A subfield of artificial intelligence that uses generative models to generate text, images, videos, audio, computer code, or other forms of digital data.
The 2023 review 'ChatGPT is not all you need' surveys the plethora of large generative models published in the preceding two years.
It maps the modality landscape: text to images (DALL-E 2), text to 3D (DreamFusion), images to text (Flamingo), text to video (Phenaki), and text to audio (AudioLM).