ResearchBenchmarksText-to-(Image+Audio) Generation on Triplet (text, image, audio)Text-to-(Image+Audio) Generation on Triplet (text, image, audio)Follow26.61CLIP Score (T->I)CoDi24.63425.14725.6626.173Dec 17, 2025Evaluation resultsMethodMethodLinksCLIP Score (T->I)CLAP Score (T->A)CoDi2025.1226.6110.99FlowBind2025.1225.0229.12OmniFlow2025.1224.7112.92