Google's Veo: The next frontier in AI‑driven video generation

Many artificial intelligence enthusiasts immediately think of "Sora" when generating videos from text descriptions. Indeed, OpenAI is gearing up to unleash this remarkable model, yet a new challenger has appeared: Google's Veo.

The Google I/O 2024 conference has been a delight for aficionados of AI-based tools and technology. Among the innovations showcased was Project Astra, poised as a contender to OpenAI's GPT-4. In the same vein, Google's Veo aims to offer an alternative to the Sora model.

So, how does Google Veo operate, and what makes it stand out? The process is straightforward: you input a prompt and anticipate the outcome. This time, it's not merely an image but a lifelike video. Google Veo can craft a one-minute video grounded on the entered text.

Google assures that the tool will deliver high-quality recordings (1080p) and that Google Veo will facilitate their editing beyond producing videos.

Veo is set to enhance the workflow of professional creators while being accessible to novices in the art domain. The rollout of such advanced utilities tends to occur in phases, and this instance is no exception.

In the forthcoming weeks, Google plans to grant access to some of these functionalities to select creators via VideoFX, a new experimental platform available on labs.google. Registration for the waiting list is already open.