Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Image-to-Audio generation on VGGSound Paprika style (test)
Loading...
2.612
KL Divergence
Im2Wav
2.59188
2.72769
2.8635
2.99931
Feb 27, 2024
KL Divergence
Inception Score (ISc)
Fréchet Distance (FD)
Fréchet Audio Distance (FAD)
Updated 4d ago
Evaluation Results
Method
Method
Links
KL Divergence
Inception Score (ISc)
Fréchet Distance (FD)
Fréchet Audio Distance (FAD)
Im2Wav
2024.02
2.612
7.055
19.627
7.576
Diffusion Latent Aligner
variant=full, denoisin...
2024.02
2.691
6.149
20.958
6.869
Diffusion Latent Aligner
variant=vanilla, denoi...
2024.02
3.115
4.986
33.049
7.364
Feedback
Search any
task
Search any
task