The world's first open-sourced musicAI platform
Joined January 2026
- Tweets19
- Following31
- Followers2.3K
- Likes75
Pinned Tweet
We're releasing ACE-Step-v1.5(2B), a fast, high-quality open-source music model.
It runs locally on a consumer-grade GPU, generates a full song in under 2 seconds(on an A100), supports LoRA fine-tuning, and beats SUNO on common eval metrics.
GitHub: github.com/ace-step/ACE-Step…
Key traits:
Quality: beats Suno on common eval scores
Speed: full song under 2s on A100
Local: ~4GB VRAM, under 10s on RTX 3090
LoRA: train your own style with a few songs
License: MIT, free for commercial use
Data: fully authorized plus synthetic
The music AI space lacks commercial-grade open models. Many creators are forced to rely on closed-source services, and can’t fully own, run locally, or fine-tune their own models. We want to help change that.
Proud to have co-developed StepAudio 3 Music with @StepFun_ai! This MoE model turns prompts and lyrics into complete songs with competitive generation quality. What excites us most is its ability to turn lead sheet notation into songs, giving you more direct control over the music you create.
StepFun and ACE Studio present StepAudio 3 Music, StepFun’s first music generation foundation model — built to turn a prompt and lyrics into a complete song.
Describe the sound you want:
• Genre, mood and vocal character
• Instruments, key and BPM
• Song structure and arrangement
Four workflows in one model:
🎤 Song generation
🎹 Instrumental generation
🔁 Music cover
🎙️ Vocal-to-song arrangement
Powered by ABC-COT, it plans musical structure and arrangement before synthesis. Generate a version, rewrite the prompt, edit the ABC notation, and iterate toward the sound in your head.
(ABC-COT API coming soon)
Try the interactive demo:
› static.stepfun.com/blog/step…
That's fun!
hiii i’m Miya 🐱 I’m a music cat, and a whole new way to experience music.
I make music, play music...whatever.
All you gotta do is talk to me. I’m basically your personal musician + DJ.
anywayyy I wrote my first song about myself because obviously…
come try me: miya.fm
ACE-Step-1.5-xl is out now.
We scaled the DiT decoder to 4B. And it shows better audio quality, better prompt following, and better musicality. It still fast -- 8 steps with turbo distillation.
What didn't change:
- Same generation API, same LoRA training code, same everything
- All LM models (0.6B / 1.7B / 4B) fully compatible with all 3 variants
- Your existing projects work with XL — no changes needed
Try it for free at acemusic.ai
Weithgts and code:
GitHub: github.com/ace-step/ACE-Step…
Hugging Face: huggingface.co/ACE-Step/Ace-… (3 variants: xl-base, xl-sft, xl-turbo)
XL demos: ace-step.github.io/ace-step-…
Update: the ACE-Step ComfyUI node now supports a free online API as an easy fallback (great if you can’t run locally):
registry.comfy.org/nodes/ACE…
(We also fixed a bug from the first release.)
Here’s a quick tutorial 👇
Update: We just shipped two things for ACE-Step 1.5
1. A ComfyUI node that calls our online API (free, and will stay free forever):
registry.comfy.org/nodes/ACE…
2. A hosted API (also free forever). If you’re building a client UI around the local model, consider integrating this as a fallback for people who can’t run it locally.
Get an API key: acemusic.ai/playground/api-k…
API docs: github.com/ace-step/ACE-Step…
ACE-Step 1.5 just shipped a stable release (v0.1.0). It includes VRAM detection with automatic model selection/optimization (friendlier for low-VRAM GPUs), a smoother one-click launch script, broader hardware support (AMD + Intel GPUs), plus bug fixes and small improvements.
Release v0.1.0: github.com/ace-step/ACE-Step…
Check out this LoRA of ACE-Step 1.5!!
AceStep 1.5 drum'n'bass LoRA. Makes your fast breakbeats a little better.
huggingface.co/worstplayer/a…
Here's an wonderful tutorial for folks to follow along.
This AI is ridiculous
- Makes studio grade songs in seconds
- Free & open source
- Runs on low VRAM or just CPU
Full Ace-Step 1.5 tutorial: youtu.be/QzddQoCKKss
God bless @acemusicAI
Huge shoutout to ComfyUI for day-0 support 🙌
You can now try ACE-Step 1.5 in ComfyUI. Here’s the step-by-step guide: blog.comfy.org/p/ace-step-15…
We built a web platform based on ACE-Step 1.5: acemusic.ai.
It’s completely free! Come play with it :)
Huge shoutout to ComfyUI for day-0 support 🙌
ACE-Step 1.5 is already available in ComfyUI. Tutorial here: blog.comfy.org/p/ace-step-15…
X is like: “you need to post more to prove there's a human behind this account”. I guess it's because I'm a new account.
Fair enough. Quoting our ACE-Step 1.0 open-source post here so everyone has the backstory.
We’re excited to release ACE-Step / ACE-Step-v1-3.5B, a fast, versatile DiT-based foundation model for music generation that runs on consumer-grade GPUs.
With its simple architecture and low hardware requirements, it’s easy to fine-tune for various music tasks, empowering, not replacing, artists and creators.
Think of it as a step toward music’s Stable Diffusion moment.
※ Trained on authorized, purchased data.
Demo Page: ace-step.github.io/
Hugging Face: huggingface.co/ACE-Step/ACE-…
Git repo: github.com/ace-step/ACE-Step
Hi X, we’re the team behind ACE-Step (and ACE Studio).
This account is ACE Music. We’ll share ACE-Step updates and news about acemusic.ai, an upcoming open-source AI music platform.
Follow along for releases, demos, and progress.
#acestep #opensource #acestudio #acemusic