ACE-Step 1.5 (incl. 1.5 XL)
Checkpoints: acestep-v15-base / -sft / -turbo (plus turbo-shift variants) and, from 2026-04-02, XL (4B DiT) xl-base / xl-sft / xl-turbo; diffusers versions added Apr-Jun 2026. Release date 2026-01-28 is from secondary sources (HF repos created 2026-01-23, arXiv 2602.00744 submitted 2026-01-31). Authors claim quality beyond most commercial models (SongEval above Suno v5 per secondary coverage; not independently verified). Supports Mac, AMD, Intel and CUDA.
- Input
- text, audio
- Output
- audio
- License
- mit
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Hugging Face | — | huggingface.co/ACE-Step/Ace-Step1.5 | — |
| Hugging Face (XL 4B DiT) | — | huggingface.co/ACE-Step/acestep-v15-xl-sft | — |
| GitHub | — | github.com/ace-step/ACE-Step-1.5 | — |
| Web app | — | acemusic.ai | — |
Notable capabilities (3)
- Full songs in seconds on consumer hardware: 10 s to 10 min of music; under 2 s per song on an A100 and under 10 s on an RTX 3090; standard models run in <4 GB VRAM with offload (XL: >=12 GB, 20 GB recommended). source
- LM planner + DiT synthesizer: A language model (0.6B/1.7B/4B '5Hz LM') turns prompts into a song blueprint that a Diffusion Transformer renders; aligned with 'intrinsic' RL without external reward models. source
- Editing and personalization toolkit: Cover generation, repaint/editing, vocal-to-BGM, track separation, multi-track generation, BPM/key extraction and LoRA fine-tuning from ~8 songs (about 1 h on a 12 GB RTX 3090); lyrics in 50+ languages. source
The go-to MIT-licensed local song generator in 2026. Quick start: clone https://github.com/ace-step/ACE-Step-1.5 and follow the README (Gradio UI and API server included).
Sources: GitHub, HF, tech report, project page.
Timeline entry
- ACE-Step 1.5: MIT-licensed song generator that runs on consumer GPUs ★★★
ACE Studio and StepFun released ACE-Step 1.5, an MIT-licensed text-to-music model (LM planner + Diffusion Transformer) that generates full songs with lyrics in 50+ languages in seconds on consumer hardware, with covers, repainting and LoRA fine-tuning; a 4B-DiT XL series followed on 2026-04-02.