Audio Visual interaction based on AI paintings

Just tried adding some audio-visual effect onto an portrait painting generated by AI.

The full video:

The original painting generated by AI, a model using StyleGAN2.

The visual effect created mostly from shader.
And I used the handy and cool software “Fragment:Flow” based on MaxMSP/Jitter.

BGM: “Green Lake Remix 006”, by dogone – my old friend who can repair airplanes.