Google introduced its new video model Veo 3.1 with improved audio output, granular editing controls and better output for image to video. It says Veo 3.1 builds on May’s Veo 3 release and produces more realistic clips and better adheres to prompts.
The model allows users to add an object to the video and blend it into the style of the clip, Google said. Soon, users will be able to remove an existing object from a video in a flow as well.
Google releases Veo 3.1
Veo 3 already has editing features such as adding reference images to play a character, providing first and last frames to create a clip using AI, and the ability to stretch an existing video based on the last few frames. With Veo 3.1, Google is adding audio to all these features to make clips more lively.
The company is bringing the model to its video editor Flow, Gemini app, with Vertex and Gemini APIs. It said users have created more than 275 million videos on the app since Flow launched in May.