Models explained: DALL-E 2

VQ-VAE is a powerful technique for learning discrete representations of complex data types like images, video, or audio. This technique has played a key role in recent state of the art works like OpenAI’s DALL-E and Jukebox models.

As part of our DALL·E 2 research preview, more than 3,000 artists from more than 118 countries have incorporated DALL·E into their creative workflows. The artists in our early access group have helped us discover new uses for DALL·E and have served as key voices as