OpenAI continues on its ‘code red’ warpath with new image generation model

OpenAI is rolling out a new version of ChatGPT Images that promises better instruction-following, more precise editing, and up to 4x faster image generation speeds.

The new model, dubbed GPT-Image-1.5, is available starting Tuesday to all ChatGPT users and via the API. It’s the latest escalation in the competition with Google’s Gemini after OpenAI CEO Sam Altman last month declared a “code red” in a leaked internal memo. The memo detailed OpenAI’s plans to regain its position as the AI leader after Google had begun to take market share following the release of Gemini 3, its latest flagship model, and Nano Banana Pro, the newest version of Google’s viral image generator – both of which have topped the LMArena leaderboard across multiple benchmarks. 

Google maintains its lead even after OpenAI responded to its success last week with the launch of GPT-5.2, pitching it as its most advanced model yet for developers and everyday professional use. OpenAI had reportedly been planning to release a new image generator in early January, accelerating those plans with this week’s announcement. Its last image model release was GPT-Image-1 in April. 

GPT-Image-1.5 arrives as image and video generators advance beyond prototypes and gain more production-ready capabilities. Like Nano Banana Pro, ChatGPT Images offers post-production features, providing more granular edit controls to maintain visual consistency, like facial likeness, lighting, composition, and color tone across edits. 

Most GenAI image tools are bad at iteration, so this would be a huge step up. Asked for a specific change, like ‘adjust the facial expression’ or ‘make lighting colder,’ models will often reinterpret the entire image, leading to a lack of consistency. 

The update isn’t just about new features. ChatGPT Images will also now be accessible via a dedicated entry point in the ChatGPT sidebar that works “more like a creative studio,” Fidji Simo, OpenAI’s CEO of applications, wrote in a blog post Tuesday. 

“The new image viewing and editing screens make it easier to create images that match your vision or get inspiration from trending prompts and preset filters,” Simo wrote.

On top of the new image generator, OpenAI is introducing new ways to improve the ChatGPT experience with more visual elements. The plan is to make search queries display more visuals with clear sources, which could be helpful for tasks like converting measurements or checking sports scores, per Simo. 

“When you’re creating, you should be able to see and shape the thing you’re making. When visuals tell a story better than words alone, ChatGPT should include them,” Simo wrote. “When you need a quick answer or the next step lives in another tool, it should be right there. As we do this, we can keep closing the distance between what’s in your mind and your ability to bring it to life.”