Creating viral social media videos was already incredibly easy with Google’s Veo AI model, but now it’s becoming even easier than before.
Google has updated its Veo 3.1 AI video-generation model with new features, including the ability to create vertical TikTok-style videos for social media platforms using reference images. The company announced the update on Tuesday, saying it will also make videos generated from reference images more expressive and dynamic.
Veo 3.1 Upgrades
The latest update enhances how Veo 3.1 handles reference images, allowing it to generate videos with better character expressions and movements, even when prompts are shorter. Google said the model now offers improved consistency across characters, objects, and backgrounds. Users can also combine different characters, backgrounds, objects, and textures into a single, cohesive video.
The update also introduces improved upscaling to 1080p and 4K resolutions.
Already Available on YouTube
With this update, users creating AI-generated videos for platforms such as YouTube Shorts, Instagram, and TikTok can now select the 9:16 vertical format directly, eliminating the need for cropping. Google is also integrating this feature into YouTube Shorts and the YouTube Create app.
Google originally launched Veo 3.1 in October 2025, introducing improved audio output and more detailed editing controls compared to earlier versions.
These features are available to users through the Gemini app. Professional users can access them via Google’s Flow video editor, the Gemini API, Vertex AI, and Google Vids.
