
ACE Music
16 posts

ACE Music
@acemusicAI
The world's first open-sourced musicAI platform
เข้าร่วม Ocak 2026
31 กำลังติดตาม2.2K ผู้ติดตาม
ทวีตที่ปักหมุด

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-S…
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.
English

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-S…
Hugging Face: huggingface.co/ACE-Step/Ace-S… (3 variants: xl-base, xl-sft, xl-turbo)
XL demos: #XLDemos" target="_blank" rel="nofollow noopener">ace-step.github.io/ace-step-v1.5.…
English

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-Step…
(We also fixed a bug from the first release.)
Here’s a quick tutorial 👇
English

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-Step…
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…
API docs: github.com/ace-step/ACE-S…
English

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-S…
English

@acemusicAI Haha whoa 👀 My generation featured on the first track. Nice.
Thanks ACE team for this phenomenal model. Wishing you all great success!
English

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-S…
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.
English

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-…
ComfyUI@ComfyUI
ACE-Step 1.5 just dropped in ComfyUI. Full songs in under 10 seconds. Less than 4GB VRAM. Open-source music generation just got serious.
English

We built a web platform based on ACE-Step 1.5: acemusic.ai.
It’s completely free! Come play with it :)
English

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-…
English

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.
ACE Studio@ACEStudio_en
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-S… Git repo: github.com/ace-step/ACE-S…
English

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
English