MeLFusion (image-conditioned)

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio3 results

Text-to-Music GenerationonMusicCaps
FD· 2024-06-07
22.65
best: 36.42 (Stable Audio Open)
SOTA
MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models arXiv:2406.04673
Text-to-Music GenerationonMusicCaps
FAD· 2024-06-07
1.12
best: 13.4 (Riffusion)
MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models arXiv:2406.04673
Text-to-Music GenerationonMusicCaps
KL_passt· 2024-06-07
0.89
best: 1.87 (UniAudio)
MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models arXiv:2406.04673