Composite audio comparisons with state-of-the-art methods

Example 5 Back to index

Captions for each audio tracks (all sounds should be contained)

  1. Ferret squeaks softly
  2. Grass rustles gently
  3. Hands pat gently
  4. Ferret breathes calmly
  5. Wind whispers faintly
MMAudio + NAG (ours) MMAudio MMAudio + Negative prompting
Seeing-and-Hearing FoleyCrafter FoleyCrafter + Negative prompting