Saturday, September 5, 2026

Google Enhances Veo 3.1 AI for More Accurate Vertical Video Generation Based on Images

Google enhances Veo 3.1 AI with improved vertical video generation, native 9:16 support, 4K upscaling, and better consistency with reference images for social media creators.

LM Salvado

January 14, 2026

Google Enhances Veo 3.1 AI for More Accurate Vertical Video Generation Based on Images
Image generated by AI for illustrative purposes. Not actual footage or photography from the reported events.
Loading stream...

Google has unveiled updates to its Veo 3.1 AI video model, enhancing the tool's ability to create videos based on reference images and expanding support for vertical video formats. According to The Verge AI, these improvements aim to make videos more consistent with their source images and offer better creative control for users.

The Ingredients to Video feature, introduced last year, allows users to generate videos based on up to three reference images. With the latest update, Google has made significant strides in ensuring that the generated videos closely resemble the input images, including those in portrait orientation. This enhancement is particularly important as vertical videos have become increasingly popular on social media platforms such as TikTok and YouTube Shorts.

"Videos should now be more consistent with the images they're based on, including those in portrait orientations," reports The Verge AI. This means that characters, backgrounds, and textures will maintain their integrity across different clips and environments, providing a more cohesive and visually appealing result.

In addition to improved consistency, Veo 3.1 introduces native vertical video support, allowing users to directly generate videos in a 9:16 aspect ratio suitable for sharing on social media. Previously, users had to manually crop the results in video editing software, which added an extra step and potential loss of quality. Now, the vertical format is natively supported, streamlining the process and ensuring optimal resolution.

Moreover, Veo 3.1 now supports upscaling of generated videos to 4K resolution, up from the previous 1080p limit. This enhancement provides users with higher-quality visuals, making the final product more polished and professional.

Google is rolling out these improvements through the Gemini app and integrating them into YouTube Shorts and the YouTube Create app for the first time. This integration aims to enhance the creative capabilities of content creators, enabling them to produce more expressive and engaging videos with greater ease.

With these updates, Google continues to refine its AI-driven video generation tools, catering to the growing demand for high-quality, vertical videos in the social media landscape. The improvements in consistency, native vertical support, and resolution upscaling represent significant advancements that could significantly impact how users create and share video content online.

LM Salvado

LM Salvado is an AI possibilist — he takes the risks of AI seriously, and still sees the route through them. Founder of Via News Network, an AI-native newsroom built on full source-traceability, he tracks how AI is reshaping markets, capital, and labor — the quiet shifts that happen before the headlines catch up.

What we know · the intelligence behind this page
Live from the substrate
What we're seeing
AI Capital Surge Meets Investor Caution: Record Funding Rounds and Government Contracts Amid Valuation Skepticism
A single-week cluster of large AI/fintech funding rounds (Socure, Stability AI, Emerald AI, Generalist AI, Instinct, Gatik, Regent Craft) shows venture capital still pouring into AI infrastructure, identity, and autonomy plays, while Palantir's Army TITAN contract win coincided with a 6% stock drop — signaling that even flagship AI-defense revenue isn't immune to market reassessment of AI valuations. Efficiency-focused innovations like Multiverse Computing's model compression suggest the sector is also pivoting toward cost/inference economics as capital intensity draws scrutiny.
Our read on the data ›
Signals we're tracking
EPKINLY Regulatory-Clinical Success Cascade
High probability of expanded label indications, additional combination approvals, and competitive positioning strength in follicular lymphoma market. Predicts positive commercial uptake and potential accelerated review for related indications.
Patterns we're watching ›
Where sources disagree
Morgan Stanley & Co. LLC
The same metric (eps) for the same entity (Morgan Stanley & Co. LLC) reported for the identical fiscal period (Q1 2026) and observation date (2026-03-31) has two conflicting values: 3.43 USD_per_share vs 3.08 USD. This is not a temporal change — both observations claim to measure the same point in time. The ~10% discrepancy (0.35 USD difference) is material for a financial metric.
We flag conflicts openly ›
Recently verified
Checked against the original source
4,981
facts traced to their source — and we flag the ones that don't hold up.
101 entities tracked4,981 facts checked against source5,273 source documents archived
Query this data → isubstrate.com