Google launched Veo, a powerful video production artificial intelligence

Google 2 artificial intelligence model of video production Veo and photo production Image 3 through the platform Vertex AI makes available. Vertex AI is Google’s machine learning platform that allows you to train and run large language models and AI applications.

According to published reports, the Veo model is currently in private preview and Imagen 3 will be available to all Vertex AI users in a few days. Another point is that Imagen 3 also has image editing capabilities so that users can modify the generated images based on their needs.

Veo video production artificial intelligence

Veo AI, which was first introduced at the Google I/O conference, is the company’s answer to competing models such as Runway’s Gen-3 and OpenAI’s Sora. This model can convert users’ text or image commands into high-quality cinematic videos of up to 60 seconds in different visual styles.

Imagen 3, which is another artificial intelligence model of Google DeepMind, is responsible for generating images based on text and produces realistic images in different styles. Google claims that this model surpasses its competitors in displaying details, light accuracy and reducing image artifacts.

Vertex AI is Google Cloud’s flagship platform for simplifying the development and deployment of artificial intelligence applications. With the addition of Veo and Imagen 3, the platform provides organizations with a more comprehensive set of AI tools for innovation in marketing, sales and other areas.

“Warren Barkley”, Google’s senior director of product management, says in the company’s statement:

“Clients like Agoda are leveraging the power of AI models like Veo, Imagen, and Gemina to streamline their video ad production and save significant time.”

He also emphasized that both models are equipped with safety features such as digital watermark registration to reduce the risks associated with artificial intelligence.