About us
Stay in touch
An OpenAI model released in January 2021 that learned to match images with text from about 400 million captioned pictures. Artists used it to steer image generators with words, which led directly to text-to-image AI.
Artists Ryan Murdock and Katherine Crowson started combining GANs with other technologies like CLIP to create the very first openly available text-to-image models.
Peter Bauman, Ian Goodfellow on Inventing GANs