Microsoft-owned OpenAI has launched an upgraded version of its text-to-image tool -- DALL·E 3--, that uses AI chatbot ChatGPT.

COMMERCIAL BREAK
SCROLL TO CONTINUE READING

DALL·E 3 is presently in research preview, and will be available to ChatGPT Plus and Enterprise customers in October, via the API and in Labs later this fall.

"DALL·E 3 is built natively on ChatGPT, which lets you use ChatGPT as a brainstorming partner and refiner of your prompts. Just ask ChatGPT what you want to see in anything from a simple sentence to a detailed paragraph," Open AI said on Wednesday.

When prompted with an idea via ChatGPT, it will automatically generate tailored, detailed prompts for DALL·E 3 that will 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.

"DALL·E 3 understands significantly more nuance and detail than our previous systems, allowing you to easily translate your ideas into exceptionally accurate images," the company mentioned.

As with DALL·E 2, OpenAI said that the images users create with DALL·E 3 will be theirs to use and they don't need the company's permission to reprint, sell or merchandise them.

Moreover, the company stated that they have taken steps to limit DALL·E 3's ability to generate violent, adult, or hateful content like previous versions.

DALL·E 3 is also programmed to reject requests for images in the style of a living artist. Creators can now choose to exclude their images from training OpenAI's future image generation models.