OpenAI on September 20 announced the third generation of its text-to-image AI generator, DALL.E 3, which, based on images shared by the company, appears to be a significant upgrade over DALL.E 2. https://twitter.com/sama/status/1704547626656612692?s=20 A new useful feature of this version is that it allows users to take advantage of ChatGPT for generating prompts. This means you don't have to come up with your own prompt and can instead ask ChatGPT to come up with one. Image generators are generally more accurate with lengthy and detailed prompts. "When prompted with an idea, ChatGPT will automatically generate tailored, detailed prompts for DALL·E 3 that bring your idea to life. If you like a particular image, but it’s not quite right, you can ask ChatGPT to make tweaks with just a few words," OpenAI explained. Like the previous version, DALL.E 3 will not allow users to generate violent, adult, or hateful content. What's new is that DALL.E 3 will decline requests that ask for a public figure by name or prompts that ask to generate images in the style of a living artist. Artists can now also opt their images out from training OpenAI's future image generation models by filling out this form. These developments could address the copyright infringement concerns raised by artists. OpenAI already faces multiple lawsuits from authors. Article continues below ⬇, you might also want to read: The Authors Guild, George RR Martin, John Grisham, And Others Files Lawsuit Against OpenAI For Copyright Infringement Six Key Arguments By…
