ChatGPT adds native GIF generation with Images 2.6 model

Native GIF creation in ChatGPT

OpenAI is simplifying the process of making custom animations by adding a built-in GIF generator to ChatGPT. Previously, creating these files often required specialized editing software or the manual task of stitching individual image frames together. Now, the tool allows users to generate smooth, looping animations directly within the chat window.

The new feature is powered by an unannounced AI model known as Images 2.6. This model enables the system to interpret simple text descriptions or existing photos to produce motion. By bringing this capability into the main interface, OpenAI is making it easier for people to create visual content without switching between different applications.

According to Android Headlines, the company is gradually rolling out this update to users of ChatGPT and Codex. The rollout covers web, desktop, and mobile platforms, ensuring that the new animation capabilities are available across different devices. This move follows the recent launch of a sticker creation tool within the same platform.

Precise animation controls

The Images 2.6 model provides users with specific controls over how their generated animations behave. Once a GIF is created, users can adjust the playback speed to change how fast the loop moves. They can also view the animation frame by frame to see the specific details of the motion being generated.

These frame controls are designed to speed up the creative process for those making visual content. Instead of guessing how an animation will look, users can make quick edits and refinements without leaving their conversation. This level of control helps ensure that the final output matches the user's original intent more closely.

The inclusion of these tools suggests a focus on usability for casual creators. By providing these options natively, OpenAI aims to reduce the friction involved in making meme loops or simple visual effects. Users no longer have to rely on third-party apps for these basic animation tasks.

Developer tools and model variants

While casual users get the GIF generator, developers are receiving dedicated API tools as part of the broader Images 2.6 deployment. OpenAI has released two specialized models to handle different types of tasks. One is called GPT-Image-2.6 Flare, which is designed for speed-focused tasks.

The second model, GPT-Image-2.6 Sunburst, is intended for projects that require a higher level of visual quality. This dual-release approach follows the strategy OpenAI first introduced with the Images 2.5 update last September. It allows developers to choose the best tool based on whether they prioritize fast generation or high-fidelity results.

These models build on the existing infrastructure that supports OpenAI's massive image production. By offering specialized versions, the company can serve a wider range of needs, from rapid prototyping to high-quality visual assets. This infrastructure supports the growing demand for AI-generated imagery across various platforms.

Growth in image production

The launch of the GIF generator comes at a time of significant growth for OpenAI's image generation capabilities. The company reports that users now create over 4 billion images every single week across ChatGPT and its developer API. This represents a substantial increase from the 3 billion weekly images reported back in September.

This rapid growth highlights the increasing popularity of AI-generated visuals for both personal and professional use. As the volume of image production climbs to new heights, OpenAI is expanding the types of media users can create. Moving from static images to looping GIFs is a logical step in this progression of visual tools.

The expansion into motion generation also follows the shutdown of the standalone Sora AI video generation app in March. While looping GIFs are much simpler than full-length video projects, they provide a way for users to experience motion generation within the main chat interface. This makes animation more accessible to a broader audience than full video production.

The future of visual content

By integrating GIF creation into the main chat window, OpenAI is transforming ChatGPT into a more flexible tool for everyday visual content. The goal is to make animation effortless for users who might not have the skills to use traditional animation software. This shift toward integrated, multi-modal tools allows for faster content creation for social media and personal projects.

The availability of frame-by-frame editing and playback controls means that the barrier to entry for creating high-quality loops is lower than ever. Users can iterate on their ideas in real-time, receiving immediate visual feedback from the AI. This interactive loop is a core part of how the Images 2.6 model functions.

As the company continues to roll out these updates, the distinction between text generation and visual creation continues to blur. With billions of images being produced weekly, the focus is shifting toward how users can manipulate those images into more dynamic formats. Native GIF support is a key part of that evolving ecosystem.