Google has announced the availability of its two new generative AI models, Veo and Imagen 3, on its cloud platform Vertex AI. Veo is an image-to-video model capable of generating high-quality videos, while Imagen 3 can produce realistic and highest-quality images from text prompts.
Developed by Google DeepMind, Veo uses a range of cinematic styles to generate videos based on text or image prompts. The model has been shown to achieve exceptional speed in video generation.
According to Warren Barkley, senior director of product management at Google Cloud, generative AI is driving business growth and transformation for 86% of enterprise companies using AI.
Both Veo and Imagen 3 will have built-in safeguards to prevent misuse and generate harmful content. The models will be available in a private preview for Vertex AI customers starting next week.
The generated images and videos from these models will carry an invisible watermark, known as SynthID, designed to combat misinformation and misattribution. Neither model uses customer data during training.
Source: https://indianexpress.com/article/technology/artificial-intelligence/google-veo-video-generative-ai-model-now-available-9705504