OpenAI, an AI research and deployment company with the mission to ensure that artificial intelligence benefits all of humanity, has recently created an AI that lets you create bizarrely cute images from scratch—based on your own written descriptions.
Titled DALL·E, this AI has been programmed and trained to generate images from captions, using a system of datasets of text-image pairs. So basically all you need to do is come up with a written description, enter it on the program, and then wait for DALL·E to generate visual results. So far, the weirder the descriptions have been, the better results achieved.
“We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language. We recognize that work involving generative models has the potential for significant, broad societal impacts. In the future, we plan to analyze how models like DALL·E relate to societal issues like economic impact on certain work processes and professions, the potential for bias in the model outputs, and the longer term ethical challenges implied by this technology.”
Some of these examples showcased on the website, like “an armchair in the shape of an avocado” and “an illustration of a baby daikon radish in a tutu walking a dog” exhibit the breadth of this new technology. We can only imagine what this tool can help us create in terms of visualizing things that would’ve otherwise been impossible to put together. This tool is a prime example of how we can use AI to our advantage, and use its forces for good rather than evil.
Head over to their openai.com to try it out for yourself and see all the magnificent and bizarre creatures that you can now create.
Photos via OpenAI (image prompt of a baby daikon radish in a tutu walking a dog)