OpenAI has introduced Images 2.6 in ChatGPT and the API, bringing faster image generation and new creative tools that let users turn prompts or photos into animated GIFs. The update also adds frame-level editing, adjustable animation speeds, and the ability to save and reuse reference images.
ChatGPT Images 2.6 Adds GIF Creation and Frame Editing
With Images 2.6, users can create GIFs directly in ChatGPT from either a text prompt or an uploaded photo. Users can adjust the animation speed, edit individual frames, and share the finished GIF. The update also allows users to save and tag reference images of people, pets, and characters. These references can then be reused in future creations without requiring users to upload the images again.
OpenAI says more than 4 billion images are now generated every week across ChatGPT and the API, up from more than 3 billion weekly images reported around the launch of Images 2.5 eight weeks earlier.
For developers, OpenAI has introduced GPT-Image-2.6 Flare and Sunburst, which offer 50% faster image generation through the API. Flare can generate images in as little as six seconds at low quality, while Sunburst is designed for higher-quality generation with greater consistency across edits at medium or high quality.
Image markup, which is already available in ChatGPT, is also coming to the API. This allows developers to make more targeted edits to generated images. The API update additionally introduces SVG exports and a complexity control that determines how much planning the model performs during image generation.
OpenAI Images 2.6 Availability
Images 2.6 is available in ChatGPT, ChatGPT Work, and Codex across all tiers on web, desktop, and mobile. GPT-Image-2.6 Flare and Sunburst are also available through the API.
The update gives ChatGPT users more control over image creation while expanding image generation into lightweight animation and GIF creation workflows. Images 2.6 makes image generation considerably more flexible by moving beyond static images into GIF creation, frame-level editing, and reusable visual references. The faster API models and targeted editing capabilities should also be useful for developers building image-generation workflows, while the ability to turn a personal photo into an animated GIF could make the update particularly appealing to everyday ChatGPT users.
