LyricVis

A personal experiment in generative AI and creative media. The question: could song lyrics, fed into an image model one phrase at a time, produce visuals that actually deepen how you experience a piece of music?

LyricVis generates a unique AI image for each lyric phrase, synchronizes them to the audio track, and compiles the result into a music video — built entirely from the language of the song itself. No director, no crew, no budget. Just lyrics, a model, and the question of what they produce together.

Built on Python, Stable Diffusion, and moviepy. Results vary by song. That's part of what makes it worth exploring.