Google launches its latest generative AI model Veo. As announced in an official blog, Google will be rolling out Veo for businesses. Veo is Google’s AI model which could generate video with a text prompt.
Google says that Veo is capable of generating “high-quality” 1080p resolution videos. The video comes in a range of different visual and cinematic styles from text and image-based prompts. Let’s have a detailed look at what the AI model brings for you.
Veo gets launched: What’s in for you
Google has started rolling out private access to both of its Veo and Imagen 3 generative AI models. Starting today users/customers of the company’s Vertex AI Google Cloud package can start using Veo to generate videos from text prompts and images. The tech giant claims that Veo is the first hyperscale cloud provider to offer an image-to-video model.
Coming to safety and copyright infringement issues, there have been previous examples of several AI models creating such issues.In response to this, Google said that both Veo and Imagen 3 are embedded with DeepMind’s SynthID technology. But what is SynthID and how can it promise the safety of your data. So, SynthID can be defined as a kind of invisible digital watermark. The company further added that it can “decrease misinformation and misattribution concerns.”
This ‘nearly invisible watermark’ concept is quite similar to Adobe’s Content Credentials system. Notably, the Content Credentials can be embedded into content produced by the creative software giant. The mark can be added on Adobe’s own AI generated image and video generative AI models.
Other updates
Apart from Veo, the latest version of Google’s Imagen 3 text-to-image generator will also be available to all Google Cloud customers. You could get the AI tool on Vertex starting from next week. According to the official announcement, Google will be expanding its initial US release on Google’s AI Test Kitchen, which started back in August.
In addition to this, if you are on Google’s allow list, then you can also access new features. This includes features such as prompt-based photo editing, and the ability to implement your own style, brand, subject, logo and product features into every AI generated image/video .
Follow FE Tech Bytes on Twitter, Instagram, LinkedIn, Facebook
