ace-step/ACE-Step-1.5

★14,147PythonMIT⑂ 1,862Issue 98Updated Oct 11, 2026

View on GitHub ↗Website ↗

The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

Open-source text-to-music generation now runs anywhere, including Macs — ACE-Step 1.5 adds an XL series with a 4B-parameter DiT decoder for higher audio quality, available in base, sft, and turbo variants, plus full compatibility with existing LM models. It runs locally on Mac, AMD, Intel, and CUDA hardware (≥12GB VRAM with offload), making it accessible to musicians and developers without cloud dependencies.

Metrics

Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.

Star growth and Trending appearances (last 30 days)

Created Sep 4, 2025 · First on trending Oct 15, 2026

Other notable repositories in the same category (LLMs & ML)

• pst2154/nemotron-deciffusionStructured decisions from an 8B diffusion model in a single GPU pass
• todesking/slopsamplerCataloging the telltale phrases of AI-generated Japanese text
• datalab-to/indraA 1M-parameter OCR model that beats PaddleOCR and Tesseract on CPU
• fudan-generative-vision/RemorySoft memory that survives context compaction for LLM agents
• google-pytorch/torch_tpuA PyTorch Backend That Runs Models Directly on Google TPUs

See all LLMs & ML repositories →