The use case is control. It's essentially a controlnet for the actual music writing. So a musician could compose melody, harmony, and lyrics and generate many performances of the same song until they get one they like. A non-musician could similarly generate the symbolic input from scratch, and perhaps they like the composition but not the performance. This allows them to re-render and re-render until they like the performance.

> a musician could compose melody, harmony, and lyrics and generate many performances of the same song until they get one they like

Can't relate to this. Art doesn't come out as a left-brained problem solving exercise or identifying the right product for a market. It's about expression. You do it when you're feeling things.

Why.