Video-to-Audio Generation on VGGSound (test)
0.52FADFoley-Flow
Evaluation Results
| Method | Links | ||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Foley-Flow2026.03 | 0.52 | — | — | — | — | — | — | 0.97 | — | — | — | — | — | — | — | — | 98.97 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MoG-HGGuidance=Hierarchical Guidance2025.09 | 0.68 | — | — | — | — | — | — | 2.2 | — | — | — | — | — | — | — | — | 86.6 | — | — | — | — | 17.2 | — | 4.06 | — | — | — | — | — | 33.1 | — | — | |
| MoG-PGGuidance=Parallel Guidance2025.09 | 0.7 | — | — | — | — | — | — | 2.22 | — | — | — | — | — | — | — | — | 86.1 | — | — | — | — | 16.8 | — | 4.14 | — | — | — | — | — | 32.9 | — | — | |
| CFG-onlyGuidance=CFG-only2025.09 | 0.73 | — | — | — | — | — | — | 2.28 | — | — | — | — | — | — | — | — | 85.8 | — | — | — | — | 17.1 | — | 4.48 | — | — | — | — | — | 32.8 | — | — | |
| GMS-CAVP2026.01 | 0.75 | — | — | — | — | — | — | 1.63 | — | — | — | — | — | — | — | — | 95.87 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| V2A-MapperBandwidth Extension=44.1 kHz2024.07 | 0.84 | 0.24 | 2.72 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| V2A-MapperParams=229M2025.10 | 0.84 | 84.57 | — | — | — | — | — | 2.69 | — | — | — | — | — | — | — | — | — | — | — | — | — | 12.47 | 1.225 | — | — | — | — | — | — | 22.58 | — | — | |
| V2A-MapperBandwidth Extension=No2024.07 | 0.89 | 0.45 | 14.1 | 0.47 | 0.124 | -0.01 | 0.68 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| V2A-MapperModel=V2A-Mapper2025.09 | 0.9 | — | — | — | — | — | — | 2.68 | — | — | — | — | — | — | — | — | 78.3 | — | — | — | — | 12.5 | — | 8.35 | — | — | — | — | — | 22.4 | — | — | |
| MMAudio-L-44kParams=1.03B2025.10 | 0.97 | 60.6 | — | — | — | — | — | 1.65 | — | — | — | — | — | — | — | — | — | — | — | — | — | 17.4 | 0.442 | — | — | — | — | — | — | 33.22 | — | — | |
| V2A-MapperText prompts=false, Speed (s)=11.542024.11 | 0.99 | — | — | — | — | — | — | 2.78 | — | — | — | — | — | — | — | — | 74.37 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| V2A-Mapper2026.01 | 0.99 | — | — | — | — | — | — | 2.78 | — | — | — | — | — | — | — | — | 74.37 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| V2A-Mapper2026.03 | 0.99 | — | — | — | — | — | — | 2.78 | — | — | — | — | — | — | — | — | 74.37 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SpecMaskFoleyParams=300M2025.10 | 1.03 | 108.62 | — | — | — | — | — | 1.76 | — | — | — | — | — | — | — | — | — | — | — | — | — | 11.43 | 0.652 | — | — | — | — | — | — | 26.39 | — | — | |
| DAC reconstruct2024.07 | 1.06 | 0.04 | 0.1 | 0.9 | 0.126 | 0.97 | 0.46 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| V2A-mapperSampling rate=16K2024.11 | 1.13 | — | — | — | — | — | — | 2.4 | — | — | 24.5 | — | — | 25.2 | 1.24 | 8.59 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DAC-VAE (VGGSound)Sampling rate=48K, Note=Oracle baseline2024.11 | 1.21 | — | — | — | — | — | — | 0.28 | — | — | 28.2 | — | — | 35.4 | 0.62 | 5.91 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FrierenParams=159M2025.10 | 1.34 | 106.1 | — | — | — | — | — | 2.73 | — | — | — | — | — | — | — | — | — | — | — | — | — | 12.25 | 0.851 | — | — | — | — | — | — | 22.78 | — | — | |
| FrierenType=Rectified Flow Matching (RFM)2024.09 | 1.43 | — | — | — | — | — | — | 2.95 | — | — | — | — | — | 19.56 | 277 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskVAT Seq2Seq2024.07 | 1.51 | 0.06 | 0.6 | 0.55 | 0.14 | 0.05 | 0.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskVAT2026.01 | 1.51 | — | — | — | — | — | — | 2.65 | — | — | — | — | — | — | — | — | 63.87 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskVAT2026.03 | 1.51 | — | — | — | — | — | — | 2.65 | — | — | — | — | — | — | — | — | 63.87 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FrierenSampling rate=16K2024.11 | 1.54 | — | — | — | — | — | — | 2.5 | — | — | 24.7 | — | — | 25.4 | 0.87 | 5.13 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyGenModel=FoleyGen2025.09 | 1.65 | — | — | — | — | — | — | 2.35 | — | — | — | — | — | — | — | — | 73.8 | — | — | — | — | — | — | — | — | — | — | — | — | 26.1 | — | — | |
