OpenAI has introduced a new GPT Image 1.5 model and a redesigned interface. The company says it follows text instructions much better, allows for more precise photo editing, and produces results up to four times faster. It is available to all users and via an API.
OpenAI has introduced a new GPT Image 1.5 model and a redesigned interface. The company says it follows text instructions much better, allows for more precise photo editing, and produces results up to four times faster. It is available to all users and via an API.
This is a direct response to the challenge from Google Gemini. Earlier, Sam Altman declared a “code red” internally due to Google’s success. The flagship Gemini 3 and the Nano Banana Pro generator currently dominate the LMArena rankings, so the release of GPT Image 1.5 is a strategic move by OpenAI to regain its dominant position in the market.
“The new model will be able to better ‘respond to your intent,’” the company notes in its blog post, especially when editing existing photos. The changes include “more useful editing tools, more realistic fitting of clothes and hairstyles, as well as stylistic filters and conceptual transformations that preserve the essence of the original image.”
A separate "Images" tab will appear in the ChatGPT sidebar, where pre-installed filters, popular queries, and ideas will be available.
OpenAI positions the new model and features as particularly useful tools for business.
According to OpenAI's general manager of applications, Fiji Simo, the new model and image features work "more like a creative studio," The Verge writes .
“With updated viewing and editing tools, it will be easier for users to bring their ideas to life or find inspiration among trending prompts and preset filters,” Simo wrote.
