OpenAI has launched an enhanced iteration of ChatGPT Images, delivering improved adherence to user instructions, more accurate editing tools, and image generation speeds up to four times faster. The new model, named GPT-Image-1.5, became available to all ChatGPT users and through the API starting Tuesday.

This release marks the latest move in an escalating rivalry with Google’s Gemini. Last month, OpenAI CEO Sam Altman described a “code red” in an internal memo, outlining plans to reclaim the company’s position as the AI frontrunner. Google had gained market share following the debut of its latest flagship model, Gemini 3, and Nano Banana Pro—the newest version of its popular image generator. Both Google models have led the LMArena leaderboard across several benchmarks.

Even after OpenAI introduced GPT-5.2 last week—promoted as its most sophisticated model for developers and professional use—Google has maintained its lead. OpenAI had originally planned a new image generator for early January but moved up the timeline with this week’s announcement. The previous image model, GPT-Image-1, was released in April.

GPT-Image-1.5 arrives as image and video generators evolve from experimental prototypes toward production-ready tools. Similar to Nano Banana Pro, ChatGPT Images now includes advanced post-production features, offering finer edit controls to preserve visual consistency. Users can maintain elements like facial likeness, lighting, composition, and color tone across successive edits.

Most generative AI image tools struggle with iterative changes, so this upgrade represents significant progress. When asked to make specific adjustments—such as “adjust the facial expression” or “make lighting colder”—many models tend to reinterpret the entire image, breaking visual continuity.

Beyond new capabilities, ChatGPT Images is now accessible through a dedicated entry point in the ChatGPT sidebar, designed to function “more like a creative studio,” according to Fidji Simo, OpenAI’s CEO of applications. In a Tuesday blog post, Simo noted, “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.”

Alongside the image generator, OpenAI is introducing more visual enhancements to the ChatGPT experience. The plan includes displaying richer visuals with clear sources in response to search queries, which could assist with tasks like converting measurements or checking sports scores. Simo explained, “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.”

She added, “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.”