Using matched neutral and target-swap prompts, ACE-Step 1.5 and Stable Audio 3 show real key control and partial beat control, while LeVo2 does not, and much four-beat agreement is just the models' default output.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do Text-to-Music Models Really Follow Instructions? A Counterfactual Evaluation of Key and Beat Grouping
Using matched neutral and target-swap prompts, ACE-Step 1.5 and Stable Audio 3 show real key control and partial beat control, while LeVo2 does not, and much four-beat agreement is just the models' default output.