Google Cloud has introduced Veo, a new video generation model within its Vertex AI platform. Developed by DeepMind, Veo can create lifelike video from text or images and is currently available in private preview for select customers.
Veo supports high-quality 1080p video at 24 or 30 frames per second, with cinematic and visual styles. The model uses natural language understanding to convert text prompts into realistic video, allowing users to direct scenes with specific cinematic terms, such as “timelapse” or “aerial shots.”
For example, by inputting an image of a dog and a descriptive prompt, Veo can generate a video of the dog moving joyfully. The model ensures coherent and realistic motion, making it suitable for creative projects across industries.
Google also announced plans to integrate Veo into YouTube, allowing users to generate six-second Shorts and animated video backgrounds with text prompts. Animated backgrounds will be available later this year, with Shorts coming in 2025.
In addition, Google launched Imagen 3, a new text-to-image AI model, now available globally through Vertex AI. Imagen 3 produces detailed images from text and includes features like inpainting and outpainting, allowing users to modify or expand images based on prompts.
With Veo and Imagen 3, Google is expanding the creative potential of its AI platform, offering advanced tools for video and image generation.
Related topics:
How Mobile Robots Handle GPS Signal Loss
Google Cloud Partners with Air France-KLM to Transform Data and AI Strategy
Google Addresses Tenth Chrome Zero-Day Exploit of 2024 Amid Ongoing Security Challenges