Google’s update for Veo 3.1 lets users create vertical videos through reference images

Google on Tuesday updated its Veo 3.1 AI video generation model with the ability to create native vertical videos for social platforms using reference images. The changes will also make the videos generated from reference images more expressive and dynamic.

When producing AI-generated videos for YouTube Shorts or other platforms like Instagram or TikTok, Veo users can now natively choose the 9:16 vertical format to avoid any cropping. Google is also adding the feature directly to the YouTube Shorts and the YouTube Create app.

Google first released Veo 3.1 in October 2025 with improved audio output and more granular editing controls compared to previous versions.

When you provide reference images, Veo 3.1 now generates videos with better character expressions and movements, even if your prompts are shorter. Google said the update also improves character, object, and background consistency. What’s more, users can blend various characters, backgrounds, objects, and textures to create a cohesive output.

Users can access these features directly in the Gemini app. Professional users can access them through Google’s video editor Flow, the Gemini API, Vertex AI, and Google Vids.

The new update also brings an improved upscaling feature to 1080p and 4K resolutions, which is available on Flow, Gemini API, and Vertex AI in Google Cloud.