New Delhi: Google has recently introduced its latest Veo 3.1, an update to its generative AI video model that will enable users to create better AI-generated content. The company has stated that the upgrade will unveil a suite of professional-grade features and mobile-optimised formats. The most significant upgrade is the major enhancement to the ingredients for video, Google’s technology that enables users to generate motion based on specific reference images.
Improvements to the Veo 3.1 Ingredients for Video, their capability that lets users create videos based on reference images. This update makes the videos more expressive and creative, even with the simple prompts. Native vertical outputs for the Ingredients to Video to power mobile-first, short-form video creation, state-of-the-art upscaling to 1080p and 4K resolution for high-fidelity production workflows. Google has also said that one of the most persistent challenges in AI video generation is maintaining the same character or background across different clips, and Veo 3.1 addresses that.
Google has also stated that the state-of-the-art identity consistency enables the creators to keep a character’s appearance identical even as the setting or camera angle changes. The update is also going to improve background and object consistency. Google is unveiling native vertical output for the first time, allowing the creators to generate full-screen content for platforms like YouTube Shorts without the quality loss that comes with the cropping of landscape video.
There is also support for the 1080p resolution for the sharper, cleaner output optimised for standard editing, and 4K resolution for the rich textures, as well as clarity for the large-screen productions. The latest features are being integrated across Google’s entire creative suite, while casual creators can access Veo 3.1 within the Gemini application and YouTube Shorts, enterprise users and developers can leverage those upgrades through the Gemini API, Vertex AI, and Google Vids.
