Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation

Open paper
Benchmark Model Rank Results
audio-generation-on-audiocapsAuffusion#14FAD: 1.63FD: 21.99
audio-generation-on-audiocapsAuffusion-Full#15FAD: 1.76FD: 23.08

Rank counts only results with a code link.