Multimodal
A property of a model that can take in or produce more than one kind of media, such as text, images, audio or video.
Not all models are able to generate images and audio.
Related
- Interface The way a person interacts with an AI system: free text, document and image upload, audio, buttons and forms, in a chat window, terminal or IDE.
How it connects
- Multimodal is a property of some LLM