Discovered: Jan 5, 2021. Simon Willison: DALL·E: Creating Images from Text (via HN) “DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions, using a dataset of text–image pairs.”. The examples in this paper are astonishing—“an illustration of a baby daikon radish in a tutu walking a dog” generates exactly that. <— does it work for anybody or is it paywalled? Sounds like access is limited to a “lucky few”. “AI” segregation for tech elites for the loss!

Leave a comment on github