Text-to-Music Generation on MusicCaps
1.01KLDMusicLM
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MusicLM2023.01 | 1.01 | 0.44 | 4 | 0.51 | 312 | — | — | — | — | — | — | — | |
| TangoMusicTask=T2M2026.06 | 1.13 | — | — | — | — | 1.88 | 2.86 | — | 15 | 5.57 | 7.06 | 0.23 | |
| Riffusion2023.01 | 1.19 | 0.76 | 13.4 | 0.34 | 158 | — | — | — | — | — | — | — | |
| AudioLDM 2 (Full)Params=712M, Hours=17.9k2024.09 | 1.2 | — | — | — | — | 3.13 | — | — | — | — | — | — | |
| MusicGenParams=1.5B, Hours=20k2024.09 | 1.22 | — | — | — | — | 3.8 | — | 0.31 | — | — | — | — | |
| FluxMusicParams=2.1B, Hours=22K2024.09 | 1.25 | — | — | — | — | 1.43 | 2.98 | 0.36 | — | — | — | — | |
| AudioLDM-2-LargeTask=T2M2026.06 | 1.26 | — | — | — | — | 2.8 | 2.84 | — | 15.61 | 5.22 | 6.7 | 0.23 | |
| Jen-1Params=746M, Hours=5.0k2024.09 | 1.29 | — | — | — | — | 2.11 | — | 0.33 | — | — | — | — | |
| QA-MDT (DiT)Params=675M, Hours=12.5k2024.09 | 1.31 | — | — | — | — | 1.65 | 2.8 | 0.35 | — | — | — | — | |
| AudioX-TurboTask=T2M2026.06 | 1.31 | — | — | — | — | 1.54 | 3.61 | — | 9.5 | 4.89 | 6.55 | 0.22 | |
| MAGNET-largeTask=T2M2026.06 | 1.32 | — | — | — | — | 4.24 | 1.98 | — | 23.88 | 5.84 | 6.71 | 0.19 | |
| AudioX-BaseTask=T2M2026.06 | 1.38 | — | — | — | — | 1.67 | 3.47 | — | 12.89 | 4.57 | 6.45 | 0.2 | |
| MusicGenTask=T2M2026.06 | 1.43 | — | — | — | — | 4.55 | 2.24 | — | 25.4 | 5.19 | 7.16 | 0.18 | |
| AudioLDM-L-FullTask=T2M2026.06 | 1.45 | — | — | — | — | 6.34 | 2.49 | — | 34.44 | 4.72 | 6.1 | 0.22 | |
| AudioLDM 2 (Music)Params=712M, Hours=10.8k2024.09 | 1.46 | — | — | — | — | 4.04 | 2.67 | 0.34 | — | — | — | — | |
| QA-MDT (U-Net)Params=1.0B, Hours=12.5k2024.09 | 1.51 | — | — | — | — | 2.03 | 2.41 | 0.33 | — | — | — | — | |
| Stable Audio OpenTask=T2M2026.06 | 1.51 | — | — | — | — | 3.23 | 2.94 | — | 36.33 | 3.91 | 7.18 | 0.23 | |
| Mubert2023.01 | 1.58 | 0.45 | 9.6 | 0.32 | 97 | — | — | — | — | — | — | — | |
| MousaiParams=1042M, Hours=2.5k2024.09 | 1.59 | — | — | — | — | 7.5 | — | 0.23 | — | — | — | — | |
| Mubert2023.02 | — | — | — | — | 254 | — | — | — | — | — | — | — | |
| MusicCapsType=Ground Truth Reference2023.01 | — | — | — | — | 472 | — | — | — | — | — | — | — | |
| MusicCaps (Ground Truth)2023.02 | — | — | — | — | 959 | — | — | — | — | — | — | — | |
| MusicLM2023.02 | — | — | — | — | 692 | — | — | — | — | — | — | — | |
| MusicLMParams=1290M, Hours=280k2024.09 | — | — | — | — | — | 4 | — | — | — | — | — | — | |
| Noise2MusicArchitecture=Waveform2023.02 | — | — | — | — | 718 | — | — | — | — | — | — | — | |
| Riffusion2023.02 | — | — | — | — | 308 | — | — | — | — | — | — | — |