Text-to-Audio Generation on RiTTA Count OOD (test)
2.18KL DivergenceTangoFlux-RAG
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| TangoFlux-RAGbase_model=TangoFlux2025.11 | 2.18 | 37.7 | 5.1 | 7.3 | 43.7 | |
| TangoFlux2025.11 | 2.22 | 46.8 | 7.3 | 7 | 43.3 | |
| AudioLDM2-RAGbase_model=AudioLDM22025.11 | 2.71 | 35.2 | 4.4 | 8.5 | 34.2 | |
| AudioLDM22025.11 | 2.81 | 38.5 | 7.7 | 7.4 | 29 |