OpenAI’s updated image generator can now pull information from the web

OpenAI is Release the latest version An AI-powered image creator with new “thinking abilities,” allowing it to search the web to help it create multiple images from a single prompt. OpenAI announced Tuesday that ChatGPT Images 2.0 can now create more “complex” images, with improvements in its ability to follow instructions, preserve details you choose, and generate text.

It’s powered by OpenAI’s new GPT Image 2 model, with new reasoning capabilities available to ChatGPT Plus, Pro, Business, and Enterprise subscribers. When you select a thought model, the chatbot’s image generator can pull information from the web, create visual explanations based on the files you upload, and “think about the structure of the image before you create it.”

ChatGPT Images 2.0 can also create up to eight images at a time with reflection enabled, all while keeping the same characters, objects, and styles in every scene. OpenAI says this would make it easier to create things like manga pages, a series of social drawings, or design plans for every room in the house.

All ChatGPT users can benefit from updates that allow ChatGPT Images 2.0 to “better capture the characteristics of images,” as well as pixel art, manga, movie stills, and other types of images. It can now create images at up to 2K resolution and in larger aspect ratios, ranging from wider formats, such as 3:1, to longer formats, such as 1:3. Not only is it better at producing English and other Latin languages; OpenAI says Images 2.0 is making “significant gains” in creating images containing text in Japanese, Korean, Chinese, Hindi and Bengali.

ChatGPT Images 2.0 is available to all ChatGPT and Codex users starting today.