OpenAI has introduced a major upgrade to ChatGPT’s image generation features, just a week after rolling out its latest GPT-5.2 model. The update significantly improves how the chatbot creates and edits images, strengthening its position in the fast-growing AI image generation market and putting fresh pressure on competitors such as Google’s Nano Banana Pro.

According to OpenAI, the new image generation system is powered by its latest flagship image model and delivers results up to four times faster than the previous version. The company says the improvements are not limited to speed alone, as the model now produces more accurate and reliable images that better follow user instructions.

Faster generation and more precise edits

OpenAI explained that the updated model performs better when creating images from scratch and when editing existing photos. It is designed to preserve important details across multiple edits, a challenge that has affected many earlier AI image tools.

Users now have finer control over how images are modified. The system supports adding or removing objects, blending and combining elements, transposing components, applying stylistic filters, and carrying out more conceptual transformations. According to OpenAI, these enhancements allow users to make targeted changes without losing the original structure or intent of the image.

The company also noted improvements in how the model interprets instructions. It said the system follows prompts more reliably than earlier versions, making it easier to produce complex compositions where relationships between objects are maintained correctly.

Text rendering has also improved. The model can now handle smaller fonts and denser blocks of text more effectively, which is particularly useful for posters, mockups, and design-focused images.

Dedicated ChatGPT Images workspace launched

Meanwhile, OpenAI has introduced a dedicated workspace for image creation inside ChatGPT. In addition to generating images within chat conversations, users can now access a separate ChatGPT Images section from the sidebar on both the web and mobile apps.

This new space includes preset prompts and visual filters designed to help users get started quickly. According to the company, these presets will be updated regularly to reflect emerging creative trends and popular use cases.

Industry observers say the move brings ChatGPT closer to standalone creative tools, making image generation more accessible for casual users and professionals alike.

Limitations remain, OpenAI admits

Despite the improvements, OpenAI acknowledged that the new model is not without limitations. According to the company, performance can vary across some languages. Support for a few artistic styles has also declined compared with the previous version.

In addition, the model can struggle to maintain the exact identity of every person when generating images that include many individuals. OpenAI says it is actively working on addressing these issues in future updates.

A step forward for AI image creation

Overall, the upgrade marks a significant step forward for ChatGPT’s creative capabilities. With faster image generation, more precise editing tools, and a dedicated workspace, users now have a more versatile platform for visual creation.

OpenAI said the update represents meaningful progress and hinted that further improvements are on the way. These include more detailed outputs, finer control over edits, and broader language support.

As competition intensifies in the AI image generation space, the latest ChatGPT Images update signals OpenAI’s intent to remain at the forefront of both conversational and creative AI tools.