OpenAI is adding reasoning and web search to its ChatGPT Images 2.0 image generator. The model can now create up to eight consistent images from a single prompt and handles text in general, and especially in non-Latin scripts, significantly better.
Update:
OpenAI's new image model is official. ChatGPT Images 2.0 runs on the new GPT Image 2 model and shares the same core capability as Google's Nano Banana Pro: the model "thinks" before it generates, spending more or less time reasoning depending on the selected mode, and can even search the web during that process.
According to a blog post from the company, this should lead to greater variety and accuracy in generated images. Extended outputs with thinking are only available to ChatGPT Plus, Pro, and Business users, though.
With thinking mode enabled, ChatGPT Images 2.0 can generate up to eight images at once from a single prompt. Characters, objects, and styles are supposed to stay consistent across all scenes. OpenAI lists page-long mangas generated from a single picture and a text prompt, series of social media graphics, and design plans for different rooms in a house as example use cases.
