Text-to-image Generation Using Stable Diffusion
Deep Learning Algorithm
An implementation of a lightweight Variational Autoencoder, UNet, and pre-trained CLIP within a stable diffusion model in TensorFlow.
The ROLI Seaboard: Toward A New Understanding Of Musical Interfaces
Pioneer Research Program
STS Research Paper
This paper seeks to argue for an expanded conceptualization of how musicians interact with musical instruments, where software, hardware, and cultural components are analyzed as equal actors constituting the entire interaction.
Advisor: Professor Marianne de Laet | Harvey Mudd College
Published in the September 2022 Issue of The Schola.
The GAN Color Organ:
Generate visual music using onset detection and HistoGAN
Deep Music Visualizer
The GAN Color Organ aims to fuse this tradition with AI-generated visuals by integrating audio feature extraction, generative adversarial networks (GAN), and color modification into one complete algorithm. Using this program, artists could create generative GAN-based music visualizations.
Multi-Split Instrument
Max/MSP
A multi-split instrument configured with 8 snapshots that represent different effects combinations; adjustable transposition and chord voices using number boxes; a split object that routes midi signals greater than C4 to another VST instrument; a simple gray panel as the user interface; and the unmenu object to select MIDI input.
