Free workflow · new

Song from an idea — ACE-Step

A second song engine. Apache 2.0, 8 steps.

ACE-Step 1.5 XL Turbo writes a full song with vocals from a style caption and lyrics in 8 steps. Same Song Planner front end as the MiniMax Music 3 kit, so one brief can go to both engines.

Model: ACE-Step
VRAM: 16 GB+
Level: Beginner

Download workflow — free

Drag the .json onto ComfyUI. Runs best on the Gmanski RunPod template.

You get

Gmanski Music (ACE-Step) workflow + Song Planner

You need

16 GB VRAM

Model packs · Music & voice

ace-step

On the template: gmanski-packs install ace-step

Pairs well with.

Voicenew

Voice Clone — speak in your voice

Ten seconds of your voice. Any text, 23 languages.

Beginner · 12 GB+Free

Voicenew

Voice Clone — any song in your voice

Same song, same backing track, your voice singing it.

Beginner · 16 GB+Free

Voicenew

Vocal Split — a voice sample from any song

Pull the lead vocal out of a finished song.

Beginner · 8 GB+Free