| MMAudioSep (pretrain wo/frozen)Params=1.03B, Pretraining=wo/frozen2025.10 | 1.68 | 104.84 | — | — | — | — | — | 1.74 | — | — | — | — | — | — | — | — | — | — | — | — | — | 13.47 | 0.556 | — | — | — | — | — | — | 28.18 | — | — | |
| MMAudioSep (pretrain w/frozen)Params=540M, Pretraining=w/frozen2025.10 | 1.76 | 103.03 | — | — | — | — | — | 1.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | 14.99 | 0.488 | — | — | — | — | — | — | 30.35 | — | — | |
| ReWaSParams=619M2025.10 | 1.79 | 141.38 | — | — | — | — | — | 2.87 | — | — | — | — | — | — | — | — | — | — | — | — | — | 8.51 | 1.062 | — | — | — | — | — | — | 14.82 | — | — | |
| V-AURAType=Autoregressive (AR)2024.09 | 1.92 | — | — | — | — | — | — | 2.31 | — | — | — | — | — | 25.01 | 155 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VTA-LDMModel=VTA-LDM2025.09 | 2.01 | — | — | — | — | — | — | 2.37 | — | — | — | — | — | — | — | — | 77 | — | — | — | — | 10.4 | — | 12.8 | — | — | — | — | — | 26.2 | — | — | |
| MaskVAT Hybrid2024.07 | 2.04 | 0.08 | 0.88 | 0.55 | 0.136 | 0.17 | 0.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ReWaSnumber of parameters=204M2024.07 | 2.16 | 15.24 | — | — | — | — | — | — | — | 2.78 | 0.4353 | 0.1149 | 0.3008 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyCrafterModel=FoleyCrafter2025.09 | 2.32 | — | — | — | — | — | — | 2.54 | — | — | — | — | — | — | — | — | 83.6 | — | — | — | — | 9.9 | — | 18.1 | — | — | — | — | — | 27.7 | — | — | |
| VATT-GemmaBackbone=Gemma-2B, Text prompts=false, Speed (s)=0.652024.11 | 2.35 | — | — | — | — | — | — | 2.25 | — | — | — | — | — | — | — | — | 82.81 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VATT2026.01 | 2.35 | — | — | — | — | — | — | 2.25 | — | — | — | — | — | — | — | — | 82.81 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VATT2026.03 | 2.35 | — | — | — | — | — | — | 2.25 | — | — | — | — | — | — | — | — | 82.81 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VATTModel=VATT, text_input=excluded2025.09 | 2.35 | — | — | — | — | — | — | 2.25 | — | — | — | — | — | — | — | — | 82.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VATT-LLamaBackbone=LLama-2-7B, Text prompts=false, Speed (s)=1.12024.11 | 2.38 | — | — | — | — | — | — | 2.39 | — | — | — | — | — | — | — | — | 80.32 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MMAudioSep (scratch)Params=1.03B, Pretraining=None2025.10 | 2.42 | 146.05 | — | — | — | — | — | 2.11 | — | — | — | — | — | — | — | — | — | — | — | — | — | 10.31 | 0.655 | — | — | — | — | — | — | 25.09 | — | — | |
| AudioLDM-2Text Prompt=GT audio caption2024.11 | 2.46 | — | — | — | — | — | — | 2.09 | — | — | 0.326 | — | — | — | — | — | 51.84 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyCrafterParams=1.22B2025.10 | 2.51 | 140.09 | — | — | — | — | — | 2.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | 15.68 | 1.225 | — | — | — | — | — | — | 25.68 | — | — | |
| VATT-LLama-TBackbone=LLama-2-7B, Text prompts=true, Speed (s)=1.22024.11 | 2.54 | — | — | — | — | — | — | 1.41 | — | — | — | — | — | — | — | — | 80.16 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VATT-LLama-TText Prompt=GT audio caption2024.11 | 2.54 | — | — | — | — | — | — | 1.41 | — | — | 0.347 | — | — | — | — | — | 80.16 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyGenZero-shot=true2024.09 | 2.59 | — | — | — | — | — | — | 2.89 | 6.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyGenText prompts=false, Speed (s)=6.92024.11 | 2.59 | — | — | — | — | — | — | 2.89 | — | — | — | — | — | — | — | — | 73.83 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyGen2026.01 | 2.59 | — | — | — | — | — | — | 2.89 | — | — | — | — | — | — | — | — | 73.83 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyGen2026.03 | 2.59 | — | — | — | — | — | — | 2.89 | — | — | — | — | — | — | — | — | 73.83 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seeing & Hearing2026.01 | 2.63 | — | — | — | — | — | — | 2.62 | — | — | — | — | — | — | — | — | 78.95 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seeing & Hearing2026.03 | 2.63 | — | — | — | — | — | — | 2.62 | — | — | — | — | — | — | — | — | 78.95 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VAB-EncodecZero-shot=true, decoding steps=16, classifier-free guidance scale=52024.09 | 2.69 | — | — | — | — | — | — | 2.58 | 0.