Thursday, November 19, 2026

Google DeepMind Unveils Enhanced Veo 3.1, Revolutionizing AI Video Creation with Reference Images and Vertical Support

Google DeepMind has unveiled an update to its AI video generation tool, Veo 3.1, which introduces a reference image function that allows users to create more...

Via News Editorial Team

January 14, 2026

From our archive, published before source-traceability. How we work

Google DeepMind Unveils Enhanced Veo 3.1, Revolutionizing AI Video Creation with Reference Images and Vertical Support
Image generated by AI for illustrative purposes. Not actual footage or photography from the reported events.
Loading stream...

Google DeepMind has unveiled an update to its AI video generation tool, Veo 3.1, which introduces a reference image function that allows users to create more dynamic and expressive videos with simpler text prompts. This enhancement is set to revolutionize the way users interact with AI-generated content, particularly on popular platforms like YouTube.

According to The Decoder, the new update enables users to maintain character consistency across multiple scenes and seamlessly blend various elements such as textures, objects, and backgrounds. This feature not only enhances the visual quality of the generated videos but also makes the process more intuitive and user-friendly.

One of the most significant additions in Veo 3.1 is native support for vertical videos in the 9:16 format, which is ideal for YouTube Shorts and other mobile-centric content. This move aligns with the growing trend of short-form video content, making it easier for creators to produce engaging clips that fit within the constraints of these platforms.

Furthermore, Veo 3.1 now offers upscaling capabilities to 1080p and 4K resolution, catering to professional production needs. This improvement is likely to result in a surge of high-quality AI-generated content flooding YouTube, especially in the Shorts format.

The updates are currently available in the Gemini app, YouTube, Flow, Google Vids, and through the Gemini API and Vertex AI. To ensure transparency, all generated videos include an invisible SynthID watermark, allowing viewers to verify if a video was created using Google’s AI tools. Users can check the origin of a video directly within the Gemini app.

This latest iteration of Veo demonstrates Google DeepMind’s commitment to advancing AI-driven content creation, providing users with powerful tools to generate dynamic and visually appealing videos. As the demand for short-form video content continues to grow, Veo 3.1 positions itself as a key player in the evolving landscape of AI-generated media.

According to The Decoder.

Are you or your business in this article?

If something is wrong, out of context or missing, tell us. We correct errors with a dated note, and people named in an article can publish their response under it.

Correct, add context or respond →

Not a source? Spotted an error? Report an error

How this story was made

Spotted an error? Use “Correct this article” (bottom right), or select any sentence, to report it or respond to that point.

  1. Published before we listed source documents with each article.
  2. Published 14 Jan 2026 · Last updated 19 Nov 2026
  3. No responses yet from the people or organisations in this story. Are you in this story? Respond on the record ›
  4. Part of the Via News record, fingerprinted daily so it cannot be quietly rewritten. What that means › · Report an error ›
Via News Editorial Team

The Via News Editorial Team writes analysis and news from the Via News source-traceability system, under the editorial responsibility of L. Miguel Salvado, Editor. Each article is built only from source documents we hold and lists them at the end, so every claim can be checked. Articles generated with AI say so under the byline, as the EU AI Act requires.