As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/ace-step-1-5/

# ACE-Step 1.5 (incl. 1.5 XL)

ACE Studio & StepFun, ACE-Step family. Status: current. Type: music generation. Released: 2026-01-28.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face |  |  | https://huggingface.co/ACE-Step/Ace-Step1.5 |
| Hugging Face (XL 4B DiT) |  |  | https://huggingface.co/ACE-Step/acestep-v15-xl-sft |
| GitHub |  |  | https://github.com/ace-step/ACE-Step-1.5 |
| Web app |  |  | https://acemusic.ai |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text, audio
- Output: audio
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: mit

## Where it stands

- Newer music generation models in the registry since its release: 9. The 5 newest:
  - Eleven Music v2.5 (2026-09-11) https://postcutoff.com/m/elevenlabs-music-v2-5/
  - Suno v6 (v6, v6-wild, v6-mini) (2026-09-09) https://postcutoff.com/m/suno-v6/
  - YuE2-3B (2026-09-09) https://postcutoff.com/m/yue2/
  - Lyria 3.5 (2026-07-29) https://postcutoff.com/m/lyria-3-5/
  - MiniMax Music 3.0 (2026-07-16) https://postcutoff.com/m/minimax-music-3/
- Weights are public under a permissive licence (MIT).

## What stands out

- 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: https://github.com/ace-step/ACE-Step-1.5
- 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: https://arxiv.org/abs/2602.00744
- 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: https://github.com/ace-step/ACE-Step-1.5

## Notes

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.

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](https://github.com/ace-step/ACE-Step-1.5), [HF](https://huggingface.co/ACE-Step/Ace-Step1.5), [tech report](https://arxiv.org/abs/2602.00744), [project page](https://ace-step.github.io/ace-step-v1.5.github.io/).

Model page: https://postcutoff.com/m/ace-step-1-5/