Google Cloud announced on the 5th that it will launch 'Veo,' a video generation artificial intelligence (AI) model, and 'Imagen3,' an image generation model.
Veo will be available in preview form on Vertex AI. Vertex AI is a platform that supports enterprise users in training and deploying AI models and developing AI applications utilizing large language models (LLMs).
Developed by Google DeepMind, Veo quickly generates high-definition videos in various cinematic and visual styles based on text or image prompts. With excellent understanding of natural language and visual semantics, it produces videos closely aligned with the prompts, creating consistent and natural footage where people, animals, and objects move realistically throughout the video. It can also generate videos based on existing images or AI-generated images.
Google stated, "With Veo, production time can be shortened and costs reduced while quickly prototyping or iterating video content." They added, "Veo’s technology helps workers focus on higher-level tasks and allows AI to handle tedious or repetitive tasks in the video production process."
Imagen3 is a text-based image generation model. It can create realistic and vivid images, with significantly reduced visual errors compared to previous models. It also offers editing features that allow refinement and customization of existing images. Users can edit photos with simple text, edit only parts of an image including updating product backgrounds, or resize images to the required dimensions.
Imagen3’s customization feature supports setting to generate images with desired characteristics. Customers can input brand, style, logo, theme, and product features directly when generating new images. This is said to accelerate advertising and marketing processes. Starting next week, all Google Cloud customers will be able to use Imagen3 on Vertex AI.
© The Asia Business Daily(www.asiae.co.kr). All rights reserved.
