ChatGPT Learns to Make GIFs, and the Dancing Cat Is Already in the Demo
Anyone who has asked an AI chatbot for a quick animated reaction has probably been handed a pile of still frames instead.
OpenAI is trying to close that gap.
The company has added GIF creation to ChatGPT as part of its new Images 2.6 release, so a request for an animation can now be completed in one step.
For its showcase, OpenAI chose a request that surprised nobody:
"can you make a gif of a cat dancing?"
What Can Users Do With the New GIF Tool?
People can describe an animation in plain English, or upload an existing photo and ask ChatGPT to bring it to life.
Once the GIF is ready, the chat window offers controls to change the playback speed and to look through the animation frame by frame.
Users can also edit individual frames and share the finished result.
OpenAI says the feature suits more than memes.
It pointed to animated brand mascots, product shots turned into loops, social reactions and campaign material.
It also mentioned animated storyboards that let creators test how a character moves before committing to full video production.
Why Did ChatGPT Struggle With GIFs Before?
Until now, ChatGPT could not produce a GIF natively in a single step.
Users who tried usually ended up with a set of separate images and had to stitch them together elsewhere.
The new tool removes that extra work by building the animation inside the conversation.
The timing is also notable.
OpenAI shut down Sora, its standalone AI video app, in March.
GIFs are far simpler than the footage Sora produced, but the new feature does bring a basic form of motion into ChatGPT without a separate application.
How Fast Is the New Images 2.6 Model?
OpenAI launched Images 2.6 on 4 November 2026, and says it generates images 50% faster than the previous version.
The model is available across all subscription tiers on desktop, mobile and web, and works in both ChatGPT and Codex.
Developers get two new API models.
GPT-Image-2.6 Flare is built for speed and, according to OpenAI, can produce an image in as little as six seconds at low quality.
It is also said to improve layout for posters and product imagery.
GPT-Image-2.6 Sunburst is aimed at greater detail, precision and consistency across repeated edits.
Both names carry over from GPT Image 2.5, which arrived on 8 September 2026.
OpenAI has not published independent test results for these speed and quality figures, so they remain the company's own claims.
What Else Is Changing for Everyday Users and Developers?
Another addition is reusable reference images.
Users can save pictures of themselves, their pets or favourite characters and call on them later without uploading them again.
OpenAI says the goal is to keep characters, products and brand details consistent through a series of edits, which matters to marketing teams that cannot afford a mascot changing shape from one frame to the next.
Developers will see image markup, already available in ChatGPT, come to the API so they can mark exactly where a change should happen.
SVG exports will let designs move into websites, apps and print.
A new complexity setting controls how much planning the model applies to a request.
OpenAI recommends low complexity for most editing jobs and medium or high for scenes with many elements or constraints.
Pricing for both models is listed on OpenAI's API pricing page rather than in the launch post.
One early API user is Town, a startup building an AI work assistant, which has used Images 2.6 to explore how animated characters could add personality to everyday workplace interactions.
Is Demand for AI Images Still Growing?
OpenAI says people now create 4 billion images a week across ChatGPT, Codex and the API, which averages out at more than half a billion a day.
In September, around the Images 2.5 launch, the figure was more than 3 billion a week.
Faster generation helps at that scale, and GIF editing is likely to add further rounds of revision.
The market is crowded.
Google's Nano Banana models, Adobe Firefly and Runway all compete in image creation or related creative tools, and Firefly now lets users choose from several image and video models.
OpenAI is relying on distribution inside ChatGPT and Codex, together with reusable references and frame editing, to keep users within its own products.
When Will Everyone Get GIF Generation?
Not every account has it yet.
Reports from early testing found the feature missing on some accounts, with the model producing a series of frames but no finished animation.
OpenAI has not given a date for when all ChatGPT users will receive GIF generation, and it has pointed readers to a system card covering the safety checks behind Images 2.6.
For now, those still waiting for their dancing cats will need to be patient.