Google introduces Veo 3.1 AI model, adds new features to filmmaking tool Flow

Google has introduced Veo 3.1 AI model and expanded capabilities for its AI filmmaking tool Flow. These updates aim to give creators more control over their videos and enhance the realism of their scenes. Veo 3.1 builds on the Veo 3 model and offers “stronger prompt adherence and improved audiovisual quality when turning images into videos,” according to the tech giant. This means creators can produce videos that are more true to life, with realistic textures and seamless transitions between scenes.

A major update in Flow is the addition of audio to several key features. For the first time, creators can add sound when using Ingredients to Video, Frames to Video, and Extend. These features now give users more flexibility in designing their videos:

• Ingredients to Video now lets you combine multiple reference images to control characters, objects, and visual style. Flow uses these ingredients to generate a scene that matches your vision.
• Frames to Video allows you to provide a starting and ending image, and Flow will create a smooth video connecting the two.
• Extend helps you lengthen your videos by generating additional footage that continues from the final second of your clip.

Also read: Google Pixel 9 Pro Fold price drops by Rs 83,000 during Flipkart Big Bang Diwali sale

Flow also gets new editing tools for greater precision. With a new Insert feature, you can add new elements to your scenes, and Flow automatically handles shadows and lighting for a natural look. Soon, a new removal feature will allow you to seamlessly take objects or characters out of a scene while reconstructing the background as if they were never there.

Also read: Apple loses another key exec to Meta’s hiring spree, this time head of AI search project

Veo 3.1 is available through the Gemini API, Vertex AI for enterprise users, and the Gemini app. New capabilities are accessible in Gemini API and Vertex AI.