What Does the New Google Veo 3.1 Video Model Bring?

What Does the New Google Veo 3.1 Video Model Bring?

Ondřej Barták
Ondřej Barták
Entrepreneur and Programmer
15. 1. 2026
3 minutes reading · 27 views
What Does the New Google Veo 3.1 Video Model Bring?

If you’ve ever wanted to create a video from an ordinary image and have it instantly ready for TikTok or YouTube Shorts, Google has just taken a major step in that direction. Its Veo 3.1 model has received an update that makes it possible to generate videos directly in a vertical 9:16 format based on reference images. This means you don’t need to crop anything in an editing program—everything comes out exactly as you need it for mobile platforms. This new feature was introduced on January 13, 2026, and is available in Gemini, YouTube Shorts, and YouTube Create.

Ingredients to Video

Ingredients to Video is a tool in Veo 3.1 that takes up to three reference images—such as a character, background, or texture—and uses them to create a video. Now it’s even better: videos are more expressive and dynamic, even if you only enter a short description. For example, characters have richer facial expressions and movements, which helps with storytelling. Google emphasizes that consistency has improved—a character looks the same across different scenes and environments, objects do not change randomly, and textures remain consistent. This makes it easy to combine elements from different images into a single video, giving creators greater control.

Vertical Videos Directly from Images

Previously, you could create vertical videos only from text descriptions, but now you can also use reference images. That’s great for those who create content for social media. Simply select the 9:16 format, and the video is ready without any additional editing. This feature is also appearing in YouTube Shorts and YouTube Create for the first time, where you can use it right away. According to information shared by Google DeepMind on Twitter, it helps create more expressive clips with better visual quality.

Upscaling to Higher Resolutions

Another major improvement is enhanced resolution upscaling. Veo 3.1 can now upscale videos to 1080p or even 4K, which is ideal for professional use. This option is available in Flow, the Gemini API, and Vertex AI in Google Cloud. Logan Kilpatrick, who wrote about it on Twitter, mentioned that consistency when using ingredients (reference images) has improved and that support for vertical videos is now fully integrated.

Availability

These new features are available across several Google services. Regular users can access them in the Gemini app, where they can experiment with short descriptions and images. Professionals will appreciate them in the Flow editor, Google Vids, or through the developer API. Google also embeds SynthID digital watermarks in generated videos to make it clear that they are AI-generated content. Jess Weatherbed of The Verge noted that videos now match reference images more closely, including those in portrait orientation.

Imagine you have a photo of your favorite character and want to turn it into a short video with dialogue or movement—Veo 3.1 can do this more accurately than before. TechCrunch described how the update makes it possible to blend characters, backgrounds, and objects into a cohesive output. And for those who create content on mobile devices, vertical support is a huge time-saver. Overall, it makes AI video creation more accessible both to casual users and to those who take it seriously.

Advertisement

Content created with help from UpTier.

SEO and GEO on autopilot. UpTier’s multi-agent systems write and optimize content for search engines and AI answers.

Discover UpTier ↗

Category:AI
Did you enjoy this article?
Discover more interesting posts on our blog
Back to blog

Related posts

Google makes Tasks free for Gemini 4 Hydrogen usersGoogle makes Tasks free for Gemini 4 Hydrogen users
Tasks is becoming available for free to hundreds of millions of Gemini 4 Hydrogen users. Google says it can call businesses, book appointments and complete purchases on their behalf.
1 min read
18. 11. 2026
OpenAI introduces GPT-6.2 Astra and Sol for professional and everyday workOpenAI introduces GPT-6.2 Astra and Sol for professional and everyday work
OpenAI has introduced two models: Astra for complex professional tasks and Sol for everyday work. Both are available in ChatGPT Work, Codex and through the API.
3 min read
17. 11. 2026
Tencent releases Hy4 Flash with image support and a context window of up to 1 million tokensTencent releases Hy4 Flash with image support and a context window of up to 1 million tokens
The lighter Hy4 Flash model targets chat, documents and routine code edits. It accepts text and images, supports tool use and, according to Tencent, matched Claude Haiku 5.5 in tests of everyday tasks.
1 min read
16. 11. 2026
Přihlaste se k odběru našeho newsletteru
Zůstaňte informováni o nejnovějších příspěvcích, exkluzivních nabídkách, a aktualizacích.
CodedTrip

Operated by CodedTrip LLC, USA.

YouTube
TikTok