OpenAI continues its “Code Red” war march with a new image generation model

OpenAI is being rolled out New version From ChatGPT Images promises better follow-through, more accurate editing, and up to 4x faster image creation speeds.

The new model, called GPT Image 1.5, is available starting Tuesday to all ChatGPT users and via the Application Programming Interface (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 details OpenAI’s plans to regain its position as an AI leader after Google begins gaining market share post-crisis. Release Gemini 3its latest flagship model, and the Nano Banana Pro, the latest version of Google’s viral image generator — both of which topped LMArena leaderboards Across multiple criteria.

Google maintains its lead even after OpenAI responded to its success last week with… GPT-5.2 launchas it was promoted as the most advanced model to date Developers and everyday professional use. OpenAI was reportedly planning to release a new image generator in early January, accelerating those plans with this week’s announcement. The 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. He loves Nano Banana ProChatGPT Image provides post-production features, providing more granular editing controls to maintain visual consistency, such as facial shape, lighting, composition, and color tone across edits.

Most GenAI image tools are bad at iteration, so this would be a big step forward. When asking models about a specific change, such as “adjusting facial expressions” or “making the lighting cooler,” models often reinterpret the entire image, leading to inconsistency.

The update is not limited to just new features. ChatGPT images will now also be accessed via a dedicated entry point in ChatGPT’s sidebar that acts “more like a creative studio,” said Fidji Simo, chief applications officer at OpenAI. books In a blog post on Tuesday.

“New image viewing and editing screens make it easier to create images that match your vision or get inspired by popular prompts and pre-made filters,” Simo wrote.

In addition to the new image generator, OpenAI is introducing new ways to enhance the ChatGPT experience with more visual elements. The plan is to have search queries display more visuals with clear sources, which could be useful for tasks like converting measurements or verifying mathematical results, according to Simo.

“When you create, you need to be able to see and shape the thing you’re making. When visuals tell a better story than words alone, ChatGPT should include them,” Simo wrote. “When you need a quick answer or the next step is in another tool, it needs to be there. As we do that, we can continue to bridge the distance between what you have in mind and your ability to bring it to life.”