OpenAI Introduces Images 2.6 With GIF Support and Faster API Models

OpenAI has rolled out Images 2.6 for ChatGPT and its API, adding GIF creation to its image generation tools. Users can now animate photos or create GIFs from text prompts, change playback speeds and edit individual frames. The update also lets them save images of people, pets and characters to use as references later. Developers, meanwhile, get two new image generation models, along with SVG exports and more control over image edits.

OpenAI Images 2.6 Features

With Images 2.6, ChatGPT users can now make GIFs using either a text prompt or an uploaded photo, OpenAI said in a press release. Once an animation is ready, they can change its speed, edit individual frames or share it. Another useful addition is the ability to save and tag reference images of people, pets and characters. This means users can bring the same subjects into new images without having to upload their photos every time.

The GIF feature can be used for different styles, including cartoon illustrations, chibi characters and 90s anime. OpenAI has shared a few examples of what users can try, such as turning themselves into a character with a ladoo for a body or creating a looping victory dance. One of the suggested prompts even asks ChatGPT to offer emoji choices before creating an animated reaction.

OpenAI says more than 4 billion images are now generated every week across ChatGPT and its API. That's a jump from the 3 billion weekly images the company reported eight weeks ago, when it introduced Images 2.5.

OpenAI is also adding two models to its API, GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst. The company says both are 50 percent faster at generating images than their predecessors. Flare is the faster of the two, producing images in as little as six seconds at low quality. Sunburst, meanwhile, is aimed at users who need better image quality and more consistent results when making edits. It works with medium and high quality settings.

The API is also getting image markup, a feature that was previously available in ChatGPT. This will let developers select specific areas of an image and make targeted changes. They can also export images as SVG files and use a new complexity setting to control how much planning goes into generating an image.

Images 2.6 is available across all ChatGPT plans on the web, desktop and mobile, as well as through ChatGPT Work and Codex. Developers can access the new Flare and Sunburst models through the API.