Tag: Sketch tool

  • OpenAI’s ChatGPT Images 2.5 Boosts Speed, Adds Sketch and Precision Editing Tools

    OpenAI’s ChatGPT Images 2.5 Boosts Speed, Adds Sketch and Precision Editing Tools

    OpenAI has launched ChatGPT Images 2.5, the latest version of its image-generation model, bringing faster generation, sharper editing controls, and creative features designed to make visual creation more intuitive and precise. Available across ChatGPT, ChatGPT Work, and Codex on desktop, mobile, and web, the update is rolling out to all subscribers at no extra cost.

    What’s New in Images 2.5?

    Three major improvements define this release: enhanced image quality, more accurate editing, and significantly faster generation. OpenAI reports that images now render up to 50% faster than the previous Images 2.0 model. Lighting appears more natural, textures are sharper, and reference photos retain their detail—even when the subject is placed in a completely different scene.

    Beyond the core model, new tools have been integrated into the ChatGPT interface:

    • Sketch Feature: Users can draw rough ideas on a canvas, then add a short description. ChatGPT transforms the sketch into a polished, finished image. This is ideal for concepts that are easier to draw than describe.
    • Editing Toolbar: Opens when an image is selected, offering five options: Markup, Comment, Remove Background, Erase, and Resize. Remove Background isolates the subject with a transparent background. Erase removes unwanted objects with a simple brush stroke.
    • Comment-Based Editing: Click directly on part of an image and type instructions like “remove this” or “make it blue.” The AI acts on only that area, leaving the rest untouched.
    • Templates: Pre-built guides for posters, merchandise, product photography, and more. Users answer a few questions and ChatGPT generates the image.
    • Prompt Sharing: Finished images can now include the exact prompt used, allowing others to reuse and adapt the concept.

    Consistency Across Multiple Edits

    Earlier versions often degraded quality after repeated edits in the same conversation. Images 2.5 addresses this by preserving important visual details and composition through multiple rounds of changes. This reliability is especially valuable for marketing teams creating campaign assets or social media batches that need to look cohesive.

    New API Models for Developers

    Developers gain access to two new API models: Flare (default, optimized for speed and lower cost, suitable for everyday tasks) and Sunburst (slower but offers tighter control for polished campaign work). Companies like Adobe, Runway, and Manus have already integrated these models into their products.

    Competitive Edge

    Early reviews place Images 2.5 ahead of Google’s Nano Banana 2 in editing accuracy and speed. Critics note that the biggest improvement is not just raw output quality but how the new editing tools transform the daily workflow of image creation.

    Overall, ChatGPT Images 2.5 refines a system that already worked well, putting more control in users’ hands. For casual users, it simplifies quick photo touch-ups, poster design, or product shots. For businesses, the choice between Flare and Sunburst offers a practical trade-off between speed and precision. The result is steady, sensible progress that makes AI image generation more practical and accessible.

  • 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.