Just like OpenAI's DALL·E 2, you type in a prompt, and it will do its best to make pictures that match it. Most of the pictures that Craiyon creates are pretty abstract and nonsensical.

OpenAI has a new AI Text-to-Image model based on GPT-3 called DALL-E 2. It is capable of turning a text description into a unique image or work of art that has never been seen before. Putin says ...

However, [Micael Widell] shows something in a recent video that might be the best use we’ve seen yet of DALL-E 2. Instead of concocting new photos, you can apparently use the same technology for ...