Music Prompt Pixaroma

Turns one idea into the two pieces of writing a music model needs: a caption describing how the song should SOUND, and the lyrics that get sung. Wire both straight into MiniMax Music 3, and the duration output into its max_duration, so the song is given exactly the time the words were written for. It runs a language model you already have, on your own machine, twice on one load. The wording of both instructions is built in and was measured rather than guessed, so there is no formula to write: you type the idea and set the length, and the controls do the rest. Length is the important one. The music model treats it as a ceiling, so a lyric written for three minutes against a thirty second setting is simply cut off part way through. Wiring the duration output means you only set it here. A song can still come out shorter than you asked, because the music model stops when the words run out. If that happens, press Re-roll: how many lines get written varies from one seed to the next. Verses are a request, not a promise. One and two come back exactly as asked; three sometimes drifts. Left on Auto the length alone decides the shape, which is the most reliable way to run it. With no model chosen it passes your text through to both outputs, so you can drop it into a working graph and set it up afterwards. Find it by searching for music, song, lyrics, caption, or minimax.