ACE-Step music · self-hosted
ACE-Step music sound model, self-hosted on Wavemaker's GPU fleet. Pick it in the model picker or name it in your brief. This page gathers its model configurations and example graphs.
Discover · Wavemaker catalog
When to use it
- ACE-Step music sound model, self-hosted on Wavemaker's GPU fleet. Pick it in the model picker or name it in your brief. This page gathers its model configurations and example graphs.
What you provide
- A musical brief and any exact lyrics supported by the selected graph.
- The exact script, language and supported voice choice.
What you get
- An editable configuration and bound Comfy graph; rendered media is produced only after a separate run.
- A grouped reference list; each item has its own inputs, setup and execution requirements.
- An editable Comfy graph with the stages listed in Technical details. Generated outputs depend on the selected runtime and bound inputs.
- Output stages: Audio.
Creative guidance
- ACE-Step · music: Prepare a music-generation graph using ACE-Step and the source's supported musical/text controls.
- Kokoro · authored speech: Turn an authored script into speech using the retained Kokoro configuration.
- MiniMax Music 3 · retained route: Use the retained Music 3 song-generation route; it is separate from the explicit native INT8 profile.
- MiniMax Music 3 · native INT8: Author a song through the native INT8 graph, preserving supplied lyrics; the recorded short decoded output has no listening qualification.
- Model · ACE-Step: ACE-Step 1.5 open music (native ComfyUI ACE nodes, runtime-v4).
- ACE-Step 1.5 Music: MIT ACE-Step 1.5 open music via native ComfyUI ACE nodes (runtime-v4 / ComfyUI ≥0.19). XL excluded.
Setup and requirements
- Name the option you want in your brief; the agent reads its method or configuration (Source entry points) and applies it.
Source licenses and model terms continue to apply. Check runtime availability before generation.
Download source · Learn how to reuse resources