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 vae/config.json from Avdpro/ACE-Step-1.5-Turbo-MLX: direct link, hf CLI and curl.
- Browser
- Download file 425 Bytes
-
https://huggingface.co/Avdpro/ACE-Step-1.5-Turbo-MLX/resolve/main/vae/config.json
- Command line
-
hf download hf://Avdpro/ACE-Step-1.5-Turbo-MLX/vae/config.json
-
curl -L -o config.json https://huggingface.co/Avdpro/ACE-Step-1.5-Turbo-MLX/resolve/main/vae/config.json
425 Bytes
| { | |
| "_class_name": "AutoencoderOobleck", | |
| "_diffusers_version": "0.34.0", | |
| "_name_or_path": "/root/data/repo/gongjunmin/ACE-Step-1.5/checkpoints/vae/", | |
| "audio_channels": 2, | |
| "channel_multiples": [ | |
| 1, | |
| 2, | |
| 4, | |
| 8, | |
| 16 | |
| ], | |
| "decoder_channels": 128, | |
| "decoder_input_channels": 64, | |
| "downsampling_ratios": [ | |
| 2, | |
| 4, | |
| 4, | |
| 6, | |
| 10 | |
| ], | |
| "encoder_hidden_size": 128, | |
| "sampling_rate": 48000 | |
| } | |