Skip to content

Latest commit

 

History

History
19 lines (12 loc) · 1.11 KB

File metadata and controls

19 lines (12 loc) · 1.11 KB

AceStepTransformer1DModel

A 1D Diffusion Transformer for music generation from ACE-Step 1.5. The model operates on the 25 Hz stereo latents produced by [AutoencoderOobleck] using flow matching, and is trained with a Qwen3-derived backbone (grouped-query attention, rotary position embedding, RMSNorm, AdaLN-Zero timestep conditioning) plus cross-attention to the text / lyric / timbre conditions built by AceStepConditionEncoder.

AceStepTransformer1DModel

[[autodoc]] AceStepTransformer1DModel