ChatGPT Is Getting a GIF Maker Powered by OpenAI's Unannounced Images 2.6 Model

In brief

• ChatGPT is gaining native GIF generation from text prompts or uploaded photos.
• The feature runs on Images 2.6, a new OpenAI model that has yet to receive a standalone official announcement.
• The rollout is gradual, and most users won't be able to access the feature yet.

The internet may soon have an unlimited supply of AI-generated dancing cats, courtesy of ChatGPT.

OpenAI is rolling out a feature that lets users generate animated GIFs directly inside ChatGPT, according to The Verge. The feature reportedly comes powered by its new image-generation model called Images 2.6, which OpenAI has yet to formally introduce through its usual product announcements.

Users can describe an animation in plain English or upload an existing photo and ask ChatGPT to bring it to life. Once the GIF is generated, they can adjust its playback speed, inspect individual frames, make edits, and share the finished animation.

OpenAI demonstrated the capability with a simple request: “can you make a gif of a cat dancing?” The resulting interface reportedly includes controls to change animation speed and examine the GIF frame by frame.

We tried generating GIFs using ChatGPT, but the feature was not available on our accounts at the time of testing. In our interaction, the model generates a series of frames, but not the animation.