OpenAI has rolled out GPT-Image-1.5, a significant upgrade to its ChatGPT image generation capabilities, promising up to four times faster image creation, superior instruction-following, and more precise editing. This launch marks a critical escalation in the fierce AI rivalry with Google, particularly after OpenAI CEO Sam Altman's recent "code red" declaration in an internal memo.
Escalating Competition in the AI Landscape
The release comes as OpenAI continues its aggressive push to regain market leadership, following an internal memo from Altman last month that outlined plans to counter Google's growing dominance. Google had recently captured significant market share with the launch of its flagship model, Gemini 3, and the latest version of its viral image generator, Nano Banana Pro. Both models have notably topped the LMArena leaderboard across various benchmarks.
Despite OpenAI's counter-move last week with the launch of GPT-5.2, pitched as its most advanced model yet for developers and everyday professional use, Google has maintained its lead. OpenAI reportedly accelerated the release of GPT-Image-1.5, initially planned for early January, to respond to the intensifying competition. Its previous image model, GPT-Image-1, was released in April.
GPT-Image-1.5: Enhanced Features and User Experience
GPT-Image-1.5 arrives at a time when AI image and video generators are evolving rapidly from prototypes to production-ready tools. Similar to Google's Nano Banana Pro, ChatGPT Images now offers advanced post-production features. These include granular edit controls that ensure visual consistency across edits, such as maintaining facial likeness, lighting, composition, and color tone.
This capability represents a substantial leap forward, as many generative AI image tools struggle with iterative editing. Often, when users request a specific change like 'adjust the facial expression' or 'make lighting colder,' existing models tend to reinterpret the entire image, leading to a frustrating lack of consistency. GPT-Image-1.5 aims to resolve this core challenge, as demonstrated by examples showcasing its improved instruction-following for precise visual adjustments.
A More Visual and Intuitive ChatGPT
Beyond its technical enhancements, the update also introduces a revamped user experience. 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, who wrote in a blog post on 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.
OpenAI's broader vision includes integrating more visual elements into the ChatGPT experience, aiming for search queries to display richer visuals with clear sources. This could benefit tasks like unit conversions 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 emphasized. "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."
