acestep v15 xl sft

ProviderACE-Step
Categorytext-to-audio
Licensemit
Downloads4.5K
Stars10

Overview

acestep v15 xl sft is a specialized text-to-audio model designed for high-fidelity sound synthesis. Unlike general-purpose TTS, this SFT (Supervised Fine-Tuned) version is optimized for precise acoustic control and natural prosody, making it suitable for developers building immersive voice agents, automated narration tools, or dynamic game audio. It balances computational efficiency with output quality, allowing for relatively low-latency integration into production pipelines. For developers moving from standard models, v15 xl offers improved nuance in emotional inflection and better stability across longer text sequences, reducing the need for manual post-processing or extensive prompt engineering to achieve realistic results.

Highlights

  • High-fidelity text-to-audio synthesis with natural prosody
  • SFT optimization for improved emotional inflection
  • Low-latency performance for real-time application integration
  • Permissive MIT license for flexible commercial deployment
  • Enhanced stability across long-form audio generation

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("ACE-Step/acestep-v15-xl-sft")
tokenizer = AutoTokenizer.from_pretrained("ACE-Step/acestep-v15-xl-sft")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download ACE-Step/acestep-v15-xl-sft

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download ACE-Step/acestep-v15-xl-sft config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('ACE-Step/acestep-v15-xl-sft')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/ACE-Step/acestep-v15-xl-sft

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/ACE-Step/acestep-v15-xl-sft

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('ACE-Step/acestep-v15-xl-sft')
tokenizer = AutoTokenizer.from_pretrained('ACE-Step/acestep-v15-xl-sft')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model ACE-Step/acestep-v15-xl-sft

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model ACE-Step/acestep-v15-xl-sft README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('ACE-Step/acestep-v15-xl-sft')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/ACE-Step/acestep-v15-xl-sft.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/ACE-Step/acestep-v15-xl-sft.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'ACE-Step/acestep-v15-xl-sft')

Full Documentation

来源: HuggingFace

---
library_name: transformers
license: mit
pipeline_tag: text-to-audio
tags:

  • feature-extraction

  • audio

  • music

  • text2music

  • custom_code

---

<h1 align="center">ACE-Step 1.5 XL — SFT (4B DiT)</h1>
<p align="center">
<a href="https://ace-step.github.io/ace-step-v1.5.github.io/">Project</a> |
<a href="https://huggingface.co/collections/ACE-Step/ace-step-15">Hugging Face</a> |
<a href="https://modelscope.cn/collections/ACE-Step/Ace-Step-15-xl">ModelScope</a> |
<a href="https://huggingface.co/spaces/ACE-Step/Ace-Step-v1.5">Space Demo</a> |
<a href="https://discord.gg/PeWDxrkdj7">Discord</a> |
<a href="https://arxiv.org/abs/2602.00744">Tech Report</a>
</p>

Model Details

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.

XL 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 | 50 (with CFG) |

GPU Requirements

| 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.

Key Features

  • 💰 Commercial-Ready: Trained on legally compliant datasets. Generated music can be used for commercial purposes.
  • 📚 Safe Training Data: Licensed music, royalty-free/public domain, and synthetic (MIDI-to-Audio) data.
  • 🎯 CFG Support: Fine-tune prompt adherence with guidance scale control.
  • 🔮 Highest Quality: SFT + 4B parameters = the highest quality variant.

Quick Start

bash
# 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

Model Zoo

XL (4B) DiT Models

| 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 Models (all compatible with XL)

| 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 |

Acknowledgements

This project is co-led by ACE Studio and StepFun.

Citation

BibTeX
@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}
}
View official source
Join our Telegram