Google revolutionizes video and image generation with new versions of Veo 2 and Imagen 3

The new versions of Google's artificial intelligence models mark a turning point in digital content generation. Veo 2 stands out for its ability to create 4K videos with an improved understanding of real-world physics and human movement, while also allowing precise control of cinematographic aspects such as lens type and visual effects.

The Imagen 3 model has also undergone significant improvements, now offering brighter and better-composed images, with the ability to reproduce various artistic styles with greater accuracy, from photorealism to anime. Google has also implemented an invisible SynthID watermark on all creations to identify them as AI-generated.

As a complement to these updates, the company has introduced Whisk, a new experimental tool that combines Imagen 3 with Gemini's visual understanding capabilities. This integration allows users to mix and modify existing images to create new personalized designs.

The new models are available through VideoFX and ImageFX in Google Labs, with plans to expand their access to YouTube Shorts and other Google products next year. The company maintains its commitment to responsible development, implementing a gradual deployment to ensure the quality and safety of these technologies.