Veo 3.1 and Veo 3.1 Lite: Google takes AI video to 1080p/4K vertical and "ingredients-to-video"
In one sentence Google releases Veo 3.1 and Veo 3.1 Lite: video generation with "ingredients" (multiple reference images for character/scene consistency), 1080p/4K output, vertical format for Shorts. Veo 3.1 Lite is the cost-effective variant.
Veo is Google DeepMind's video model. Veo 3 (May 2025) generated video from text prompts. Version 3.1, released January 13, 2026, does two important new things.
First: vertical video. AI video models have been working in 16:9 (cinema/TV format). Veo 3.1 is built to generate 9:16 (YouTube Shorts, TikTok, Reels format). For social content creators that's a foundational shift.
Second: ingredients-to-video. Instead of describing in words "a woman in a red jacket walks across an Italian piazza", you upload an image of the woman, an image of the jacket, an image of the piazza, and Veo 3.1 composes them while keeping visual consistency. It's the difference between "describing in words" and "showing the pieces".
Output up to 1080p or 4K. Veo 3.1 Lite ships alongside as the cheaper variant for developers at volume.
Companies
Google, Google DeepMind
Tools
Veo 3.1, Veo 3.1 Lite, Flow
Tags
Sources