The battle for supremacy among AI image generation models has intensified with the release of OpenAI’s GPT Image 1.5, which the company says delivers more accurate compositions than ever before.
The launch is in just under a month arrival Based on Google’s Nano Banana Pro tool gemini 3Which was widely considered a major step forward and was warmly welcomed by users.
OpenAI’s update is now available to most ChatGPT users globally and is available in the API as GPT Image 1.5, which brings with it a series of updates. Business and enterprise customers will have to wait for access.
These focus on the ability to better follow user instructions and speed, with OpenAI saying images can be generated up to four times faster than previous models.
Launching is also one New Images Tab Within the ChatGPT app and browser, it is being introduced as an idea generator to “spark inspiration and facilitate creative exploration”.
were upgrades announced In online posts, where comments focused on the extra level of accuracy. Editing, for example, can focus on specific details, leading to greater consistency in the output with elements such as lighting, composition, and appearance. OpenAI said it has also improved aspects of image editing, including adding, subtracting, combining, blending and transposing. Text rendering also takes a step forward, dense and small text can now be accommodated.
The post highlighted that a series of pre-defined ideas and concepts in the app and browser meant no written prompts were needed.
Fidzi Simo, CEO of Applications at OpenAI, explained the reasoning behind the update substack postWhile first experiences with ChatGPT often involved converting text prompts to images, he acknowledged that the interface was not originally designed for this and needed “space built in for visuals”, This, he added, ultimately led to the latest iteration, which is designed to work “like a creative studio,”
He promised future image-focused improvements, including increasing the use of pictures in response to prompts, aiding research, and providing comparisons.
Images update goes ahead from OpenAI deal with disney Last week it announced it would be able to use more than 200 of the most famous characters on its Sora video generation, underscoring the growing importance of visuals in AI.
