by ACE-Step
Open source · 4k downloads · 116 likes
ACE-Step 1.5 XL Turbo is an AI model specialized in high-quality audio generation, capable of producing realistic music or sounds in just 8 inference steps, making it exceptionally fast. With its 4-billion-parameter architecture, it delivers superior sound quality compared to lighter models while maintaining optimal efficiency. Designed for commercial use, it relies on legally compliant training data, including licensed music, royalty-free works, and syntheses generated from MIDI scores. Perfect for content creators, music app developers, or studios looking to automate audio production without compromising on quality or legality, it stands out for its unique balance of speed, performance, and copyright compliance—making it suitable for both professional projects and creative experimentation.
Project | Hugging Face | ModelScope | Space Demo | Discord | Tech Report
This is the XL (4B) Turbo variant of ACE-Step 1.5 — a distillation-accelerated model that generates high-quality audio in just 8 steps. Combines the speed of turbo with the quality of the 4B architecture.
| Parameter | Value |
|---|---|
| DiT Decoder hidden_size | 2560 |
| DiT Decoder layers | 32 |
| DiT Decoder attention heads | 32 |
| Encoder hidden_size | 2048 |
| Encoder layers | 8 |
| Total params | ~4B |
| Weights size (bf16) | ~18.8 GB |
| Inference steps | 8 (no CFG, distilled) |
| VRAM | Support |
|---|---|
| ≥12 GB | With CPU offload + INT8 quantization |
| ≥16 GB | With CPU offload |
| ≥20 GB | Without offload (recommended) |
| ≥24 GB | Full quality (XL + 4B LM) |
All LM models (0.6B / 1.7B / 4B) are fully compatible with XL.
# Install ACE-Step
git clone https://github.com/ace-step/ACE-Step-1.5.git
cd ACE-Step-1.5
pip install -e .
# Download this model
huggingface-cli download ACE-Step/acestep-v15-xl-turbo --local-dir ./checkpoints/acestep-v15-xl-turbo
# Run with Gradio UI
python acestep --config-path acestep-v15-xl-turbo
| DiT Model | CFG | Steps | Quality | Diversity | Tasks | Hugging Face | ModelScope |
|---|---|---|---|---|---|---|---|
acestep-v15-xl-base | ✅ | 50 | High | High | All (extract, lego, complete) | Link | Link |
acestep-v15-xl-sft | ✅ | 50 | Very High | Medium | Standard | Link | Link |
acestep-v15-xl-turbo | ❌ | 8 | Very High | Medium | Standard | This repo | Link |
| LM Model | Params | Audio Understanding | Composition | Hugging Face | ModelScope |
|---|---|---|---|---|---|
acestep-5Hz-lm-0.6B | 0.6B | Medium | Medium | Link | Link |
acestep-5Hz-lm-1.7B | 1.7B | Medium | Medium | Included in main | Included in main |
acestep-5Hz-lm-4B | 4B | Strong | Strong | Link | Link |
This project is co-led by ACE Studio and StepFun.
@misc{gong2026acestep,
title={ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation},
author={Junmin Gong, Yulin Song, Wenxiao Zhao, Sen Wang, Shengyuan Xu, Jing Guo},
howpublished={\url{https://github.com/ace-step/ACE-Step-1.5}},
year={2026},
note={GitHub repository}
}