What changed

ChatGPT can now create animated GIFs using OpenAI's Images 2.6 model. The update allows users to generate GIFs from text prompts or uploaded photos and adjust animation speed or edit individual frames. OpenAI demonstrated the feature with a prompt for a cat dancing, producing several variations that are combined into a flipbook-style GIF.

What this means in practice

Users of ChatGPT and Codex on web, desktop, and mobile apps can now generate animated GIFs. The model's image consistency ensures the character remains recognizable across frames, unlike earlier models that would alter the appearance too much. OpenAI also released API models GPT-Image-2.6 'Flare' for efficient image generation and 'Sunburst' for higher-quality results. These models were first introduced with Image 2.5. OpenAI reported that users now generate over four billion images per week via ChatGPT and the API, an increase of one billion from September.

Limitations and availability

The feature is rolling out to all ChatGPT and Codex users across platforms. The Images 2.6 model's image consistency appears strong enough for the GIF creation feature, but the supplied announcement does not specify any limitations on hardware requirements or license conditions. The API models 'Flare' and 'Sunburst' are available for developers, though the exact terms of their availability are not detailed in the source.

Source facts for ChatGPT Now Creates Animated GIFs Using OpenAI's Images 2.6 Model: Users can generate a GIF from a text prompt or uploaded photo, then adjust animation speed or edit individual frames. OpenAI via The Verge Beyond GIFs, Images 2.6 is also meant to speed up image generation overall. Both model variants were first introduced with Image 2.5.
Original AINewsTrend explainer based on the cited source. This graphic summarizes source statements; it is not an independent benchmark.

Sources and further reading

  1. thedecoder: ChatGPT can now turn text prompts and photos into animated GIFs with OpenAI's Images 2.6 model