CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.music / ACE-Step-v1-3.5B
From: ACE-Step <huggingface.co/ACE-Step>Newsgroups: alt.freeweights.musicSubject:

ACE-Step-v1-3.5B

Date: 2026-11-15Commit: 82cd0d7Signed: 2DC28CC7B26A283B ✓

Text to audio model. Safetensors weights, 8.28 GB in all. Published by ACE-Step under Apache-2.0.

music8.28GBACE-Step-v1-3.5Bsafetensorspermissive
FactsParamsnot statedSize8.28 GBFormatssafetensorsTasktext to audioLicenseApache-2.0From sourcepermissive
$ fw get ACE-Step/ACE-Step-v1-3.5B
# manifest sha256 70f8cdc18479… · 8.28 GB · 14 files
$ fw verify ./ACE-Step-v1-3.5B ACE-Step/ACE-Step-v1-3.5B
From sourceHosted (signed)ACE-Step/ACE-Step-v1-3.5BLast check: 2026-11-15 04:30 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Run9Fine-tune7Convert8Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

TransformersComfyUILocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
8.28 GB
Weights
8.26 GB (safetensors)
Parameters
not stated
Formats
safetensors
Task
text to audio
License
Apache-2.0 (permissive)
Files
14, each with a sha256
Publisher
ACE-Step
Added
2026-11-15
Section
alt.freeweights.music
Lineage

Original release from the publisher.

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 04:30 UTCpassed

Model card

From the publisher at commit 82cd0d7. Shown as plain text with links; images open at the publisher.

ACE-Step: A Step Towards Music Generation Foundation Model#

Image: ACE-Step Framework

Model Description#

ACE-Step is a novel open-source foundation model for music generation that overcomes key limitations of existing approaches through a holistic architectural design. It integrates diffusion-based generation with Sana's Deep Compression AutoEncoder (DCAE) and a lightweight linear transformer, achieving state-of-the-art performance in generation speed, musical coherence, and controllability.

Key Features:

  • 15× faster than LLM-based baselines (20s for 4-minute music on A100)
  • Superior musical coherence across melody, harmony, and rhythm
  • full-song generation, duration control and accepts natural language descriptions

Uses#

Direct Use#

ACE-Step can be used for:

  • Generating original music from text descriptions
  • Music remixing and style transfer
  • edit song lyrics
Downstream Use#

The model serves as a foundation for:

  • Voice cloning applications
  • Specialized music generation (rap, jazz, etc.)
  • Music production tools
  • Creative AI assistants
Out-of-Scope Use#

The model should not be used for:

  • Generating copyrighted content without permission
  • Creating harmful or offensive content
  • Misrepresenting AI-generated music as human-created

How to Get Started#

see: https://github.com/ace-step/ACE-Step

Hardware Performance#

Device27 Steps60 Steps
NVIDIA A10027.27x12.27x
RTX 409034.48x15.63x
RTX 309012.76x6.48x
M2 Max2.27x1.03x

RTF (Real-Time Factor) shown - higher values indicate faster generation

Limitations#

  • Performance varies by language (top 10 languages perform best)
  • Longer generations (>5 minutes) may lose structural coherence
  • Rare instruments may not render perfectly
  • Output Inconsistency: Highly sensitive to random seeds and input duration, leading to varied "gacha-style" results.
  • Style-specific Weaknesses: Underperforms on certain genres (e.g. Chinese rap/zh_rap) Limited style adherence and musicality ceiling
  • Continuity Artifacts: Unnatural transitions in repainting/extend operations
  • Vocal Quality: Coarse vocal synthesis lacking nuance
  • Control Granularity: Needs finer-grained musical parameter control

Ethical Considerations#

Users should:

  • Verify originality of generated works
  • Disclose AI involvement
  • Respect cultural elements and copyrights
  • Avoid harmful content generation

Model Details#

Developed by: ACE Studio and StepFun Model type: Diffusion-based music generation with transformer conditioning License: Apache 2.0 Resources:

Citation#

@misc{gong2025acestep,
  title={ACE-Step: A Step Towards Music Generation Foundation Model},
  author={Junmin Gong, Wenxiao Zhao, Sen Wang, Shengyuan Xu, Jing Guo}, 
  howpublished={\url{https://github.com/ace-step/ACE-Step}},
  year={2025},
  note={GitHub repository}
}

Acknowledgements#

This project is co-led by ACE Studio and StepFun.

