Google’s Veo 3.1 Just Beat Sora?! 😳

Why It Matters

By enabling image-conditioned generation, multi-ingredient composition, and longer video extensions, Veo 3.1 broadens practical use cases for AI video—from personalized content and advertising to prototyping—and raises the bar for competitors in the fast-moving generative-video market.

Summary

Google has released Veo 3.1, a significant update to its AI video-generation model that improves output quality and introduces several new creative controls. Users can now supply one or multiple images as “ingredients” to populate or style generated videos, animate a transition from one image to another, and extend existing videos to durations of a minute or more. The update claims improved physics and overall results, and the feature is accessible via Google’s Flow app or a 3D API. Early demos show notable gains over prior models, positioning Veo 3.1 as a more flexible tool for personalized and longer-form AI video creation.

Original Description

If you liked Sora… you’ll love what Google just dropped. Veo 3.1 takes video generation to another level: animate a single image into motion, bridge between two photos, extend scenes up to a minute, and even control objects and styles using multiple reference images. It’s like giving your stills a second life.

Better sound, smoother physics, more control. The gap between imagination and reality is closing fast.

I’m Louis-François, PhD dropout, now CTO & co-founder at Towards AI. Follow me for tomorrow’s no-BS AI roundup 🚀

#Veo3 #GoogleDeepMind #AIvideo #short