OpenAI announces DALL-E 2, its second text-to-image model

OpenAI announced DALL-E 2 on 6 April 2022. It produced higher-resolution and more coherent images from written descriptions than the 2021 DALL-E, and could edit existing pictures or generate variations of them. Access ran through an invite-only test environment.

Why it mattered DALL-E 2 set the quality bar that Midjourney and Stable Diffusion were measured against later in 2022, and drew wide public attention to text-to-image generation.