Techonology

Google introduces Veo and Imagen 3 to AI platform

Google has two new generative AI models, Veo and Imagen 3 now available On cloud hosting service Vertex AI. Veo takes video, and Imagen 3 takes photos.

Google proposes that these models can be used in marketing, e-commerce, and more.

Veo creates video from text or image signals

After experiments with video generation by companies like OpenAI earlier this year met with mixed success, infrastructure and processing power have caught up and made video generation more practical. Just this week, Amazon introduced a video-generation model on AWS called Amazon Nova Reels.

Veo creates videos from text or image prompts and can add elements to existing videos. Google addressed common challenges in video-generation AI, such as maintaining continuity and avoiding activity that looks unnatural. The effort follows OpenAI’s February Sora showcase, which highlighted issues such as bizarre activities, including unrealistic examples featuring wolves.

Veo can generate images longer than a minute at 1080p resolution, and longer videos can include multiple scenes generated from sequential signals.

VO can mimic different art styles, as shown in this video, which is entirely modeled. Image: Google DeepMind

Veo is now available in private preview. To get started, account holders can contact their organization’s Google Cloud account representative.

Imagen 3 creates images that look photorealistic or animated

Imagen 3, released at Vertex AI in a private preview in June, will be generally available “starting next week.” Imagen 3 can create realistic or stylized images from a text prompt. Google said there are improvements in detail, lighting, and artifact reduction compared to the previous generation of Imagen.

For marketing, Google highlighted that organizations can incorporate their own “brand, style, logo, theme or product features” into AI-generated images. That customer data is not fed back into the model to train new iterations of the image.

A company can insert its own product images into Imagen 3's AI-generated content.
A company can insert its own product images into Imagen 3’s AI-generated content. Image: Google Cloud

Google A guide is offered Working with Imagen 3 for developers. For security, Imagen 3 comes with digital watermarking, content filters, and data governance safeguards.

SEE: These video production templates for Google Sheets and more can make your workflow run more smoothly.

Companies offer more generative AI options, explore ROI sources

Google Cloud has sold Veo and Imagen 3 on Vertex AI to various high-profile clients, who have praised the tool for its rapid iteration of content using generative AI. However, generative AI giants and their customers sometimes struggle with how to get value from the tools.

During this time, Google claimed 74% of organizations with generative AI investments see ROI. However, the reception of AI-generated content has not been universally positive: Coca-Cola’s November AI-generated video ad created ControversySome consumers reacted negatively to it as lacking creativity or authenticity.

(TagstoTranslate)Artificial Intelligence(T)Generative AI(T)Google Imagen 3(T)Google VO(T)Google Vertex AI(T)Video Generation
#Google #introduces #Veo #Imagen #platform

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *