sourceactiveMusic and sound design

ACE-Step 1.5

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 2 · updated 2026-10-18 · src_01M569EH7T3ETK0TS4BRR8QX9A

Evidence: review revision unknown · inspection source_inspected · execution reported_by_source · review unreviewed · origin research_agent

Source: https://github.com/ace-step/ace-step-1.5

Successor line to ace-step/ACE-Step v1 (Apache-2.0, last push 2026-02-15); GitHub does not mark it a fork. Speed/quality figures are README claims, not tested.

Structured fields

{
  "archived": false,
  "checked_at": "2026-10-17T00:00:00.000Z",
  "usefulness": "Open music foundation model v1.5 for consumer hardware: full songs of 10 s to 10 min, claimed under 2 s per song on an A100, LoRA training from ~8 songs, track separation, XL 4B DiT variants (2026-04). Repo is MIT; weights and training-data rights need separate checking.",
  "source_type": "repository",
  "availability": "available",
  "source_owner": "ACE-Step team",
  "next_check_at": "2026-10-18T00:00:00.000Z",
  "hardware_notes": "README: <4 GB VRAM claim for base; 12-20 GB for XL models.",
  "upstream_updated_at": "2026-10-11T14:11:22.000Z"
}

Evidence claims

[upstream_claim] README: ACE-Step v1.5 is an open-source music foundation model claiming quality beyond most commercial music models (between Suno v4.5 and v5), under 2 seconds per full song on an A100 and under 10 seconds on an RTX 3090, running locally with less than 4GB VRAM. · locator: README, abstract and features source
[upstream_claim] README news 2026-04-02: ACE-Step 1.5 XL (4B DiT) released, ~9 GB VRAM for weights (vs ~4.7 GB for 2B), needing >=12 GB with offload+quantization or >=20 GB without; features include 10 s to 10 min generation, LoRA training (8 songs, 1 hour on a 3090 12GB) and track separation. · locator: README, News and feature table source
[sourced_fact] README License & Disclaimer: project licensed under MIT; acknowledges risks of unintentional copyright infringement from stylistic similarity and misuse; Python 3.11-3.12, CUDA recommended, also MPS/ROCm/Intel XPU/CPU. · locator: README, License & Disclaimer; Requirements source
[upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.

Rights

component	license	hosting	redistribution	modification	training	Evidence and notes
code	MIT	permitted	permitted	permitted	unknown	https://github.com/ace-step/ACE-Step-1.5/blob/main/LICENSE MIT per README.
model_weights	unknown	unknown	unknown	unknown	unknown	https://github.com/ace-step/ACE-Step-1.5 README license statement refers to the project; Hugging Face weight cards and training-data provenance were not inspected.

Linked records

Which open music-generation models are safe for commercial scoring, and what evidence supports their training-data claims? discusses → this

Machine-readable: JSON · Markdown · revisions · changes