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VAB2026.01 | 2.69 | — | — | — | — | — | — | 2.58 | — | — | — | — | — | — | — | — | 76.83 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VAB2026.03 | 2.69 | — | — | — | — | — | — | 2.58 | — | — | — | — | — | — | — | — | 76.83 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VAB-EncodecModel=VAB-Encodec2025.09 | 2.69 | — | — | — | — | — | — | 2.58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyCrafterSampling rate=16K2024.11 | 2.74 | — | — | — | — | — | — | 2.07 | — | — | 25.3 | — | — | 30.2 | 1.24 | 6.89 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VATT2025.10 | 2.77 | 131.88 | — | — | — | — | — | 1.48 | — | — | — | — | — | — | — | — | — | — | — | — | — | 11.9 | 1.195 | — | — | — | — | — | — | 25 | — | — | |
| V-AURAParams=695M2025.10 | 2.88 | 218.5 | — | — | — | — | — | 2.42 | — | — | — | — | — | — | — | — | — | — | — | — | — | 10.08 | 0.654 | — | — | — | — | — | — | 27.64 | — | — | |
| MultiFoleySampling rate=48K2024.11 | 2.92 | — | — | — | — | — | — | 1.43 | — | — | 34.4 | — | — | 28 | 0.8 | 4.62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VATT-Gemma-TBackbone=Gemma-2B, Text prompts=true, Speed (s)=0.762024.11 | 2.98 | — | — | — | — | — | — | 1.66 | — | — | — | — | — | — | — | — | 81.48 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VATT-Gemma-TText Prompt=GT audio caption2024.11 | 2.98 | — | — | — | — | — | — | 1.66 | — | — | 0.31 | — | — | — | — | — | 81.48 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FoleyGenSampling rate=16K2024.11 | 3.01 | — | — | — | — | — | — | 2.48 | — | — | 23.4 | — | — | 24.4 | 1.24 | 4.62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AudioGenText Prompt=GT audio caption2024.11 | 3.17 | — | — | — | — | — | — | 2.19 | — | — | 0.409 | — | — | — | — | — | 48.96 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VAB-DACZero-shot=true, decoding steps=16, classifier-free guidance scale=52024.09 | 3.24 | — | — | — | — | — | — | 2.84 | 1.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VABSampling rate=16K2024.11 | 3.26 | — | — | — | — | — | — | 2.18 | — | — | 23.5 | — | — | 27.9 | 1.2 | 4.85 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskVAT AdaLN-BConditioning=CLIP and S3D conditioning2024.07 | 3.39 | 0.05 | 0.88 | 0.5 | 0.123 | 0.16 | 0.43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AudioLDM-2Text Prompt=LLAVA visual caption2024.11 | 3.62 | — | — | — | — | — | — | 3.54 | — | — | — | — | — | — | — | — | 53.49 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskVAT AdaLN-AConditioning=only CLIP conditioning2024.07 | 3.83 | 0.06 | 1.21 | 0.48 | 0.123 | 0.05 | 0.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SpecVQGANBandwidth Extension=No2024.07 | 5.27 | 0.26 | 7.75 | 0.33 | 0.08 | 0.02 | 0.67 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seeing&HearingParams=415M2025.10 | 5.4 | 219.01 | — | — | — | — | — | 2.26 | — | — | — | — | — | — | — | — | — | — | — | — | — | 8.58 | 1.204 | — | — | — | — | — | — | 33.99 | — | — | |
| SpecVQGANnumber of parameters=379M2024.07 | 5.57 | 26.63 | — | — | — | — | — | — | — | 3.3 | 0.1336 | 0.1422 | 0.2851 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diff-FoleyType=Diffusion (DM)2024.09 | 5.62 | — | — | — | — | — | — | 3.23 | — | — | — | — | — | 16.88 | 321 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SpecVQGANBandwidth Extension=44.1 kHz2024.07 | 5.75 | 0.42 | 8.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diff-FoleyModel=Diff-Foley2025.09 | 5.79 | — | — | — | — | — | — | 3.12 | — | — | — | — | — | — | — | — | 89.9 | — | — | — | — | 10.8 | — | 21.9 | — | — | — | — | — | 20.4 | — | — | |
