ResearchBenchmarksAudio-to-(Text+Image) Generation on triplet (text, image, audio)Audio-to-(Text+Image) Generation on triplet (text, image, audio)Follow36.79CLAP Score (A->T)FlowBind17.279622.344827.4132.4752Dec 17, 2025Evaluation resultsMethodMethodLinksCLAP Score (A->T)AIS Score (A->I)FlowBind2025.1236.7959.99OmniFlow2025.1236.0754.22CoDi2025.1218.0357.14