Audio-to-Image Generation on Image-Text-Audio
22.61FIDMUNI
Evaluation results
| Method | Links | |
|---|---|---|
| MUNICategory=Generalists2026.06 | 22.61 | |
| MUNI†Category=Generalists2026.06 | 22.97 | |
| MMVAECategory=Multimodal VAEs, Backbone=same as MUNI, Compute=same as MUNI2026.06 | 23.09 | |
| MoPoECategory=Multimodal VAEs, Backbone=same as MUNI, Compute=same as MUNI2026.06 | 23.57 | |
| Sound2VisionCategory=Specialists2026.06 | 25.59 | |
| FlowBindCategory=Generalists2026.06 | 28.47 | |
| CoDiCategory=Generalists2026.06 | 53.6 | |
| OmniFlowCategory=Generalists2026.06 | 97.56 |