Workflows / MiniMax Music

Free workflow
Song from an idea
Idea in, finished song out.
A local LLM writes the structured caption and lyrics, MiniMax Music 3 sings it. Full-length songs, no API.
Download workflow — free
Drag the .json onto ComfyUI. Runs best on the Gmanski RunPod template.
You get
- Music 3 workflow + Song Planner node
You need
- 48 GB VRAM
Model packs · Music & voice
musicOn the template: gmanski-packs install music
Pairs well with.
ACE-StepnewSong from an idea — ACE-Step
A second song engine. Apache 2.0, 8 steps.
Beginner · 16 GB+Free
VoicenewVoice Clone — speak in your voice
Ten seconds of your voice. Any text, 23 languages.
Beginner · 12 GB+Free
VoicenewVoice Clone — any song in your voice
Same song, same backing track, your voice singing it.
Beginner · 16 GB+Free