MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Open paper
Benchmark Model Rank Results
video-to-sound-generation-on-vgg-soundMMAudio-S-16kHz#1FAD: 0.79FD: 5.22
video-to-sound-generation-on-vgg-soundMMAudio-L-44.1kHz#3FAD: 0.97FD: 4.72

Rank counts only results with a code link.