Sihwa Park

About

Selected Works
MAIAP
Diffusion TV
YouTube Mirror
Uncertain Facing
GeoD
ARLooper
Ballet Mécanique
Brand Logo Sonification
TopicBubbles
Loading...
BeHAVE
InstaSynth
Structured Improvisation X
FormSound

Archive
SoniPi
Letter Frequency Visualization
Generative Audiovisual Study
Ring of Quartets
Hans Zimmer’s OST vs Film
︎︎︎Past Works (2008-2015)

Recent News

- Apr 8, 2025: Diffusion TV has been accepted for CVPR 2025 AI Art Gallery (On-site display and online).
- Dec 11, 2024: Diffusion TV has been accepted for the ISEA 2025 Exhibition.
- Aug 30, 2024: I performed in Exit Points#52 at Arraymusic, Toronto.
- Apr 7, 2024: YouTube Mirror was accepted for CVPR 2024 AI Art Gallery (Online).
- Oct 24, 2023: I was appointed a Connected Minds Research Enhanced Hire position with a $100,000 CAD startup fund.
- Sep 1, 2023: YouTube Mirror was presented at AIMC 2023, Brighton, UK.
- Jun 12, 2023: YouTube Mirror was accepted for AIMC 2023 as both a paper and an installation.
- May 31, 2023: YouTube Mirror was exhibited at NIME 2023, Mexico City, Mexico.
©2024 Sihwa Park

Sihwa Park


(WIP) MAIAP: Multimodal AI-based Interface for Audiovisual Performance

Date: July 2024-
Categories: AI Art, Audiovisual Interface, Audiovisual Performance, Generative

I have been working on designing a novel interface for utilizing image and sound AI models in audiovisual performance. As an early experiment, I created a prototype that generates images and sounds with pre-trained models in response to real-time webcam and mic input. The prototype was demonstrated in one of Exit Points' performances on August 30, 2024 at Arraymusic, which was organized by Michael Palumbo.

The prototype uses SpecVQGAN for sound generation and StreamDiffusion with Stable Diffusion XL Turbo for image generation, both with modifications.

Exit Points #52 Ensemble 2 Performance Footage

My Sound Generated

Exit Points #52 Swtchemups Session (Visualization Only)

Credit for the performance
  • MAYSUN: Percussion, Electronics
  • Danika Lorén: Opera
  • Emmanuel Lacopo: Electric Guitar
  • Michael Palumbo: Modular Synth
  • Sihwa Park: AI-generated Sound, Visualization
  • Video and audio recordings for the first video were provided courtesy of Arraymusic and Michael Palumbo.

This project is supported by the Connected Minds program and the Canada First Research Excellence Fund.