OpenAI is overhauling its image generator with a new model and redesigned interface. On Tuesday, the company announced its “new flagship image generation model,” GPT Image 1.5, which it said has a better ability to follow instructions, edit photos in specific ways, and generate results up to four times more quickly. It’s available today to all users.
The new model will be able to better “match your intent,” the company wrote in a blog post, particularly when modifying an existing photo. The changes include “more useful photo edits, more believable clothing and hairstyle try-ons, alongside stylistic filters and conceptual transformations that retain the essence of the original image.” A new dedicated Images tab in the ChatGPT sidebar will include preset filters and trending prompts and ideas, per the company.
OpenAI is positioning the new model and features as especially useful tools for enterprise, as part of its push to turn a profit under pressure from investors. And the image generation competition is heating up among AI labs, particularly after the viral success of Google’s Nano Banana.
It’s “a shift from novelty image generation to practical, high-fidelity visual creation,” the company said in a release, “turning ChatGPT into a fast, flexible creative studio for everyday edits, expressive transformations, and real-world use.” A section of the blog post also focused on how the image generation tools could be useful for work and product images. OpenAI’s CEO of Applications, Fidji Simo, wrote in a Substack post that the new model and image features work “more like a creative studio.”
