ACE-Step 1.5
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
3recommend
1warn against
Feb 9, 2026first mention
Apr 7, 2026latest mention
Why people recommend it
“the results were actually good with it being opensource and for how cheap the model is to run.”
“ACEStep (very good music generation model)”
Show 2 more
“Ace step 1.5 is great, only 1.5b params so very easy to run locally.”
“experimenting with ACE-Step 1.5 lately”
Caveats and dissent
“the musicality of this system is much lower than what we have commercially”
Often compared with
From the makers not counted in the ranking
“We released ACE-Step 1.5, an open-sourced AI music model.”
Threads where it came up
- Ace-Step 1.5 prompt tips: how I get more controllable music output 2 mentions
- Ace-Step-1.5 playground- SOTA open source music model 1 mention
- Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act 1 mention
- Claude Sonnet 4.6 1 mention
- SHOW HN:AceStep1.5an on-device music model that beats Suno on common eval metric 1 mention
Also written as ACE-Step, Ace-Step-1.5. Data: ace-step-1-5.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 5
“the results were actually good with it being opensource and for how cheap the model is to run.”
“ACEStep (very good music generation model)”
“Ace step 1.5 is great, only 1.5b params so very easy to run locally.”
“the musicality of this system is much lower than what we have commercially”
“experimenting with ACE-Step 1.5 lately”