ChatGPT may make things up when generating images, like including text with fake country names on a picture.
The new capabilities will be available Tuesday via OpenAI’s GPT-4o model
Photo Credit: Reuters
OpenAI is making it easier to edit images in ChatGPT and create visuals for work that include lengthy, legible text, potentially broadening the chatbot's appeal for businesses and everyday users.
During a livestreamed event on Tuesday, the San Francisco-based company showed how ChatGPT users will be able to refine images by having a series of conversations with the chatbot. A user might, for example, request an image of a snail in a city, then ask to change part of the backdrop and add a hat.
ChatGPT will also be able to better create images with coherent text, according to the company, making it more adept at spitting out diagrams, infographics and logos for professional uses. A person might prompt the chatbot to generate a photorealistic image of a custom menu, for instance, or a map. It will also be able to carry out more complicated instructions from users regarding the composition of an image, the company said.
OpenAI has increasingly tried to position ChatGPT as a kind of everything app that offers a search engine, voice assistant and video generator. With the latest improvements, OpenAI is trying to incorporate more advanced image features that could be applicable in a mix of personal and professional uses. It also may help ChatGPT keep ahead of chatbots from rivals like Elon Musk's xAI, which have also added image generators.
As with other AI uses, however, ChatGPT may make things up when generating images, such as including text with fake country names on a picture. In a blog post, the company said these errors can happen with less detailed prompts from users. OpenAI also said its AI can have a hard time creating small-sized text and text in non-Latin alphabets, among other issues.
It can also take up to a minute to produce images with the updated feature, according to a company blog post. During the livestream, OpenAI Chief Executive Officer Sam Altman said it takes longer because the images are more detailed.
The new capabilities will be available Tuesday via OpenAI's GPT-4o model, which is open to free and paid users. The company said it will roll out the new features over the next few weeks to software developers who use its application programming interface.
© 2025 Bloomberg L.P.
(This story has not been edited by NDTV staff and is auto-generated from a syndicated feed.)
Catch the latest from the Consumer Electronics Show on Gadgets 360, at our CES 2026 hub.