multimodal model
an AI model that understands images as well as text
A multimodal model takes more than one kind of input, usually text and images, and sometimes audio or video. It can describe a picture, read text in it, or answer questions about it. This lets software act on what is shown on a screen, not only on written data.
Think of it as
A colleague you can show a photo to, instead of having to describe it in words.
Ideas that use this term