Merely days after OpenAI released its Sora 2 AI video generator app, which quickly went viral for some pretty morbid reasons, Google is giving a lift to its own AI video tools. The company’s Flow video creation platform is getting upgraded to the new Veo 3.1 AI video model, alongside a bunch of new tricks in tow. The next-gen video AI model is now available to users in the Gemini app, as well, starting today.
What’s new?
One of the biggest upgrades this time around is the ability to add audio, alongside a bunch of new creative controls in the Flow suite. For example, the new “Ingredients to video” system lets users upload multiple images to ensure that they can achieve just the right style and character control in the scene.
The overarching idea is that instead of describing every minute detail, users can take the easier route. For example, you can upload the image of a person, pick another image with the background of your choice, and the third image is that of a costume for the character.
The AI will combine them all. It’s not just convenient, but also offers a far more granular control over the videos you want to create, instead of dealing with hit-or-miss AI prompts. It’s almost like creating hybrid emojis using the Emoji Kitchen system in Google’s Gboard app.
A whole new level of creative control
In addition to controlling the scene elements, Flow is also getting a new “Frames to video” feature that lets users create a scene by simply supplying the start and end frames. Once the two images are uploaded, the AI will automatically stitch them together and create a seamless video out of it.
Next, we have the new “Extend” tool. As the name makes it abundantly clear, it comes in handy for prolonging a scene without having to write a fresh prompt or add another image as the source material. “Flow creates a new video based on the final second of your original clip,” source material.
And finally, we have the new “Insert” feature, which lets users add anything to a video naturally without disturbing the background continuity. Soon, Google will also let Flow users remove objects from videos, somewhat like the Magic Eraser feature in the Google Photos app. As far as the Veo 3.1 model goes, it adds “richer audio, more narrative control, and enhanced realism that captures true-to-life textures” to videos created in Flow.
