Video-to-audio generation on VGGSound
0.97FD_VGGMMAudio-L
Evaluation results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MMAudio-LAudio length=~10 seconds2026.02 | 0.97 | 17.4 | 13.33 | 33.22 | 0.442 | — | — | — | — | — | — | — | — | — | — | — | — | |
| VSSFlow-MParam. Count=443M, Extra Data=–2025.09 | 1.11 | — | — | — | 0.59 | 107.95 | 6.58 | 12.37 | 2.22 | 29.64 | — | — | — | — | — | — | — | |
| VSSFlow-LParam. Count=681M, Extra Data=–2025.09 | 1.12 | — | — | — | 0.59 | 98.45 | 6.52 | 12.83 | 2.26 | 29.59 | — | — | — | — | — | — | — | |
| MMAudioConditioning=Video and text prompt2026.06 | 1.27 | — | — | 0.31 | 0.57 | 102.93 | — | 15.76 | 1.99 | — | 0.21 | — | — | — | — | — | — | |
| VSSFlow-SParam. Count=245M, Extra Data=–2025.09 | 1.33 | — | — | — | 0.65 | 136.8 | 9.55 | 10.62 | 2.24 | 28.38 | — | — | — | — | — | — | — | |
| V2A-M.Param. Count=–, Extra Data=–2025.09 | 1.45 | — | — | — | 1.22 | 113.55 | 8.16 | 12.45 | 2.66 | 22.25 | — | — | — | — | — | — | — | |
| FrierenParam. Count=421M, Extra Data=–2025.09 | 1.49 | — | — | — | 0.85 | 100.33 | 11.66 | 12.25 | 2.71 | 22.88 | — | — | — | — | — | — | — | |
| MMHNet-SAudio length=~10 seconds2026.02 | 1.54 | 16.73 | 12.52 | 32.11 | 0.46 | — | — | — | — | — | — | — | — | — | — | — | — | |
| Foley-OmniConditioning=Video and text prompt2026.06 | 1.57 | — | — | 0.28 | 0.5 | 101.4 | — | 14 | 1.92 | — | 0.21 | — | — | — | — | — | — | |
| MMAudio-SAudio length=~10 seconds2026.02 | 1.66 | 18.02 | 12.46 | 32.27 | 0.444 | — | — | — | — | — | — | — | — | — | — | — | — | |
| LoVAAudio length=~10 seconds2026.02 | 1.7 | 9.73 | 9.91 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MMAudioParam. Count=1054M, Extra Data=A.&W.C.2025.09 | 1.77 | — | — | — | 0.45 | 65.16 | 5.95 | 17.4 | 1.67 | 33.23 | — | — | — | — | — | — | — | |
| LoVAParam. Count=1057M, Extra Data=A.S.2025.09 | 2.02 | — | — | — | 1.22 | 150.54 | 13.13 | 11.39 | 2.3 | 26.01 | — | — | — | — | — | — | — | |
| MMHNet-LAudio length=~10 seconds2026.02 | 2.09 | 20.52 | 15.34 | 32.11 | 0.46 | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyC.Param. Count=1126M, Extra Data=–2025.09 | 2.17 | — | — | — | 1.21 | 142.34 | 12.85 | 10.59 | 2.33 | 27.75 | — | — | — | — | — | — | — | |
| HunyuanVideo-FoleyConditioning=Video and text prompt2026.06 | 2.18 | — | — | 0.32 | 0.55 | 79.07 | — | 15.49 | 2.02 | — | 0.23 | — | — | — | — | — | — | |
| V-AURAParam. Count=893M, Extra Data=–2025.09 | 2.2 | — | — | — | 0.65 | 218.5 | 14.8 | 8.95 | 2.42 | 27.6 | — | — | — | — | — | — | — | |
| MultiF.Param. Count=332M, Extra Data=HQ-SFX2025.09 | 2.45 | — | — | — | 0.82 | 148.93 | 13.81 | 15.9 | 1.69 | 27 | — | — | — | — | — | — | — | |
| FoleyCrafterConditioning=Video and text prompt2026.06 | 2.54 | — | — | 0.25 | 1.23 | 137.52 | — | 15.02 | 2.32 | — | 0.19 | — | — | — | — | — | — | |
| V-AURAAudio length=~10 seconds2026.02 | 2.88 | 10.08 | — | 27.64 | 0.654 | — | — | — | — | — | — | — | — | — | — | — | — | |
| VABParam. Count=403M, Extra Data=A.S.2025.09 | 2.98 | — | — | — | 1.17 | 192.07 | 18.26 | 9.6 | 2.51 | 25.82 | — | — | — | — | — | — | — | |
| TiVAParam. Count=346M, Extra Data=A.S.2025.09 | 3.86 | — | — | — | 1.18 | 304.6 | 23.62 | 6.6 | 3.23 | 16.92 | — | — | — | — | — | — | — | |
| Seeing.Param. Count=416M, Extra Data=–2025.09 | 3.94 | — | — | — | 1.2 | 206.63 | 21.96 | 5.92 | 2.78 | 36.81 | — | — | — | — | — | — | — | |
| DifffoleyParam. Count=859M, Extra Data=A.S.2025.09 | 4.72 | — | — | — | 0.91 | 409.2 | 23.05 | 10.77 | 3.14 | 20.6 | — | — | — | — | — | — | — | |
| SpecVQParam. Count=377M, Extra Data=–2025.09 | 4.8 | — | — | — | 1.23 | 270.07 | 28.62 | 5 | 3.31 | 13.77 | — | — | — | — | — | — | — | |
| Im2WavParam. Count=360M, Extra Data=–2025.09 | 4.84 | — | — | — | 1.22 | 242.05 | 18.34 | 7.29 | 2.5 | 19.59 | — | — | — | — | — | — | — | |
| MMAudio2026.06 | 6.18 | — | — | — | — | — | — | 14.95 | 1.97 | — | — | 2.04 | 3.38 | 5.91 | 0.35 | 87 | -0.56 | |
| AudioX-Base2026.06 | 6.94 | — | — | — | — | — | — | 12.35 | 1.98 | — | — | 2 | 3.75 | 6.31 | 0.28 | 89 | -0.61 | |
| AudioX-Turbosampling steps=42026.06 | 7.88 | — | — | — | — | — | — | 12.39 | 1.99 | — | — | 1.34 | 3.78 | 6.23 | 0.29 | 90 | -0.6 | |
| VATT2026.06 | 11.71 | — | — | — | — | — | — | 10.02 | 1.4 | — | — | 2.55 | 3.64 | 5.85 | 0.25 | 84 | -0.66 | |
| VTA-LDMConditioning=Video and text prompt2026.06 | 18.77 | — | — | 0.06 | 1.17 | 827.57 | — | 2.01 | 3.45 | — | -0.04 | — | — | — | — | — | — | |
| VAB2026.06 | 20.21 | — | — | — | — | — | — | 8.15 | 2.3 | — | — | 3.05 | 3.52 | 5.93 | 0.24 | 82 | -0.64 |