Google Cloud has announced the expansion of its Vertex AI platform with the introduction of Veo, a video generator AI model.
Veo, developed by DeepMind, Google’s AI research division, can generate lifelike video from text or images and is now available in private preview for customers via Vertex AI.
Go deeper with GlobalData
Vertex AI is a managed platform that enables users to train and deploy machine learning models and customise generative LLMs for AI-powered applications.
It provides tools for both technical and non-technical users to build, customise, test, and experiment with AI models. The platform includes access to many foundation models from Google and other sources.
Unveiled at the Google I/O conference, Veo is Google’s most capable video generation AI model.
It can create high-quality 1080p resolution video with 24 or 30 frames per second in various cinematic and visual styles, extending beyond a minute in length.
How well do you really know your competitors?
Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.
Thank you!
Your download email will arrive shortly
Not ready to buy yet? Download a free sample
We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form
By GlobalDataVeo uses natural language understanding to produce video from text and can also incorporate images to condition its outputs.
For example, Veo can transform an image of a dog with the text prompt, “The dog gets up, wags his tail, looking at the camera, happy and full of life,” into a video.
The resulting video will depict the dog hopping up, tail wagging joyfully, and ears flapping, as if expecting a treat.
“The model provides an unprecedented level of creative control and understands cinematic terms like ‘timelapse’ or ‘aerial shots of a landscape,’” Google said about the model in its initial announcement.
“Veo creates footage that’s consistent and coherent, so people, animals and objects move realistically throughout shots.”
In September 2024, YouTube announced that users would be able to generate six-second Shorts clips and video backgrounds using the Veo model with simple text prompts.
Animated video backgrounds are set to launch this year, while six-second video clips are expected in 2025.
Google has also made Imagen 3, its latest text-to-image AI model, available to all Google Cloud customers globally on Vertex AI.
Imagen 3 produces lifelike images from natural language prompts with improved lighting, composition, and fine detail rendering. It offers enhanced control over text placement in generated images.
New features for Imagen 3 are being introduced for customers on the allowlist, enabling companies to edit and customise images. These include inpainting and outpainting, allowing users to modify or expand image sections based on descriptive prompts.
Imagen 3 also offers customisation controls for brand, style, logo, subject, and product features.
