ChatGPT will launch a GIF generation feature powered by the undisclosed Images 2.6 model

OpenAI is gradually rolling out a GIF generation feature within ChatGPT, allowing users to describe animations in natural language or upload existing photos for ChatGPT to convert into GIFs. Once generated, users can adjust playback speed, view frames one by one, edit, and share the final product. According to The Verge, this feature is powered by OpenAI's new image generation model Images 2.6, which has not yet been officially announced through a product release.

This GIF feature is part of the Images 2.6 update, which promises faster image generation speeds. The Verge reports that OpenAI is pushing this model to web, desktop, and mobile users of ChatGPT and Codex. Developers will also gain access to two new API models, GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst, aimed at faster generation speeds and higher quality results, respectively. OpenAI has not released a separate announcement detailing the capabilities of this model.

This update follows the release of ChatGPT Images 2.5 in September, which brought sharper details, more precise editing, and up to a 50% increase in generation speed compared to the previous generation. Additionally, OpenAI shut down its standalone AI video generation application Sora in March. Currently, this feature is being rolled out gradually, and most users are temporarily unable to access it; OpenAI has not provided a specific timeline for when all ChatGPT accounts will gain access to the GIF generation feature.