What is Dall-E?

Dall-E is an artificial intelligence program that creates images from textual descriptions, revealed by OpenAI on January 5, 2021. It uses a 12-billion parameter training version of the GPT-3 transformer model to interpret the natural language inputs and generate corresponding images. Dall-E is capable of creating images of common concepts like “a cat sitting on a chair” or “a person riding a bike”, as well as more outlandish concepts like “a giant robot made of smaller robots”. Dall-E works by first representing the textual description as a vector in a high-dimensional space. This vector is then compared to a set of pre-generated images, and the one with the closest vector is chosen as the output. If no match is found, Dall-E will generate a new image from scratch. Dall-E is still in its early stages, and is not yet perfect. However, it shows great promise for the future of artificial intelligence and image generation.

Promt-1

Portrait, stunningly beautiful medievyadult men face, dark fantasy style, Medieval castle background, aurora sky , cinematic light, digital art, unreal engine, by Craig Mullins, Edward Burne Jones, Karol Bak, Peter Mohrbacher, Waterhouse, whimsically designed, unreal engine, –w 832 –h 1280.