Photo: openai.com
OpenAI has introduced an updated version of ChatGPT Image powered by its flagship GPT-5.2 model. The update brings faster image generation, more precise editing, and a dedicated “Images” section in the ChatGPT interface. The new model is already rolling out to all users and is available via the API as GPT Image 1.5.
According to OpenAI, the updated ChatGPT Image can generate images up to four times faster than before. The model also adheres more closely to user instructions and edits only the requested elements in existing images, while preserving lighting, composition, and people’s appearance. GPT-Image-1.5 supports adding, merging, and removing objects, as well as other transformations. Text rendering within images has also been improved, with small and dense text displayed more accurately.
Alongside the model update, OpenAI has launched a new “Images” section in ChatGPT. Available in both the web version and the mobile app, it includes built-in filters and ideas to help users generate visuals more easily.
“GPT Image 1.5 produces high-quality images with precise rule adherence, while maintaining composition, lighting, and fine details,” said Hila Gatt, head of AI research and data science at Wix.
OpenAI believes the potential of image generation is only beginning to unfold. The company describes this update as an important milestone that will unlock even more capabilities, from more detailed editing to richer, more nuanced results across multiple languages.
