You may have heard about DALL-E 2. According to its authors, it “is a new AI system that can create realistic images and art from a description in natural language.” In concrete words, it is a machine learning model that has been trained to produce picture from text prompts. The results are astounding, and the release of the service has gathered a lot of attention from tech writers and then the general media. Rather than trying to summarize it, let me just link John Oliver’s humorous take on this trend.
Right now, the models are not available for purchase or direct use. You need to register on a waiting list to access the closed beta. Once you get access, you get some free credits (1 credit = 1 prompt) and you can buy some more if you want to. Well, for me, the wait is over 🙂! I got access to the beta yesterday.
Without further ado, and since a picture is worth a thousand words, here is one of the first images that DALL-E 2 generated for me:
