OpenAI Launches ChatGPT Images 2.5 With Enhanced Features

OpenAI has released ChatGPT Images 2.5, an updated image generation model that promises sharper details, faster creation times, and more precise editing capabilities. The release introduces new features for users and enhanced models for developers, with early integration by Adobe. The new version, rolled out on September 8, 2026, offers significant enhancements over its predecessor, Images 2.0. OpenAI states that Images 2.5 produces more natural lighting and richer textures, is better at preserving subjects in reference photos, and follows editing instructions more reliably across multiple turns. Image generation latency has been reduced by up to 50%, allowing users to generate images and refine concepts more quickly. For ChatGPT users, the update includes a new Sketch feature that enables drawing directly within the application to serve as a reference for image generation. Additionally, templates are now available for popular image formats, and users can place comments directly on images for more focused editing. A notable social feature allows users to share the prompts used to create images, enabling others to run those prompts with their own details and photos.