OpenAI has launched a new version of its image generation model, dubbed “ChatGPT Images 2.0,” which it says improves on its previous system and competing tools.
The updated model is being rolled out across ChatGPT, Codex, and the company’s API, bringing enhancements in creative reasoning, design output, and usability.
“Today, OpenAI is launching ChatGPT Images 2.0, a new Image Generation model with a meaningful jump over competitors and our current ImageGen 1.5,” the company said on Wednesday, April 22.
According to OpenAI, the new system is designed to handle more complex visual tasks, including generating text-heavy graphics, infographics, product mockups, and user interface concepts.
It also introduces expanded aspect ratios and higher resolutions, with API users able to generate images in up to 4K quality.
The company said paying users — including Plus, Pro, Business, and Enterprise subscribers — will have access to a more advanced version called “Imagegen Thinking 2.0,” which can refine prompts, generate multiple variations, and use tools such as Web search to improve results.
OpenAI also highlighted improvements to the overall user experience, including faster performance, better prompt suggestions, and enhanced editing and multi-output features across mobile, Web, and desktop platforms.
The rollout of ChatGPT Images 2.0 with advanced capabilities will gradually become available to paid users, according to the company.
