ChatGPT users can now generate GIFs by describing an animation in a text prompt or uploading an image to animate. The feature is powered by Images 2.6, OpenAI’s latest image-generation model, and is rolling out globally across ChatGPT and the coding tool Codex.
Users can also submit a rough drawing for the model to develop into a more complete image before animating it. After a GIF is generated, they can adjust its animation speed and view or edit individual frames, according to The Verge. OpenAI also said in a since-deleted post on X that uploaded images could be saved for reuse in future prompts.
OpenAI describes the feature as a way to create animated storyboards or explore character movement before video production, rather than as an AI video generator. Images 2.6 is available across all ChatGPT and Codex subscription tiers.
OpenAI says Images 2.6 generates images 50 percent faster than its previous model, Images 2.5. Its speed-focused GPT-Image-2.6 Flare model can produce an image in about six seconds when set to low quality. The GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst models are also rolling out through the company’s API.
Sources: Mashable.