Instructions to use LumeryApp/Ace-Step-v1.5-ScragVAE-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use LumeryApp/Ace-Step-v1.5-ScragVAE-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Ace-Step-v1.5-ScragVAE-mlx LumeryApp/Ace-Step-v1.5-ScragVAE-mlx
- ACE-Step
How to use LumeryApp/Ace-Step-v1.5-ScragVAE-mlx with ACE-Step:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
ScragVAE (Ace-Step 1.5) โ MLX (LumeryApp)
MLX-format conversion of ScragVAE โ a community-finetuned drop-in replacement for the
AceStep 1.5 audio VAE. It shares the AutoencoderOobleck architecture and config schema,
so it substitutes directly for the bundled decoder. Lumery uses it as the default
production decode chain for AceStep music.
- Format: MLX, BF16 (
model.safetensors+config.json). - Upstream:
scragnog/Ace-Step-1.5-ScragVAE, ยฉ @scragnog, licensed MIT. - Modifications: conversion of the original weights to MLX safetensors. No retraining.
Provenance & attribution
Unofficial community conversion โ not affiliated with or endorsed by @scragnog. See
NOTICE for the MIT attribution.
License
MIT, inherited from upstream. See NOTICE.
Model tree for LumeryApp/Ace-Step-v1.5-ScragVAE-mlx
Quantized
scragnog/Ace-Step-1.5-ScragVAE