HKUSTAudio / AudioX-MAF-MMDiT

Audio10612Updated Feb 18, 2026

Downloads

106

Likes

12

Last updated

Feb 18, 2026

License

cc-by-nc-4.0

AudioX is a unified framework for generating audio and music from diverse multimodal control signals, including text, video, and audio. It features a Multimodal Adaptive Fusion (MAF) module to effectively align and fuse these inputs.

Tasks & library

  • text to audio

Tags

  • diffusion_cond
  • audio-generation
  • music-generation
  • text-to-audio

Technical specifications

ParametersNot available
LibraryNot available
LanguagesNot available
Licensecc-by-nc-4.0