AI news illustration: Google's Veo Turns Portraits into AI Videos with Multi-Image Generation Tool
Google Veo: AI Turns Single Images into Dynamic Videos
Google's Veo Turns Portraits into AI Videos with Multi-Image Generation Tool
Google's engineers taught an AI what a chair is. A real one. The quiet core of the new Veo 3.1 model isn't just better video—it's a feature called "Ingredients to Video." Upload a reference image of a face, a specific wood grain, a fabric.
The system uses those as fixed anchors. It builds a scene from those parts, and those parts are meant to hold.
The Ingredients to Video tool allows Veo users to generate videos based on up to three reference images, pulling in materials like character subjects, backgrounds, and textures to have more control over how the results will look. Google says this update will make videos "more expressive and creative," and provide "richer dialogue and storytelling." There are also consistency improvements that should be more perceptible -- Veo 3.1 should now ensure a character looks the same across different clips and environments, and will let users reuse objects, backgrounds, and textures across scenes.
That "expressive storytelling" pitch is a veneer. They are selling control. The goal is to move from a slot machine to a construction kit.
Physics will still bend. The output will glitch. But the visual thread—that worn leather chair, that specific face—is meant to persist.
Turning a portrait into a moving clip is a novelty. Making that clip feel like it features the same person ten seconds later is the actual, fragile engineering. This is an attempt to build a coherent world, piece by locked-down piece.
Related Reading
Browse all Google news →
AI Tools & Apps Claude gains shared context in Excel, PowerPoint; Microsoft adds Copilot Cowork
AI Tools & Apps Windows Copilot AI unable to pinpoint image source in user test
AI Tools & Apps LG's recent webOS update adds Microsoft Copilot app, now removable
Related Topic NVIDIA and Google Cloud let developers scale AI from prototype to production
Market Trends
Related Topic Google tests visual 'magazine-style' UI for Gemini 3 Pro users
LLMs & Generative AI
From Archives Google Adds Direct Purchase Options to Gemini and Search AI Tools
From Archives Google launches Universal Commerce Protocol to enable frictionless AI shopping
From Archives Google's AI Inbox tested on near-inbox-zero user with six emails left
Market Trends
From Archives Microsoft launches retail AI agents while Gmail’s Gemini receives upgrade
LLMs & Generative AI
Common Questions Answered
How does Google's Veo transform static portraits into video content?
Veo allows users to generate videos by inputting up to three reference images, including character subjects, backgrounds, and textures. The AI tool can create dynamic vertical videos that maintain visual consistency across the generated content, giving creators more control over the storytelling process.
What makes the Ingredients to Video tool unique in AI video generation?
The Ingredients to Video feature enables users to blend multiple reference images to create more expressive and creative videos. By allowing input of different visual elements, Veo can generate more nuanced and intentional video clips that closely match the original visual inspiration.
What improvements does Veo 3.1 bring to AI video generation?
Veo 3.1 introduces enhanced consistency in video generation, ensuring that characters and visual elements remain more stable across the generated content. The update provides creators with more precise control over video production, making the AI-generated videos more coherent and visually appealing.
Further Reading
- Google's update for Veo 3.1 lets users create vertical videos through reference images — TechCrunch
- Veo 3.1: Google's Advanced AI Video Generator — Higgsfield
- The Ultimate Veo 3.1 Prompt Guide — DreamHost
- Veo 3.1 Ingredients to Video: More consistency, creativity and control — Google Blog
- Google Veo 3 vs OpenAI Sora 2 — Santa Clarita Valley Signal
