Multimodal
A model that understands or generates more than one type of data — text, images, audio, video — in a single system. Gemini can look at an image and describe it; Sora 2 turns text into video with synchronized sound. Multimodality is why modern creative workflows feel seamless: you can upload a photo, ask questions about it, and use the answer to drive an edit. Example: VAR2's smart edit suggestions use a multimodal model (Gemini) to analyze your image and propose specific, relevant edits instead of generic ones — the model literally sees what it is advising on.