Google reveals Veo and Imagen 3 generative AI models
Google recently unveiled its latest generative AI models, Veo and Imagen 3, on Vertex AI. These models bring advanced capabilities to the world of artificial intelligence.
Veo Model
The Veo model is capable of taking a static image and animating it based on instructions provided to it. It is the first hyperscaler to offer an image-to-video model, allowing companies to create dynamic visuals and even convert text to video. Veo is currently in private preview, showcasing Google's innovative approach to generative AI.
Imagen 3 Model
On the other hand, the Imagen 3 model will be accessible to all Vertex AI users starting next week. This model enables customers to generate images based on text prompts they input, surpassing the performance of its predecessors. Google's continuous improvement in AI technologies is evident in the advancements seen in Imagen 3.
According to Google's official blog post, prominent companies like Honor, Agoda, Quora, and WPP are already leveraging generative AI for various applications.
