Tag: GPT-Image-2.5

  • OpenAI Launches ChatGPT Images 2.5 with Sketch Tool for Enhanced Editing Control

    OpenAI Launches ChatGPT Images 2.5 with Sketch Tool for Enhanced Editing Control

    OpenAI has officially launched ChatGPT Images 2.5, a major update to its image generation platform, introducing a new Sketch tool that allows users to draw directly inside a chat to guide the final image. The update, released on September 8, 2026, promises faster editing, stronger consistency across edits, and two new API models for developers.

    The Sketch tool is the headline feature of this release. Users can type “@Sketch” to open a canvas and rough out ideas—whether it’s a room layout, a clothing concept, or something easier to draw than describe. OpenAI also added new templates for common formats like flyers and product photos, along with the option to leave comments directly on an image for more targeted edits.

    According to OpenAI, editing control matters more than raw output quality in this version. Earlier versions of ChatGPT Images often lost track of a subject’s likeness after a few rounds of edits. Images 2.5 does a better job preserving people, pets, and key details, even as users apply changes to a specific part of an image without disturbing the rest. That consistency carries across longer conversations, so earlier edits stay intact instead of degrading with each new instruction.

    The new engine claims up to 50 percent lower generation latency than Images 2.0. The update rolled out to ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web on all tiers. OpenAI shared the news first with Axios.

    Alongside the ChatGPT update, OpenAI introduced two API models: GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst. Flare serves as the default option for most use cases, offering higher image quality than GPT-Image-2 at half the latency. Sunburst targets premium workflows like campaign creative and polished product imagery, where tighter editing control matters more than speed.

    OpenAI said people generate more than 3 billion images every week across ChatGPT Images and the GPT-Image API models combined. Adobe has already added the new models to Firefly, its creative AI platform, according to comments the company shared at launch. Pricing for both new API models comes in at twice the rate of GPT-Image-2.