hugpadhugpad

ACE-Step / acestep-v15-xl-sft-diffusers

Audio4.2B2.8K12Updated Jun 3, 2026
Hugging Face

Downloads

2.8K

Likes

12

Last updated

Jun 3, 2026

License

mit

Diffusers-format checkpoint of ACE-Step v1.5 XL SFT - the supervised fine-tuned 5B-parameter flow-matching DiT for text-to-music generation (hiddensize=2560, 32 layers, 32 heads; encoderhiddensize=2048 on the condition encoder).

Tasks & library

  • text to audio
  • diffusers

Tags

  • diffusers
  • acestep
  • audio
  • music
  • text-to-music
  • flow-matching

Technical specifications

Parameters4.2B
Librarydiffusers
LanguagesNot available
Base modelACE-Step/acestep-v15-xl-sft
Licensemit