Instructions to use Avdpro/ACE-Step-1.5-Turbo-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Avdpro/ACE-Step-1.5-Turbo-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Avdpro/ACE-Step-1.5-Turbo-MLX --local-dir ACE-Step-1.5-Turbo-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
|
Download README.md from Avdpro/ACE-Step-1.5-Turbo-MLX: direct link, hf CLI and curl.
- Browser
- Download file 913 Bytes
-
https://huggingface.co/Avdpro/ACE-Step-1.5-Turbo-MLX/resolve/main/README.md
- Command line
-
hf download hf://Avdpro/ACE-Step-1.5-Turbo-MLX/README.md
-
curl -L -o README.md https://huggingface.co/Avdpro/ACE-Step-1.5-Turbo-MLX/resolve/main/README.md
913 Bytes
| license: mit | |
| library_name: mlx | |
| pipeline_tag: text-to-audio | |
| base_model: ACE-Step/Ace-Step1.5 | |
| # ACE-Step 1.5 Turbo MLX for AI2Apps | |
| Converted from ACE-Step/Ace-Step1.5 revision 19671f406d603126926c1b7e2adc169acbcade22. Includes Turbo DiT, VAE, Qwen3-Embedding-0.6B and 1.7B planning LM. No quantization was added. | |
| Modified tensors: convolution layouts transposed for MLX, LM keys prefixed with model., silence latent converted from a weights-only PyTorch tensor to NumPy. Original component precision is preserved. Conversion script is experiments/music_mlx/convert_ace.py in the AI2Apps Local project. Runtime uses the pinned mlx-audio commit in provenance.json. | |
| ACE-Step is MIT licensed. Qwen3 components are subject to Apache-2.0. See the included component license notices. Package model code and checkpoint distributions are published separately; no runtime downloads or PyTorch fallback are needed. | |