OpenAI launched one new version of ChatGPT Images that promises better step-by-step instructions, more precise editing, and up to 4x faster image creation speed.

The new model, called GPT Image 1.5, will be available starting Tuesday to all ChatGPT users and through the API. This is the latest development in the Google Gemini competition after OpenAI CEO Sam Altman last month declared it a “code red” in a leaked internal memo. The memo details OpenAI’s plans to regain its position as the AI ​​leader after Google began taking market share after the release of Gemini 3its latest flagship model, and the Nano Banana Pro, the latest version of Google’s viral image generator — both top the LMA’s leaderboard in many benchmarks.

Google continued its lead even after OpenAI responded to its success last week in launch of GPT-5.2which positions it as the most advanced model for developers and daily professional use. OpenAI is reportedly planning to release a new image generator in early January, accelerating plans with this week’s announcement. The last release of the image model was GPT Image 1 in April.

GPT Image 1.5 comes as image and video generators progress beyond prototypes and gain more production-ready capabilities. as Nano Banana ProChatGPT Image offers post-production features, which provide more granular editing controls to maintain visual consistency, such as facial features, lighting, composition, and color tone in edits.

Most GenAI image tools are not good at rendering, so this is a big step. Asked for a specific change, such as “adjusting the facial expression” or “making the lighting cooler,” the models will often re-render the entire image, leading to a lack of consistency.

The update isn’t just about new features. ChatGPT images can now also be accessed through a dedicated entry point in the ChatGPT sidebar that functions “more like a creative studio,” Fidji Simo, OpenAI’s CEO of applications, WRITES in a blog post Tuesday.

“New image viewing and editing screens make it easy 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 introduces new ways to improve the ChatGPT experience with more visual elements. The plan is to create search queries that display more visuals with clear sources, which can help with tasks such as converting measurements or checking sports scores, according to Simo.

“When you’re creating, you need to see and shape what you’re creating. If visuals tell a story better than words alone, ChatGPT should include them,” Simo wrote. “If you need a quick answer or the next step resides in another tool, it should be right there. As we do this, we can continue to close the gap between what you have in mind and your ability to bring it to life.”