GPT Image 1.5 brings faster and precise edits
Users can create or transform images with new tools for blending, rearranging, and stylistic transformations in ChatGPT Images.
OpenAI has released a new version of ChatGPT Images, powered by the flagship GPT Image 1.5 model. The upgrade allows users to generate images from scratch or edit existing photos with greater precision, while delivering results up to four times faster.
The updated ChatGPT Images experience is now available for most users, with Business and Enterprise access coming later.
The model excels at precise edits, preserving details such as lighting, composition, and appearances while making only the requested changes. It supports transformations such as adding, subtracting, blending, and rearranging elements for practical edits and creative reimaginings.
Text rendering has also improved, allowing denser and smaller text to be handled more accurately.
A new dedicated Images workspace within ChatGPT helps users explore and experiment with preset filters, prompts, and styles. The model follows instructions reliably, keeping element relationships intact for creative projects, marketing, e-commerce, and other professional applications.
GPT Image 1.5 is also available via the API, offering improved preservation of logos and visuals, and reduced costs for image inputs and outputs by 20 per cent.
OpenAI plans to continue enhancing the system, aiming for finer-grained edits and more detailed outputs across languages, while maintaining flexibility for both individual and enterprise users.
Would you like to learn more about AI, tech and digital diplomacy? If so, ask our Diplo chatbot!
