11 months ago
53
OpenAI has announced its new text-to-image model, DALL·E 3, and said that ChatGPT Plus and Enterprise users will soon be able to generate images with this new model. DALL·E 3 will be integrated into ChatGPT next month.
Our new text-to-image model, DALL·E 3, can translate nuanced requests into extremely detailed and accurate images.
Coming soon to ChatGPT Plus & Enterprise, which can help you craft amazing prompts to bring your ideas to life:https://t.co/jDXHGNmarT pic.twitter.com/aRWH5giBPL
On the DALL·E 3’s official page, OpenAI said that the new text-to-image model understands significantly more nuance and detail than the company’s previous systems, allowing users to easily translate their ideas into exceptionally accurate images.
Also read: Official ChatGPT app experience is unique in both big and little ways
DALL·E 3 is currently in research preview, and will be available to ChatGPT Plus and Enterprise users in October, via the API and in Labs later this fall.
OpenAI claimed that even with the same prompt, DALL·E 3 delivers significant improvements over DALL·E 2. Below are the images generated with the prompt “An expressive oil painting of a basketball player dunking, depicted as an explosion of a nebula.” The left image was generated using the DALL·E 2 model, while the right image was created using the new DALL·E 3.
“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,” OpenAI said.
Also read: ChatGPT rivals Bard even more with its new features
Moreover, if users like a particular image, but it’s not quite right, they will be able to ask ChatGPT to make tweaks with just a few words.
“As with DALL·E 2, the images you create with DALL·E 3 are yours to use and you don't need our permission to reprint, sell or merchandise them,” the company clarified.
Also, like previous versions, the company has taken steps to limit DALL·E 3’s ability to generate violent, adult, or hateful content. OpenAi is also experimenting with a provenance classifier—a new internal tool that can help to identify whether or not an image was generated by DALL·E 3.
English (US)