OpenAI is revamping its image generator with a fresh model and a redesigned interface. On Tuesday, the company announced its “new flagship image generation model,” GPT Image 1.5, which it says provides improved ability to follow instructions, edit photos in specific ways, and generate results up to four times faster. It is available to all users today.
The fresh model will be able to better “fit your intentions,” the company said in a statement blog postespecially when modifying an existing photo. The changes include “more useful photo edits, more reliable clothing and hair try-ons, and styling filters and conceptual transformations that preserve the essence of the original image.” A fresh, dedicated Images tab in the ChatGPT sidebar will feature pre-built filters as well as trending tips and ideas, according to the company.
OpenAI positions the fresh model and functions as tools that are particularly useful for enterprises as they strive to make a profit under investor pressure. Competition for image generation in AI labs is heating up, especially after the viral success of Google’s Nano Banana.
“It is a “transition from novel image generation to hands-on, high-fidelity image creation,” the company said in a release, “transforming ChatGPT into a fast, flexible creative studio for everyday editing, expressive transformations, and real-world applications.” Part of the blog post also focused on how image generation tools can be useful for work and product photos. OpenAI Applications General Manager Fidji Simo wrote in: Fasting at the stake that the fresh model and imaging features work “more like a creative studio.”