Google is building its Veo 3.1 AI video model by paying more attention to the context images you want the clip generated based on. The company is releasing new visual improvements to the “Content in Video” tool, which was introduced last year, as well as expanding native vertical video support and resolution upscaling features.
The Content tool for videos allows VO users to create videos based on up to three reference images, with greater control over how the results will look by dragging and dropping materials like character subjects, backgrounds and textures. Google says this update will make videos “more expressive and creative” and facilitate “richer dialogue and storytelling.” There are also continuity improvements that should be more perceptible – VO 3.1 should now ensure that a character looks the same in different clips and environments, and will let users reuse objects, backgrounds and textures across scenes.
Clips created using Content for Video will now also support vertical output. This comes after Google last year gave developers the ability to generate vertical video in Veo for text-based prompts without context. Users can choose to output video in the native 9:16 aspect ratio that is ready to upload to platforms like TikTok and YouTube Shorts instead of manually cropping the results in video editing software.
Google is adding VO’s improved content video and portrait mode features to the Gemini app starting today, and integrating those tools into the YouTube Shorts and YouTube Create apps “for the first time.”
Finally, this update allows Veo 3.1 users to upscale their generated videos from the previous 1080p limit to 4K resolution. Google says 1080p video generation has also been improved to deliver “a sharper, clearer video.” This is not the native 4K resolution that Google claimed the Veo was able to produce back in 2024 – something we haven’t seen yet in any version of VO launched to the public – but on-platform upscaling is better than nothing.
