
AI
ChatGPT Can Now Make Animated GIFs as OpenAI Rolls Out Images 2.6 With 50% Faster Generation
Images 2.6 turns a prompt or a photo into a GIF you can speed up, slow down and edit frame by frame. It is rolling out to every ChatGPT tier, and two new image models land in the API.
San Francisco · Jordan Hale, AI · Nov 5 2026
SAN FRANCISCO - ChatGPT can make GIFs now. OpenAI on Wednesday released Images 2.6, an update to its image generator that turns a text prompt or an uploaded photo into an animated GIF, and the company says the new model also generates images 50% faster than before.
Screenshot: @OpenAI on X
Once a GIF is made, you can change its playback speed, edit individual frames and share it, The Verge reported. Until this update, ChatGPT could not natively generate a GIF in a single step. “GIFS!” OpenAI wrote on X. “With ChatGPT Images 2.6, turn a prompt or image into an animated GIF. Adjust the speed, edit individual frames, and share it on repeat.”
Screenshot: @OpenAI on X
OpenAI pitches the feature at people who want to “animate a brand mascot for a campaign, create reactions and memes for social media, or use animated storyboards to explore character movement before video production.” One example on its announcement page pairs a pen sketch of an owl on lined paper with an animated cartoon owl.
Speed is the other half of the release. In the API, developers now choose between two models, GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst. OpenAI says Flare “can generate images in as little as six seconds” when quality is set to low, while Sunburst brings higher-quality generation and “even greater image consistency across edits” at medium or high quality. In one side-by-side the company published, the same luxury travel ad took 7.08 seconds with GPT-Image-2.5 Flare and 4.84 seconds with GPT-Image-2.6 Flare.
Image: OpenAI
Developers also get image markup, already available in ChatGPT, so teams “can pinpoint exactly where to make specific changes,” along with SVG exports and a new complexity setting that adjusts how much planning the model does to meet a request.
The usage numbers are large. OpenAI says people now create 4 billion images a week across ChatGPT, Codex and the API, “more than half a billion images created per day.” The Verge noted that is up from the 3 billion a week OpenAI reported in September.
Motion also brings new risks, and OpenAI says so in its system card. GIFs can carry risks “that may not be apparent in individual still images,” including “harmful meaning conveyed across frames,” and GIF-specific rules block some content more broadly than for stills. “Motion-related violations remain challenging to detect, and the safeguards may not catch all violations,” the card says.
Images 2.6 is available globally in ChatGPT and Codex “across all subscription tiers on desktop, mobile, and web,” according to OpenAI, and both new models are live in the API now.