| Im2wavnumber of parameters=365M2024.07 | 5.94 | 16.87 | — | — | — | — | — | — | — | 2.53 | 0.4001 | 0.131 | 0.2763 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AudioGenText Prompt=LLAVA visual caption2024.11 | 6.03 | — | — | — | — | — | — | 3.65 | — | — | — | — | — | — | — | — | 41.66 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Im2WavBandwidth Extension=No2024.07 | 6.21 | 0.45 | 11.9 | 0.45 | 0.116 | 0 | 0.68 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| IM2WAVZero-shot=true2024.09 | 6.32 | — | — | — | — | — | — | 2.54 | 289.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| IM2WAVText prompts=false, Speed (s)=289.52024.11 | 6.32 | — | — | — | — | — | — | 2.54 | — | — | — | — | — | — | — | — | 74.31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Im2Wav2026.01 | 6.32 | — | — | — | — | — | — | 2.54 | — | — | — | — | — | — | — | — | 74.31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Im2Wav2026.03 | 6.32 | — | — | — | — | — | — | 2.54 | — | — | — | — | — | — | — | — | 74.31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diff-FoleyZero-shot=true2024.09 | 6.4 | — | — | — | — | — | — | 3.15 | 4.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diff-FoleyText prompts=false, Speed (s)=4.42024.11 | 6.4 | — | — | — | — | — | — | 3.15 | — | — | — | — | — | — | — | — | 82.47 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diff-Foley2026.01 | 6.4 | — | — | — | — | — | — | 3.15 | — | — | — | — | — | — | — | — | 82.47 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diff-Foley2026.03 | 6.4 | — | — | — | — | — | — | 3.15 | — | — | — | — | — | — | — | — | 82.47 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SpecVQGANType=Autoregressive (AR)2024.09 | 6.41 | — | — | — | — | — | — | 3.16 | — | — | — | — | — | 10.09 | 409 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| IM2WAVModel=IM2WAV2025.09 | 6.41 | — | — | — | — | — | — | 2.54 | — | — | — | — | — | — | — | — | 74.3 | — | — | — | — | — | — | — | — | — | — | — | — | 19 | — | — | |
| Diff-Foleynumber of parameters=859M2024.07 | 6.46 | 21.96 | — | — | — | — | — | — | — | 3.15 | 0.401 | 0.1571 | 0.2059 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diff-FoleySampling rate=16K2024.11 | 6.53 | — | — | — | — | — | — | 2.9 | — | — | 20.5 | — | — | 19.5 | 1.01 | 4.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seeing&Hearingmode=Optimization-based generation2024.07 | 6.58 | 20.72 | — | — | — | — | — | — | — | 2.34 | 0.5805 | 0.1668 | 0.1858 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SpecVQGANZero-shot=true2024.09 | 6.63 | — | — | — | — | — | — | 3.78 | 7.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SpecVQGANText prompts=false, Speed (s)=7.22024.11 | 6.63 | — | — | — | — | — | — | 3.78 | — | — | — | — | — | — | — | — | 48.79 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SpecVQGAN2026.01 | 6.63 | — | — | — | — | — | — | 3.78 | — | — | — | — | — | — | — | — | 48.79 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SpecVQGAN2026.03 | 6.63 | — | — | — | — | — | — | 3.78 | — | — | — | — | — | — | — | — | 48.79 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Im2WavSampling rate=16K2024.11 | 7.36 | — | — | — | — | — | — | 2.11 | — | — | 25.2 | — | — | 22.3 | 1.25 | 5.88 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diff-FoleyBandwidth Extension=44.1 kHz2024.07 | 7.54 | 1.22 | 22.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Im2WavBandwidth Extension=44.1 kHz2024.07 | 7.89 | 0.45 | 7.24 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Diff-FoleyBandwidth Extension=No2024.07 | 8.6 | 1.09 | 30.8 | 0.35 | 0.087 | 0.07 | 0.57 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AC-FoleyAudio Conditioning=true2026.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | 37.1 | — | — | — | — | — | 56 | 4.93 | — | 0.465 | 1.08 | 0.84 | 0.95 | 28.32 | 53.17 | 11.37 | — | — | — | |
| AC-FoleyAudio Conditioning=false2026.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | 36.6 | — | — | — | — | — | 64.9 | 8.59 | — | 0.41 | 3.87 | 1.17 | 1.34 | 26.19 | 50.95 | 14.59 | — | — | — | |
| AudioIMstyle_encoder=excluded2026.06 | — | — | — | — | — | — | 3.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.68 | 1.9 | — | — | — | — | — | — | |
| AudioIMvariant=ours2026.06 | — | — | — | — | — | — | 4.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.63 | 1.85 | — | — | — | — | — | — | |
| AudioIMStyle Encoder=false2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.21 | — | — | — | — | — | — | — | — | 0.51 | — | 1.49 | 1.7 | — | — | — | — | — | — |