OpenAI has introduced ChatGPT Images 2.6, an updated image-generation system designed to improve editing precision, reduce generation time and support animated GIF creation. The update also introduces new developer tools aimed at providing greater control over AI-generated visuals.
According to the company, the latest version can generate images up to 50 per cent faster than its predecessor, allowing users to create and modify visuals with shorter processing times.
A central focus of the update is improving consistency during repeated image edits. AI image-generation tools can alter details unintentionally when users request changes to an existing visual, requiring additional prompts to restore the original appearance.
OpenAI said Images 2.6 is designed to better preserve characters, products and brand elements across multiple editing rounds. The capability is intended to help users modify selected aspects of an image without changing other important visual details.
The company has also added support for animated GIF generation, allowing users to create moving visuals without relying on separate animation software.
The feature supports applications such as animated brand mascots, social media content, reaction images and storyboards. Users can also provide sketches as starting points for animated characters.
For marketing and creative teams, the addition expands the range of visual formats that can be produced within ChatGPT, particularly for digital campaigns and social media communication.
Alongside the consumer-facing update, OpenAI has introduced two image-generation models for developers through its application programming interface (API).
GPT-Image-2.6 Flare is intended for general-purpose image generation, including posters, product imagery and other visual assets. OpenAI said the model can produce images in as little as six seconds when the quality setting is configured to low.
The second model, GPT-Image-2.6 Sunburst, focuses on higher-quality output and improved consistency during image editing, particularly at medium and high quality settings.
The API update also introduces image markup, allowing developers to identify specific areas of an image that require modification. This provides a more targeted editing process than relying solely on text instructions.
Additional capabilities include SVG export support and a complexity parameter, giving developers more control over the structure and detail of generated images.
These additions could be relevant to businesses developing automated creative workflows, where image quality, consistency and processing time affect production requirements.
OpenAI said ChatGPT Images 2.6 is available globally across all ChatGPT subscription tiers, including desktop, web and mobile access. The system is also available through Codex, while developers can access the Flare and Sunburst models through the API.
The launch expands OpenAI's image-generation capabilities as businesses increasingly explore AI tools for content creation, visual editing and digital marketing production.
Disclaimer: This article may include information derived from interviews, press releases, public statements, research, company communications and other publicly available or third-party sources. Such material may be summarised, paraphrased or contextualised for journalistic and editorial purposes. All rights in third-party content remain with their respective owners.