jeankassio

jeankassio / ComfyUI-AceStep_SFT

Public

An all-in-one node for ComfyUI that implements AceStep 1.5 SFT (Supervised Fine-Tuning), a high-quality music generation model. This node replicates the full functionality of the official Gradio pipeline, offering fine control over audio synthesis parameters.

ace-step ace-step15 comfyui comfyui-custom-node comfyui-nodes
19
5
100% credibility
Found Mar 22, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Custom nodes for the ComfyUI interface that allow users to generate music from text prompts, analyze audio for styles and beats, and apply style tweaks using AceStep 1.5 SFT models.

How It Works

1
🔍 Discover Music Maker Add-on

You hear about a cool tool that turns words and ideas into songs right inside your favorite AI creativity app.

2
📥 Add It to Your App

Simply copy the add-on files into your app's special folder and restart – new music blocks appear like magic.

3
🎵 Grab Sound Brains

Download a few big sound recipe files from trusted spots and drop them into your app's music folder to power it up.

4
🧩 Build Your Song Block

Drag colorful blocks together: pick moods, add lyrics, set length, and connect any tune you want to remix.

5
Choose Your Adventure
🎤
Create New Song

Type what you hear in your head – upbeat dance or chill piano – and let it compose.

🔬
Analyze a Tune

Feed in a song to pull out its style, beat, and mood for remixing magic.

6
▶️ Hit Generate

Press the button and watch as your description turns into beautiful, original music playing back instantly.

🎉 Your Song Comes Alive

Dance to your custom track, share it with friends, or remix endlessly – pure creative joy!

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ComfyUI-AceStep_SFT?

This Python-based ComfyUI custom node pack delivers an all-in-one ComfyUI node for AceStep 1.5 SFT, a supervised fine-tuning model for high-quality music generation from text prompts, lyrics, or source audio. It replicates the official Gradio pipeline inside ComfyUI workflows, handling latent creation, diffusion sampling, VAE decoding, and audio editing with fine control over parameters like BPM, keyscale, and duration. Users get text-to-music, style transfer via reference audio, and batch generation without leaving their node graphs.

Why is it gaining traction?

As a comfyui all in one node, it stands out by matching AceStep 1.5's exact quality through advanced guidance modes like APG for cleaner, stable audio, plus an AI music analyzer pulling tags, BPM, and key from clips using nine models with auto-downloads. Developers hook into chainable LoRA stacking with auto-conversion for PEFT/DoRA files, multilingual lyric support, and auto-duration estimation from lyrics—features that slash setup time versus manual pipelines. Early adopters praise the precise parameter tweaks for editing and timbre transfer in audio workflows.

Who should use this?

ComfyUI powerusers experimenting with AI music synthesis, like sound designers remixing tracks or prototyping generative audio tools. Music producers needing fine control over diffusion params for custom beats, or workflow builders chaining analysis-to-generation pipelines for style-matched outputs. Skip if you're not in ComfyUI or prefer Gradio simplicity.

Verdict

Solid pick for ComfyUI audio enthusiasts despite 19 stars and 1.0% credibility score signaling early maturity—docs are thorough with examples, but test in small batches first. Worth cloning if AceStep 1.5 all-in-one generation fits your stack.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.