ace-step/ACE-Step-1.5

Health v2 · maintenance only

Adoption not part of the score

12421 stars · 1577 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

ACE-Step 1.5 is an open-source music generation foundation model combining a language model planner with a Diffusion Transformer to create full songs from text prompts and lyrics. It runs locally on consumer hardware with under 4GB VRAM and supports LoRA personalization from a few example songs.

Use cases

• generate music from text descriptions locally
• create full songs with lyrics from a prompt
• train a LoRA to mimic my own music style
• run a text-to-music model on a Mac or AMD GPU
• generate long background music tracks up to 10 minutes
• produce commercial-quality songs without paying for a music API

When to choose

• you need local, offline music generation on consumer GPUs or Apple Silicon
• you want to fine-tune a music model on your own songs via LoRA
• you need fast generation (seconds per song) with commercial-grade quality
• you want an MIT-licensed alternative to paid music generation services

When to avoid

• you need real-time live music performance or MIDI editing rather than generated audio
• you lack a GPU and cannot tolerate slow CPU inference
• you need a simple sample-loop library rather than full song synthesis

Facets

library · maturity active

machine-learning deep-learning llm-inference audio-processing tts artificial-intelligence machine-learning media deep-learning python cross-platform windows text-to-music music-generation diffusion-transformer lora-fine-tuning local-inference generative-audio audio gpu macos linux docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ace-step/ACE-Step-1.5")