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 videos created 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 choose a 9:16 vertical format to avoid cropping. Google also added the feature directly to the YouTube Shorts and YouTube Create apps.
Google was first released Veo 3.1 in October 2025 with good audio output and more granular editing controls compared to previous versions.
When you provide a reference image, Veo 3.1 now produces video with better character expression and movement, even if your request is shorter. Google says the update also improves character, object, and background consistency. What’s more, users can mix different characters, backgrounds, objects, and textures to create a cohesive output.
Users can access these features directly in the Gemini app. Professional users can access it through Google Flow video editor, Gemini API, Vertex AI, and Google Vids.
The new update also brings improved upscaling features for 1080p and 4K resolutions, available in Flow, Gemini API, and Vertex AI on Google Cloud.
Techcrunch event
San Francisco
|
13-15 October 2026