OpenAI has released a new version of ChatGPT Images, promising significant improvements. The updated model, called GPT Image 1.5, offers better instruction-following, more precise editing, and image generation speeds up to four times faster. It became available to all ChatGPT users and via the API starting Tuesday.
This launch marks the latest move in OpenAI’s competitive race with Google’s Gemini. It follows a leaked internal memo from OpenAI CEO Sam Altman last month that declared a “code red,” detailing plans to regain its position as the AI leader. Google had begun taking market share after releasing its latest flagship model, Gemini 3, and the new version of its viral image generator, Nano Banana Pro. Both Google models have topped the LMArena leaderboard across multiple benchmarks.
Google maintained its lead even after OpenAI responded last week with the launch of GPT-5.2, which was pitched as its most advanced model for developers and professional use. OpenAI had reportedly been planning a new image generator release for early January but accelerated those plans with this week’s announcement. Its previous image model, GPT Image 1, was released in April.
GPT Image 1.5 arrives as image and video generators evolve from prototypes into tools with production-ready capabilities. Similar to Nano Banana Pro, ChatGPT Images now offers advanced post-production features. These provide more granular edit controls to maintain visual consistency across changes, such as preserving facial likeness, lighting, composition, and color tone.
Most generative AI image tools struggle with iteration, often reinterpreting an entire image when asked for a specific change, which leads to a lack of consistency. This update aims to solve that problem. The improvements are not limited to new features. ChatGPT Images will also be accessible via a dedicated entry point in the ChatGPT sidebar designed to work more like a creative studio.
Fidji Simo, OpenAI’s CEO of applications, explained in a blog post that the new image viewing and editing screens make it easier to create images that match a user’s vision or to draw inspiration from trending prompts and preset filters.
Beyond the new image generator, OpenAI is introducing ways to enhance the ChatGPT experience with more visual elements. The plan is for search queries to display more visuals with clear sources, which could assist with tasks like converting measurements or checking sports scores.
Simo wrote that when creating, users should be able to see and shape what they are making. When visuals tell a story better than words alone, ChatGPT should include them. The goal is to keep closing the distance between what is in a user’s mind and their ability to bring it to life.