OpenAI announced ChatGPT Images 2, its new AI image model, on Tuesday. The upgrade focuses on creating text-heavy professional visuals like infographics and study guides. It rolls out to all ChatGPT users with generation limits based on subscription plans.
OpenAI released ChatGPT Images 2 on April 21, following the shutdown of its Sora video app a month earlier. The company positioned the model as a step toward building a super app with creative tools for personal assistants. Adele Li, product lead for ChatGPT Images, said, 'The aperture and use cases for visual intelligence just expand so broadly, and we believe that this is so critical to ChatGPT's vision for developing your own personal assistant, because your creative assistant is a huge part of who you are as an individual.' She spoke during a press briefing reported by CNET. The model excels at producing professional images with improved typography, iconography, and composition. It generates legible text in multiple languages and supports up to eight consistent images from a single prompt, such as a multi-page report. Developers can access 2K and 4K resolutions via API, though higher options remain in beta. Paying subscribers gain access to reasoning models that search the web and verify designs. ChatGPT Images 2 targets working professionals, including teachers for lesson plans and marketers for social media assets. While it handles detailed images and text better than predecessors, tests show it still struggles with non-English languages like Chinese and Hindi, according to WIRED. Editing requires regenerating images, which may consume credits faster. Safety measures include C2PA metadata for provenance and bans on abusive or illegal content, unchanged from prior models.
