acappemin / video-to-audio-and-piano

Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization (Updated 1 month, 2 weeks ago)

  • Public
  • 34 runs
  • GitHub
  • Weights
  • Paper
  • License
Iterate in playground

Want to make some of these yourself?

Run this model