OpenAI is reportedly rolling out a feature that lets users generate animated GIFs directly inside ChatGPT, according to The Verge. The tool is said to run on a new image-generation model called Images 2.6, which OpenAI has not yet formally introduced through its usual product announcements.

GIF creation inside ChatGPT
Users can describe an animation in plain English or upload an existing photo and ask ChatGPT to bring it to life. After the GIF is created, they can change playback speed, inspect individual frames, make edits, and share the finished animation.
OpenAI demonstrated the feature with a simple prompt: 「can you make a gif of a cat dancing?」 The reported interface includes controls for changing animation speed and reviewing the GIF frame by frame.
Decrypt said it tried generating GIFs with ChatGPT, but the feature was not available on its accounts at the time of testing. In that test, the model produced a series of frames, but not the animation itself.
The rollout appears to be gradual, so some users may need to wait before the feature reaches their accounts.
Images 2.6 is part of a broader update
The Verge reported that the GIF maker is part of a wider Images 2.6 update that promises faster image generation. The publication said OpenAI is bringing the model to ChatGPT and Codex users across web, desktop, and mobile platforms.

Developers are also set to receive two new API models: GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst. The first is designed for faster generation, while the second targets higher-quality output. OpenAI has not published a standalone announcement detailing the model’s capabilities, and Decrypt said it could not independently test performance.
How it fits with recent OpenAI releases
The update follows the September release of ChatGPT Images 2.5, which introduced sharper details, more precise editing, and generation speeds up to 50% faster than its predecessor.
Decrypt also referenced its earlier testing of Images 2.5 against Google’s Nano Banana 2 across six categories, where each model won three. In that comparison, OpenAI’s model stood out in illustration quality and improved on the oversharpening issues seen in earlier versions, though it still made mistakes when rendering text.
The move into GIF generation comes months after OpenAI shut down Sora, its standalone AI video-generation app, in March. Animated GIFs are much simpler than the videos Sora generated, but the new feature brings a form of motion generation directly into ChatGPT without requiring a separate app.
OpenAI has not provided a specific date for when GIF generation will reach every ChatGPT account.


