OpenAI has introduced a new feature in ChatGPT that allows users to create and edit animated GIFs using text prompts or uploaded photos.
By Hermes-Vector AI Desk
OpenAI has begun rolling out the ability to create animated GIFs in ChatGPT, according to reports from The Verge, UA.News, and Mezha. The new feature is being released alongside the company's Images 2.6 model and is available to all ChatGPT and Codex users across web, desktop, and mobile apps.
Users can now generate GIFs using a text prompt or by uploading a photo to the AI chatbot. Once a GIF is created, the interface provides tools to adjust the animation playback speed, edit individual frames, and share the finished animation.
In a demonstration shared by OpenAI, the chatbot responded to the prompt, “can you make a gif of a cat dancing?” by producing an animation that allowed the user to view it frame by frame and change the playback speed. Previously, ChatGPT could not natively generate GIFs in a single step; users had to generate separate images and use external tools to stitch them together.
Technical details from a code review of OpenAI’s Codex repository indicate that the capability supports animations consisting of between 2 and 16 frames. The default setting is 9 frames, with each frame displayed for 200 milliseconds. The code also supports spritesheet-based edits and maintains a still preview while the animation is generating.
Alongside the GIF functionality, the Images 2.6 update is expected to enable faster image generation in ChatGPT, according to OpenAI. For developers using the API, OpenAI is launching two new models: GPT-Image-2.6 Flare, which is tuned for speed, and GPT-Image-2.6 Sunburst, which is designed for higher-quality image generation. These variants follow the GPT Image series that succeeded DALL·E as OpenAI’s image engine.
OpenAI reports that users currently generate over 4 billion images per week across ChatGPT and its API. This is an increase from the 3 billion images per week the company reported in September.
This release follows the launch of ChatGPT Images 2.5 on September 8, 2026, which OpenAI says improved image generation speed by up to 50% and added features like direct sketching. While the current GIF tool is limited to short loops, anticipated future additions to the model include support for 4K resolution and markup-based edits, where users annotate an image to indicate desired changes.
On the developer side, the GIF output capability currently sits behind a feature flag that is disabled and has not yet been publicly documented in the API.
Sources
This article was drafted with AI assistance and checked against the sources above. Company claims are reported as claims. Cover image is AI-generated.
The day's checked news, by email
One short email a day with the top stories. Free, and you can unsubscribe in one click.
Or follow for the latest news:
No comments yet. Start the discussion.
DevRev has announced the integration of OpenAI's GPT-6.1 Sol into its Computer and Operator platforms to provide autonomous enterprise IT self-service.
Starting in early 2027, Google will disable Gemini and other AI tools by default for K-12 student accounts, requiring administrators to manually enable them.
