ChatGPT images don’t roll off the tongue like Nano Banana, but OpenAI finally has an answer to Google’s uber-popular AI image editor. The company’s “new flagship image generation model” is now available on the ChatGPT Images and API under the model name GPT Image 1.5.
OpenAI has been on a tear lately, actually. The company, which was rumored to be “code red” we said following the launch of Google Gemini 3, introduced GPT-5.2 last week. Today, OpenAI continues its attack against Google’s new push in the AI space with a major update to ChatGPT graphics, which promises to produce better images, edit images more efficiently, and do so much faster.
“Whether you’re creating something from scratch or editing an image, you’ll get an output,” OpenAI said in its letter. announcement post. “Performs accurate editing while keeping detail intact, and produces images up to 4x faster.”
In addition to the update, which does not appear to have a catchy name as Google’s Nano BananaOpenAI also introduces a new graphics tab within the ChatGPT app and browser. In addition to being a dedicated space for creating images, the new ChatGPT Images also serves as a kind of discovery and idea feed to give you ideas for what to create. OpenAI says this new feature is “designed to make graphics production fun – to inspire and make old experiments effortless.”
These 6 warnings of Nano Banana Pro are wild with Gemini 3 development
In general performance, the latest update is seen as a refinement rather than something entirely new. OpenAI says the new ChatGPT Image model will be more reliable, better match user intent, and keep information more consistent across multiple results. That last one became a meme in the AI user community, and many have try 100x ChatGPT image trend to see what they came up with.
OpenAI’s announcement post includes a full list of updates with GPT Image 1.5, as well as impressive examples of the new image model at work.
Mashable Light Speed
Images of ChatGPT vs. There’s Banana
Nano Banana is an alias for Gemini 2.5 Flash Image, Google’s AI image generator. The tool has proven its potential as a fast and easy-to-use AI photo editor, and as its popularity has grown, Google has integrated it with Gemini, Google Photos, Search, and Messages. So, how do the new ChatGPT images compare?
It took all of 10 minutes, but GPT-Image-1.5 quickly took first place LMArena’s Text-to-Image leaderboardbumping the Nano Banana Pro into second place. However, real-world examples so far exist mixed lightly.
I asked both Nano Banana and the new ChatGPT Images to edit the same image, and I got very similar results.
Using the same information as the photo, I asked both models to edit the photo of my car from night to day.
First picture
Credit: Joe Hindy
While both models earn a passing grade, Google’s version looks the best in my eyes.
On the left:
Result from Nano Banana.
Credit: Joe Hindy / Google Gemini
Right:
Result from ChatGPT Images.
Credit: Joe Hindy / OpenAI
How to try the new ChatGPT Images
According to OpenAI, the update is rolling out as we talk to all users, so it should be available to try soon. In short, all you need to do is go to ChatGPT and look for the new tab Photos. You can find the tool at chatgpt.com/images. As usual, free users will have very limited access.
The new image model is also available in the OpenAI API, and you can check the values on the OpenAI website. So, developers and people with their own AI tools can start using it right away.
Disclosure: Ziff Davis, Mashable’s parent company, in April filed a lawsuit against OpenAI, alleging that it infringes Ziff Davis’ copyrights in training and using its AI programs.
