Run this workflow on InstaSD
Get started in minutes! Run this ComfyUI workflow online - no setup required.
Description
This workflow brings the ACE-Step music generation model into ComfyUI, allowing you to generate complete songs from text — no external tools required. With just a genre-based prompt and structured lyrics, you can produce unique, high-quality music inside your AI workflows.
🔧 What It Does
- Accepts ACE-Step–style inputs:
- 🎛 Prompt: Genre, instruments, mood, BPM, key, vocal style (e.g.
funk, soul, female vocals, 100 bpm, A minor
) - ✍️ Lyrics: Structured verses, choruses, bridges in plain text
- 🎛 Prompt: Genre, instruments, mood, BPM, key, vocal style (e.g.
- Outputs a fully generated song with vocals and instrumentation
🧩 Use Cases
- Rapid prototyping of AI-generated songs
- Creating music for video, animation, or storytelling projects
- Educational demos and interactive creative tools
- Embedding in multimedia workflows within ComfyUI
🚀 How to Use
- Fill in your prompt (e.g.
psychedelic rock, ambient synth, male vocals, 90 bpm, D minor
) - Paste your lyrics in the provided text area
- Run the workflow to generate your song
💡 Tip
Pair this workflow with Text-to-Video or Image-to-Video nodes in ComfyUI to create full AI-powered music videos.
Models
File | Destination | Source |
---|---|---|
ace_step_v1_3.5b.safetensors | /ComfyUI/models/checkpoints | Download |
Nodes
ModelSamplingSD3VAEDecodeAudioCheckpointLoaderSimpleConditioningZeroOutKSamplerEmptyAceStepLatentAudioTextEncodeAceStepAudioSaveAudio