(Credit: Google)
After rolling out text-based vertical video generation in Veo last year, Google is now expanding the feature by letting it draw inspiration from reference images.
With an update to Veo 3.1’s Ingredients to Video tool, Google now allows users to upload up to three portrait reference images. Veo then blends the characters, objects, and backgrounds from those images into “a cohesive, high-impact clip,” Google says.
The update also brings greater consistency to characters. They remain visually coherent even as the setting changes throughout the clip, Google notes.
Another major change is native support for a 9:16 aspect ratio. Users can now select the vertical format in Veo and upload outputs directly to YouTube Shorts or TikTok without cropping or compressing. Users can also upscale their videos to a 4K resolution when the previous limit was 1080p.
All of these Veo improvements are now rolling out to the Gemini mobile app. Google is also making them available in YouTube Shorts and the YouTube Create app for the first time. Professional and enterprise users, meanwhile, can use these features in Flow, Gemini API, Vertex AI, and Google Vids.
The upgraded capabilities could mean more AI slop in YouTube Shorts and similar platforms. A recent study found that nearly 21% of the Shorts we see are AI-generated.
If you want to remove Shorts from YouTube search results, you can make use of the platform’s new content filters.
To check whether a video you received was generated using Google’s own AI tools, you can upload the clip to Gemini and ask it to verify it.