Instructions to use marcorez8/acestep-v15-xl-base-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use marcorez8/acestep-v15-xl-base-bf16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="marcorez8/acestep-v15-xl-base-bf16", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("marcorez8/acestep-v15-xl-base-bf16", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
ACE-Step 1.5 XL β Base (4B DiT) BF16
Project | Hugging Face | ModelScope | Space Demo | Discord | Tech Report
Model Details
This is the BF16 version of ACE-Step/acestep-v15-xl-base β the XL (4B) Base variant of ACE-Step 1.5. This BF16 conversion reduces memory usage while maintaining near-identical quality to the original model. It is a full-quality base model that generates high-quality audio in 50 steps with CFG, offering high diversity and support for all tasks (extract, lego, complete).
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) | ~7.5 GB |
| Inference steps | 50 (with CFG) |
GPU Requirements
| VRAM | Support |
|---|---|
| β₯8 GB | With CPU offload + INT8 quantization |
| β₯12 GB | With CPU offload |
| β₯16 GB | Without offload (recommended) |
| β₯20 GB | Full quality (XL + 4B LM) |
All LM models (0.6B / 1.7B / 4B) are fully compatible with XL.
Key Features
- π° Commercial-Ready: Trained on legally compliant datasets. Generated music can be used for commercial purposes.
- π Safe Training Data: Licensed music, royalty-free/public domain, and synthetic (MIDI-to-Audio) data.
- π― High Diversity: Base model offers the highest diversity among XL variants.
- π§ All Tasks: Supports extract, lego, and complete tasks.
- π§ BF16 Precision: Converted to BF16 for reduced VRAM usage and faster inference, with negligible quality loss.
Quick Start
# 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 marcorez8/acestep-v15-xl-base-bf16 --local-dir ./checkpoints/acestep-v15-xl-base-bf16
# Run with Gradio UI
python acestep --config-path acestep-v15-xl-base-bf16
Model Zoo
XL (4B) DiT Models
| DiT Model | CFG | Steps | Quality | Diversity | Tasks | Hugging Face | ModelScope |
|---|---|---|---|---|---|---|---|
acestep-v15-xl-base |
β | 50 | High | High | All (extract, lego, complete) | Link | Link |
acestep-v15-xl-base-bf16 |
β | 50 | High | High | All (extract, lego, complete) | This repo | β |
acestep-v15-xl-sft |
β | 50 | Very High | Medium | Standard | Link | Link |
acestep-v15-xl-turbo |
β | 8 | Very High | Medium | Standard | Link | Link |
acestep-v15-xl-turbo-bf16 |
β | 8 | Very High | Medium | Standard | Link | β |
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. The BF16 conversion was done by marcorez8 to make the model more accessible to the community.
Citation
@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}
}
- Downloads last month
- 29
Model tree for marcorez8/acestep-v15-xl-base-bf16
Base model
ACE-Step/acestep-v15-xl-base