Files

14 files · 8.28 GBWeights 8.26 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256
FileSizesha256
.gitattributes1.58 KBd770b16a6c2bd919c2266aba306f2dcbe4d4393ab9e56d2b4b70ab432eb35df3
README.md3.51 KBb5674b0c01f5b8e6e38291f1d36baa749a60f5cd5c450b70d23e247a772d930f
ace_step_transformer/config.json639 B4d78beb6afb4c7f3705256b44faaf60f3e1e2d78f4015ca87740f3695d7f5447
ace_step_transformer/diffusion_pytorch_model.safetensors6.61 GBe810f16728d8a2e0d1b9c3a907aac8c9a427ce38edbd890cb3dce5ff92da5aad
config.json639 B4d78beb6afb4c7f3705256b44faaf60f3e1e2d78f4015ca87740f3695d7f5447
music_dcae_f8c8/config.json1.03 KBb14a49a8c52a52c2c8050098af1a946810a8a1a0b6e50abc75ba81371383cf04
music_dcae_f8c8/diffusion_pytorch_model.safetensors314 MB2b0cb469307ac50659d1880db2a99bae47d0df335cbb36853964662d4b80e8ee
music_vocoder/config.json940 B39ddc4c417e01dc3be1862fcf315887358dd61b7f91c3cc8227f65072984bb55
music_vocoder/diffusion_pytorch_model.safetensors206 MBc92c9b46e28ab7b37b777780cf4308ad7ddac869636bb77aa61599358c4bc1c0
umt5-base/config.json848 Bafae5da9a35e2b293cee66536f03fc2581cfc3f3d5707d3a262b552748de1572
umt5-base/model.safetensors1.13 GB779cec0d210b2123e21d0a9cd8128f02b4d412627355028965a8be0b241cc3b6
umt5-base/special_tokens_map.json7.08 KB456b58fd240a06c743a7c2cf8008bec501240d68ebd1fc4018ea569505fea270
umt5-base/tokenizer.json16.8 MB20a46ac256746594ed7e1e3ef733b83fbc5a6f0922aa7480eda961743de080ef
umt5-base/tokenizer_config.json61.7 KBed9a3a8b0faa71a70a32847e0435fe036e6e112d4df4edb7bb48a921e344dc05
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
82cd0d7b63 pinned now2026-11-15 04:30 UTC14 files · 8.28 GB

Use it

$ fw get ACE-Step/ACE-Step-v1-3.5B
# manifest sha256 70f8cdc18479… · 8.28 GB · 14 files
$ fw verify ./ACE-Step-v1-3.5B ACE-Step/ACE-Step-v1-3.5B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/ACE-Step/ACE-Step-v1-3.5B.json --dir ./ACE-Step-v1-3.5B $ python3 fw.py verify ./ACE-Step-v1-3.5B ./ACE-Step__ACE-Step-v1-3.5B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ACE-Step/ACE-Step-v1-3.5B --revision 82cd0d7b6322bd28cd4e830fe675ddb6180ce36c --local-dir ./ACE-Step-v1-3.5B
Packaged for ComfyUI. Most image, video and music models run in ComfyUI . Check the publisher's page for the workflow. Freeweights does not host it.
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
b5674b0c01f5b8e6e38291f1d36baa749a60f5cd5c450b70d23e247a772d930f
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: ACE-Step <huggingface.co/ACE-Step>Newsgroups: alt.freeweights.musicSubject: ACE-Step-v1-3.5BDate: 2026-11-15Commit: 82cd0d7Signed: 2DC28CC7B26A283B ✓
Upstream
ACE-Step/ACE-Step-v1-3.5B
Pinned commit
82cd0d7b6322bd28cd4e830fe675ddb6180ce36c
Manifest
ACE-Step-v1-3.5B.json · .minisig
Manifest sha256
70f8cdc18479f92df4dc5455c28e402bf3fd9ebf37584cf00b24bccde2a16bf7
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:30 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ACE-Step/ACE-Step-v1-3.5B.json $ curl -O https://freeweights.allternit.com/manifests/ACE-Step/ACE-Step-v1-3.5B.json.minisig $ minisign -Vm ACE-Step-v1-3.5B.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

1 model in the catalog name this one as their parent.

Fine-tunes
1
Fine-tunes 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ACE-Step/ACE-Step-v1-3.5B
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. ACE-Step-v1-3.5B.json. Provenance. Takedown history: none.
Source
huggingface.co/ACE-Step/ACE-Step-v1-3.5B

Related models

All of alt.freeweights.music →
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: ACE-Step
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: stable-audio-3
From: stabilityai <huggingface.co/stabilityai>Subject: stable-audio-3-medium
From: stabilityai <huggingface.co/stabilityai>Subject: stable-audio-3-medium-base
From: stabilityai <huggingface.co/stabilityai>Subject: stable-audio-3-optimized
From: stabilityai <huggingface.co/stabilityai>Subject: stable-audio-3-small-music