AI/EXPLORER
ToolsCategoriesSitesLLMsCompareAI QuizAlternativesPremium
—AI Tools
—Sites & Blogs
—LLMs & Models
—Categories
AI Explorer

Find and compare the best artificial intelligence tools for your projects.

Made within France

Explore

  • ›All tools
  • ›Sites & Blogs
  • ›LLMs & Models
  • ›Compare
  • ›Chatbots
  • ›AI Images
  • ›Code & Dev

Company

  • ›Premium
  • ›About
  • ›Contact
  • ›Blog

Legal

  • ›Legal notice
  • ›Privacy
  • ›Terms

© 2026 AI Explorer·All rights reserved.

HomeLLMsacestep v15 xl base

acestep v15 xl base

by ACE-Step

Open source · 1k downloads · 66 likes

2.3
(66 reviews)AudioAPI & Local
About

ACE-Step 1.5 XL Base is an artificial intelligence model specialized in audio generation and manipulation, designed to produce high-quality music from text or other inputs. With its 4 billion parameters, it delivers superior sound quality compared to lighter versions while remaining accessible for a variety of uses. The model supports multiple tasks, such as creating music from text descriptions, remixing existing tracks, modifying audio tracks, and extracting specific sound elements. Its training is based on legally compliant data, ensuring secure commercial use of the generated creations. What sets it apart is its balance of performance, versatility, and copyright compliance, making it a tool suitable for both professionals and independent creators.

Documentation

ACE-Step 1.5 XL — Base (4B DiT)

Project | Hugging Face | ModelScope | Space Demo | Discord | Tech Report

Model Details

This is the XL (4B) Base variant of ACE-Step 1.5 — a larger DiT decoder with ~4B parameters for higher audio quality. It is the foundation model supporting all tasks: text-to-music, cover, repaint, extract, lego, and complete.

XL Architecture

ParameterValue
DiT Decoder hidden_size2560
DiT Decoder layers32
DiT Decoder attention heads32
Encoder hidden_size2048
Encoder layers8
Total params~4B
Weights size (bf16)~18.8 GB
Inference steps50 (with CFG)

GPU Requirements

VRAMSupport
≥12 GBWith CPU offload + INT8 quantization
≥16 GBWith CPU offload
≥20 GBWithout offload
≥24 GBFull 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.
  • 🎯 Full Task Support: Text2Music, Cover, Repaint, Extract, Lego, Complete.
  • 🔮 Higher Quality: 4B parameters provide richer audio quality compared to the 2B variants.

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-base --local-dir ./checkpoints/acestep-v15-xl-base

# Run with Gradio UI
python acestep --config-path acestep-v15-xl-base

Model Zoo

XL (4B) DiT Models

DiT ModelCFGStepsQualityDiversityTasksHugging FaceModelScope
acestep-v15-xl-base✅50HighHighAll (extract, lego, complete)This repoLink
acestep-v15-xl-sft✅50Very HighMediumStandardLinkLink
acestep-v15-xl-turbo❌8Very HighMediumStandardLinkLink

2B DiT Models

DiT ModelCFGStepsHugging FaceModelScope
acestep-v15-turbo (default)❌8LinkLink
acestep-v15-sft✅50LinkLink
acestep-v15-base✅50LinkLink

LM Models (all compatible with XL)

LM ModelParamsAudio UnderstandingCompositionHugging FaceModelScope
acestep-5Hz-lm-0.6B0.6BMediumMediumLinkLink
acestep-5Hz-lm-1.7B1.7BMediumMediumIncluded in mainIncluded in main
acestep-5Hz-lm-4B4BStrongStrongLinkLink

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}
}
Capabilities & Tags
transformerssafetensorsacestepfeature-extractionaudiomusictext2musiccustom_codetext-to-audio
Links & Resources
Specifications
CategoryAudio
AccessAPI & Local
LicenseOpen Source
PricingOpen Source
Rating
2.3

Try acestep v15 xl base

Access the model directly