Google Flow is a video generation platform using artificial intelligence (AI) that was launched last May. Unlike other generative AI, Flow allows for more precise control over the video that is to be generated. Today Google announced several improvements to Flow and also announced a new AI model Veo 3.1.
Flow can now be given images to use as objects in the video. This is similar to Nano Banana which generates static images with several uploaded photos as references. Flow. can also be given instructions for the first and last frames of the video. With this, the generated video better meets the vision in the user's head.
Users can also now add or remove objects from the generated video. The video extension feature has also been improved so that it does not look awkward.
Meanwhile, through the Veo 3.1 model, it can generate more accurate audio, better narrative control and generate videos that look more realistic compared to Veo 3. All of the features announced are available today.
