Text-to-Audio Generation on Image-Text-Audio
2.47FADTangoFlux
Evaluation results
| Method | Links | |
|---|---|---|
| TangoFluxCategory=Specialists2026.06 | 2.47 | |
| MoPoECategory=Multimodal VAEs, Backbone=same as MUNI, Compute=same as MUNI2026.06 | 3.46 | |
| MUNICategory=Generalists2026.06 | 3.52 | |
| MUNI†Category=Generalists2026.06 | 3.52 | |
| MMVAECategory=Multimodal VAEs, Backbone=same as MUNI, Compute=same as MUNI2026.06 | 3.55 | |
| OmniFlowCategory=Generalists2026.06 | 4.08 | |
| FlowBindCategory=Generalists2026.06 | 4.64 | |
| UnifiedIO2-LCategory=Generalists2026.06 | 7.13 | |
| CoDiCategory=Generalists2026.06 | 8.67 |