by ACE-Step
Open source · 3k downloads · 64 likes
ACE-Step 1.5 XL SFT is an AI model specialized in high-quality music generation, featuring 4 billion parameters. It enables the creation of musical pieces from text descriptions while offering precise control over adherence to prompts through classifier-free guidance (CFG). Designed for commercial use, it relies on legally compliant training data, including licensed music, royalty-free works, and audio synthesized from MIDI scores. This model stands out for its ability to produce professional results, suitable for content creators, artists, and music application developers alike. Its optimized architecture and advanced features make it a versatile solution for automated or assisted composition.
Project | Hugging Face | ModelScope | Space Demo | Discord | Tech Report
This is the XL (4B) SFT variant of ACE-Step 1.5 — a supervised fine-tuned model with ~4B parameters. SFT provides higher audio quality with CFG (Classifier-Free Guidance) support for fine-grained prompt adherence control.
| 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 | 50 (with CFG) |
| VRAM | Support |
|---|---|
| ≥12 GB | With CPU offload + INT8 quantization |
| ≥16 GB | With CPU offload |
| ≥20 GB | Without offload |
| ≥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-sft --local-dir ./checkpoints/acestep-v15-xl-sft
# Run with Gradio UI
python acestep --config-path acestep-v15-xl-sft
| 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 | This repo | Link |
acestep-v15-xl-turbo | ❌ | 8 | Very High | Medium | Standard | Link | 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}
}