ACE-Step
ACE-StepACE-Step is an open music generation model family from the ACE Studio and StepFun collaboration that writes full songs, vocals included, from lyrics and a style prompt. ACE-Step 1.5 pairs a diffusion transformer, up to 4B parameters in its XL variants, with a language model that plans the song, and supports cover generation, repainting, completion and LoRA training.
Openness
3 high confidence- weights
- open(the ACE-Step 1.5 base, SFT, turbo and XL checkpoints, the planning language models and ACE-Step v1 download from Hugging Face without a gate)
- data
- described(the 1.5 card describes licensed, royalty-free and synthetic training music
- code
- partial(ACE-Step 1.5 publishes LoRA training only
- license
- MIT(ACE-Step 1.5 code and weights)+Apache-2.0(ACE-Step v1 code and weights)
ACE-Step's weights and code are released under MIT and Apache 2.0, and the generated music may be used commercially. The training data is described but not released, and the current release publishes only LoRA training rather than its full pipeline.
- https://huggingface.co/ACE-Step/Ace-Step1.5/raw/main/README.md recorded 2026-09-26
Card: trained on "Licensed Data", "Royalty-Free / No-Copyright Data" and "Synthetic Data"; "You can strictly use the generated music for commercial purposes."
- https://huggingface.co/api/models?author=ACE-Step&sort=downloads&direction=-1&limit=100 recorded 2026-09-26
Hugging Face listing of the ACE-Step organization: every checkpoint public and ungated, licenses mit and apache-2.0.
- https://huggingface.co/api/models/ACE-Step/Ace-Step1.5?expand[]=downloads&expand[]=likes&expand[]=cardData&expand[]=gated&expand[]=lastModified&expand[]=createdAt recorded 2026-09-26
Hugging Face API record for Ace-Step1.5: gated false, license mit.
- https://ungh.cc/repos/ace-step/ACE-Step-1.5/files/main/LICENSE recorded 2026-09-26
LICENSE body: "MIT License / Copyright (c) 2026 ACEStep".
- https://ungh.cc/repos/ace-step/ACE-Step-1.5/files/main/README.md recorded 2026-09-26
README Train section: a "LoRA Training Tutorial" and "Advanced Training with Side-Step".
- https://ungh.cc/repos/ace-step/ACE-Step/files/main/LICENSE recorded 2026-09-26
v1 LICENSE body: "Apache License / Version 2.0, January 2004".
Adoption
3 high confidenceAdoption is measured as Hugging Face downloads across the ACE-Step 1.5 and v1 checkpoints, led by the main 1.5 repository. The LoRA adapters are left out.
- https://huggingface.co/api/models?author=ACE-Step&sort=downloads&direction=-1&limit=100 recorded 2026-09-26
Listing sorted by downloads: Ace-Step1.5 59314, acestep-5Hz-lm-0.6B 9839, acestep-5Hz-lm-4B 9738 in the trailing 30 days.
Capability
1 medium confidenceACE-Step generates complete songs with vocals, but it has no placement on the public music arenas, where MusicGen at least appears. That leaves its quality against the closed services unmeasured.
- https://artificialanalysis.ai/music/leaderboard/instrumental recorded 2026-09-26
The "AA-Music-Instrumental v1.1" leaderboard lists 19 models and no ACE-Step entry.
- https://artificialanalysis.ai/music/leaderboard/vocals recorded 2026-09-26
The "AA-Music-Vocal v1.1" leaderboard lists 13 models and no ACE-Step entry.
- https://huggingface.co/ACE-Step/Ace-Step1.5/raw/main/README.md recorded 2026-09-26
Card describing song generation from lyrics and tags, with editing and LoRA training.
Verified 2026-09-26