OpenAI has introduced a significant update to edit images in ChatGPT and create visuals for work that include lengthy, legible text.
During a live-streamed event on Tuesday, March 25, 2025, OpenAI announced that ChatGPT will now be able to create improved images with coherent text.
Users might prompt the model to generate a photorealistic image of a customised menu.
It will be capable of carrying out more complex instructions from users regarding the composition of a photo, OpenAI stated.
ChatGPT manufacturer is integrating cutting-edge image features that could be applicable in a mix of personal and professional uses.
The features assists ChatGPT to keep ahead of chatbots from competitors such as Elon Musk’s xAI, which has added image generators.
As with other AI uses, ChatGPT may create things when generating images, including text with fake country names on a picture, and more.
In a blog post, the company stated that these errors can have a hard time generating small-sized text and text in non-Latin alphabets, and other issues.
With this latest feature, users can generate images within a couple of minutes.
Notably, the advanced capabilities will be available via OpenAI’s GPT-4o model, for free and paid users in the near future.
