Google Veo now turns selfies into AI-powered vertical videos

Google is making its Veo 3.1 AI video model pay more attention to the reference images it wants its generated clips to be based on. The company is releasing new visual improvements for Video Components tool. Which was introduced last year, along with expanded native vertical video support and resolution upscaling features.

The Video Components tool lets Veo users create videos based on up to three reference images, dragging in textures like character themes, backgrounds, and textures to get more control over how the results look. Google says this update will make videos “more expressive and creative,” and provide “richer dialogue and narration.” There are also consistency improvements that should be more noticeable – Veo 3.1 should now ensure a character looks similar across different clips and environments, and will allow users to reuse objects, backgrounds and textures across scenes.

Clips created with Video Components will now support vertical output. This comes after Google gave developers the ability to do so Created vertical videos in Veo last year For text-based prompts without references. Users can choose to output videos in their native 16:9 aspect ratio ready to upload to platforms like TikTok and YouTube Shorts, rather than manually cropping the results in video editing software.

Google is adding Veo’s enhanced video and portrait mode features to the Gemini app starting today, and integrating these tools into YouTube Shorts and the YouTube Create app “for the first time.”

Finally, this update allows Veo 3.1 users to upscale their created videos to 4K resolution, up from the previous 1080p limit. Google says 1080p video creation has also been improved to provide “clearer, cleaner video.” This is not the native 4K resolution that Google claimed the Veo was capable of producing Again in 2024 — something we haven’t seen yet in any version of Veo released to the public — but leveling up on the platform is better than nothing.