OpenAI’s DALL·E 2 is capable of creating original, realistic images and art from a simple text description, combining concepts, attributes, as well as styles. Simply put, it harnesses the power of a neural network to generate images from prompts, whether it be astronauts riding horses or even sea otters in the style of Vincent van Gogh. How does DALL·E 2 work? It uses OpenAI’s language-model CLIP, which can pair written descriptions with images, to translate the text prompt into key characteristics that an image should have before running it on a neural network to generate an image.
Unlike its predecessor, DALL·E 2 can make realistic edits to existing images from a natural language caption. This means adding or removing elements while still taking shadows, reflections, and textures into account. You’re also able to take an image and create different variations of it inspired by the original. It has essentially learned the relationship between images and the text used to describe them.
- Powerful Productivity: AMD Ryzen 3 3350U delivers desktop-class performance and amazing battery life in a slim notebook. With Precision Boost, get up...
- Maximized Visuals: See even more on the stunning 15.6" Full HD display with 82.58% screen-to-body, 16:9 aspect ratio and narrow bezels
- Backlit Keyboard and Fingerprint Reader: Biometric fingerprint reader and Windows Hello sign-in options help keep your Acer PC secure
One way you can think about this neural network is transcendent beauty as a service. Every now and then it generates something that just makes me gasp,” said Ilya Sutskever, cofounder and chief scientist at OpenAI.