Views
No views yet
| 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) |
1# Install ACE-Step
2git clone https://github.com/ace-step/ACE-Step-1.5.git
3cd ACE-Step-1.5
4pip install -e .
5
6# Download this model
7huggingface-cli download ACE-Step/acestep-v15-xl-base --local-dir ./checkpoints/acestep-v15-xl-base
8
9# Run with Gradio UI
10python acestep --config-path acestep-v15-xl-base| DiT Model | CFG | Steps | Quality | Diversity | Tasks | Hugging Face | ModelScope |
|---|---|---|---|---|---|---|---|
acestep-v15-xl-base | ✅ | 50 | High | High | All (extract, lego, complete) | This repo | Link |
acestep-v15-xl-sft | ✅ | 50 | Very High | Medium | Standard | Link | Link |
acestep-v15-xl-turbo | ❌ | 8 | Very High | Medium | Standard | Link | Link |
| DiT Model | CFG | Steps | Hugging Face | ModelScope |
|---|---|---|---|---|
acestep-v15-turbo (default) | ❌ | 8 | Link | Link |
acestep-v15-sft | ✅ | 50 | Link | Link |
acestep-v15-base | ✅ | 50 | 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 |
1@misc{gong2026acestep,
2 title={ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation},
3 author={Junmin Gong, Yulin Song, Wenxiao Zhao, Sen Wang, Shengyuan Xu, Jing Guo},
4 howpublished={\url{https://github.com/ace-step/ACE-Step-1.5}},
5 year={2026},
6 note={GitHub repository}
7}