Modalities & Generative Media

Beyond text: image, audio, video and multimodal models, how generative media is produced, and what the outputs can and cannot do.

Learn

Modalities & Generative Media

Modalities & Generative Media

1

ConceptWhat Is Multimodal AI?Multimodal AI is AI that can process and relate information from more than one kind of data—such as text, images, audio, or video—to complete one task. A multimodal model might accept an image and a written instruction yet produce only text; “multimodal” does not mean that every data type works as both input and output.