented at the 7th International Conference on Live Coding (ICLC2023) in Utrecht.
- react-codemirror
- glsl-canvas : might not use
- babel-plugin-glsl
- three.js
- react-three/drei
- react-three/fiber
- Dropfile
- Material UI
- Parser : @lezer/highlight
- Config : js-yaml
- tone.js
- tone.js/midi
- tensorflow.js
- magenta.js
Current genny's code is really complex. I am thinking to update the code to make it more readable and maintainable.
- support repricate API? and audio generation?
- convert to typescript
- bug fix some web audio api
- update latest react-code mirror
- multiple model running simultaneously
- redefine rhythm pattern representation and allow to upload own sound file
- show model loading state