OpenAI launches faster, smarter ChatGPT Images

OpenAI has rolled out a new version of its image generation tool, ChatGPT Images, promising faster speeds, improved instruction-following, and more precise editing. The updated model, GPT Image 1.5, is available from Tuesday to all ChatGPT users and via the API.

The tool allows users to make granular edits to uploaded images, such as adjusting facial expressions, changing lighting, or transforming styles — from photorealistic to watercolour — without losing important details. It can render dense text, multiple faces in one frame, and maintain composition and colour consistency across iterative edits.

“The new image viewing and editing screens make it easier to create images that match your vision or get inspiration from trending prompts and preset filters,” wrote Fidji Simo, OpenAI’s CEO of applications in a blog post. The update introduces a dedicated Images workspace in the ChatGPT sidebar, functioning like a mobile and web-based creative studio that makes exploring, generating, and editing images faster and more intuitive.


OpenAI noted that instruction-following has been improved, enabling more precise original compositions, concept transformations, and stylistic changes while preserving the key elements of the image. The tool also supports creative workflows like adding, subtracting, combining, blending, and transposing image elements with minimal manual effort.

The update is part of OpenAI’s broader strategy to position ChatGPT as an all-in-one platform, including AI search, voice, image, and video capabilities. GPT Image 1.5 arrives amid growing competition from Google’s Gemini 3 and Nano Banana Pro, as well as other AI image tools such as xAI’s Grok, reflecting a broader push for production-ready, user-friendly generative AI tools.

The new ChatGPT Images 1.5 is available globally for individual users today, with business and enterprise access to follow. OpenAI says this marks a significant step in delivering professional-grade image generation with faster speeds, richer outputs, and enhanced creative flexibility, bringing users closer to turning their visual ideas into reality.