OpenAI unveils a faster and smarter version of ChatGPT for images

Following the launch of the new GPT-5.2 release, OpenAI has revealed an upgraded version of ChatGPT for images, delivering image generation speeds up to four times faster than the previous version. This advancement further strengthens the company’s position in the rapidly evolving artificial intelligence race.

The move is aimed at direct competition with Google’s tools, particularly the Nano Banana Pro model, just as GPT-5.2 was introduced in response to Gemini 3 Pro. In a press statement, OpenAI explained that the new version adheres more closely to user intent, enabling highly precise image edits while preserving elements that were not requested to be changed—across inputs, outputs, and subsequent modifications.

The new feature opens up broader creative and editing possibilities, turning ChatGPT for images into a portable creative studio capable of performing practical adjustments and reimagining visuals in innovative ways. It supports adding, removing, merging, blending, and moving elements, ensuring that requested edits are applied without compromising the image’s core components.

The enhanced interface also introduces ready-made styles and preset ideas, allowing users to work without writing text prompts, while improving instruction accuracy and maintaining visual relationships between image elements. The updated version further shows noticeable improvements in rendering text and small faces within images.

OpenAI confirmed that the new version of ChatGPT for images is now available worldwide to all users, offering a faster and more intelligent tool for image generation and editing.