A New Text-to-Art Engine

DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language. It was announced by OpenAI in April 2022. The name is a portmanteau of „WALL-E“ and „Salvador Dalí“. The website openai.com says more about the program: „DALL·E 2 can create original, realistic images and art from a text description. It can combine concepts, attributes, and styles.“ (Website openai.com) Moreover, it is able to „make realistic edits to existing images from a natural language caption“ and to „add and remove elements while taking shadows, reflections, and textures into account“ (Website openai.com). Last but not least, it „can take an image and create different variations of it inspired by the original“ (Website openai.com). The latter form of use is shown by variations of the famous painting „Girl with a Pearl Earring“ by Johannes Vermeer. The website says about the principle of the program: „DALL·E 2 has learned the relationship between images and the text used to describe them. It uses a process called ‚diffusion,‘ which starts with a pattern of random dots and gradually alters that pattern towards an image when it recognizes specific aspects of that image.“ (Website openai.com) DALL·E mini is a slimmed down version of the powerful program, with which you can gain a first insight. The six images below were automatically generated by DALL·E mini from the text „A young female astronaut with long hair on the flight to Mars“. In total, 9 suggestions were made in a few seconds. Overall, this is a fascinating and valuable project. From the perspective of information ethics and the philosophy of technology, many questions arise.

Fig.: A young female astronaut with long hair on the flight to Mars (Photo: DALL·E mini)