Google DeepMind’s impressive video generation tool Veo has just received an update that brings a long-awaited feature to users. The tool now supports native vertical video output, making it ideal for creating content for Instagram Reels, YouTube Shorts, and TikTok.
In its announcement, Google notes that Veo now allows users to create videos in a 9:16 aspect ratio, eliminating the need to crop or frame clips for vertical-first platforms. To create portrait videos, users simply need to upload a vertical image and Veo will maintain the aspect ratio and orientation. The update also brings improvements to the tool’s Ingredients to Video features, allowing videos to be made “more expressive and creative, even with simple prompts.”
Identity consistency has also been improved in the latest version of Veo 3.1, so generated characters now look the same even when the setting changes. Google says this makes it easier for creators to tell a complete narrative “by having the same character appear in multiple scenes.” In addition, the tool now maintains the integrity of the environment and the objects within it, allowing users to reuse objects, backgrounds or textures in different scenes.
Creators can now upscale videos to 1080p and 4K
Google adds that Veo now also has the ability to combine different elements such as characters, objects, textures and stylized backgrounds to create more cohesive videos. For developers who need high-resolution clips for their projects, the tool also supports upscaling to 1080p and 4K.
The update is already rolling out and users can try out Portrait Mode and Ingredients to Video extensions in the Gemini app. These features also come to Flow, the Gemini API, Vertex AI and Google Vids. However, upscaling options for 1080p and 4K resolutions are currently limited to Flow, the Gemini API, and Vertex AI.
