%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
OpenAI is launching a new generation of image generation model GPT Image1.5 to counter Google's strong rise in the field of artificial intelligence. According to AIbase, this new model promises significant performance improvements, including more accurate instruction following, more detailed editing control, and up to four times faster image generation speed.
Speed and Accuracy Upgrade: GPT Image1.5 Fully Competes with Google
GPT Image1.5 has been made available this Tuesday to all ChatGPT users and API users. This update is the latest strategic move by OpenAI to reclaim leadership in artificial intelligence, following CEO Sam Altman's announcement of entering "red alert" status.
Previously, Google's flagship model Gemini3 and its viral image generator Nano Banana Pro performed strongly, ranking at the top of the LMArena leaderboard and beginning to erode market share. Although OpenAI launched what it called "the most advanced to date" model GPT-5.2 last week, Google still maintains the lead. It was reported that OpenAI had originally planned to release a new image generator in early January, but the release plan was accelerated in response to competition.
Comparable to Post-Production: Solving GenAI Image Consistency Issues
GPT Image1.5 is another iteration following the GPT Image1 released in April, moving the image generator from the prototype stage to more productive functions. The new model particularly emphasizes post-production features, similar to Nano Banana Pro, which provides finer editing control, thus maintaining key visual consistency (such as facial similarity, lighting, composition, and tone) during the editing process.
This is a major advancement for GenAI image tools. OpenAI specifically noted that most existing tools perform poorly in iterative editing, such as when users ask to "adjust facial expressions" or "make the light colder," the model often reinterprets the entire image, leading to inconsistent results. GPT Image1.5 aims to solve this instruction following issue.
Integration of "Creative Studio" and Visual Experience Optimization
OpenAI's Chief Executive Officer of the App, Fidji Simo, revealed in a blog post that ChatGPT now provides a "more like a creative studio" dedicated entry through the sidebar to access image features. The new image viewing and editing interface is designed to make it easier for users to create images that match their ideas or get inspiration from popular prompts and preset filters.
In addition to the new image generator, OpenAI also plans to improve the overall user experience of ChatGPT by introducing more visual elements. Simo said future search queries will display more visual elements with clear sources, which will be very useful for tasks such as unit conversion or viewing sports scores.