GCP – Veo and Imagen 3: Announcing new video and image generation models on Vertex AI

Generative AI is leading to real business growth and transformation. Among enterprise companies with gen AI in production, 86% report an increase in revenue¹, with an estimated 6% growth. That’s why Google is investing in its AI technology with new models like Veo, our most advanced video generation model, and Imagen 3, our highest quality image generation model. Today, we’re building on that momentum at Google Cloud by offering our customers access to these advanced generative media models on Vertex AI: 

1. Veo, now available on Vertex AI in private preview, empowers companies to effortlessly generate high-quality videos from simple text or image prompts. As the first hyperscaler to offer an image-to-video model, we’re helping companies transform their existing creative assets into dynamic visuals. This groundbreaking technology unlocks new possibilities for creative expression and streamlines video production workflows.
2. Imagen 3 will be available to all Vertex AI customers starting next week. Imagen 3 generates the most realistic and highest quality images from simple text prompts, surpassing previous versions of Imagen in detail, lighting, and artifact reduction. Businesses can seamlessly create high quality images that reflect their own brand style and logos for use in marketing, advertising, or product design. 

Vertex AI provides an orchestration platform that makes it simple to customize, evaluate performance, and deploy these models on our leading infrastructure. In alignment with our AI Principles, the development and deployment of Veo and Imagen 3 on Vertex AI prioritizes safety and responsibility with built-in precautions like digital watermarking, safety filters, and data governance. 

Veo: our most capable video generation model, now available on Vertex AI

Developed by Google DeepMind, Veo generates high-quality, high-definition videos based on text or image prompts in a wide range of cinematic and visual styles with exceptional speed. With an advanced understanding of natural language and visual semantics, it generates video that closely aligns to the prompt. Veo on Vertex AI creates footage that’s consistent and coherent, so people, animals, and objects move realistically throughout shots. See examples of Veo’s image-to-video generation capabilities on Vertex AI below: 

Image-to-video: Veo generates videos from existing or AI-generated images. Below are examples of how Veo uses images generated using Imagen 3 (top two images) and real-world images (bottom two images) to create short video clips.

Text-to-video: Below are examples of how Veo uses text to create short video clips.

Veo on Vertex AI empowers companies to effortlessly generate high-quality videos from simple text or image prompts. This means faster production, reduced costs, and the ability to quickly prototype and iterate on video content. Veo’s technology can be a great partner for human creativity by allowing creators to focus on higher-level tasks while AI can help handle tedious or repetitive aspects of video production. Customers like Agoda are using the power of AI models like Veo, Gemini, and Imagen to streamline their video ad production, achieving a significant reduction in production time. Whether you’re a marketer crafting engaging social media posts, a sales team creating compelling presentations, or a production team exploring new concepts, Veo streamlines your workflow and unlocks new possibilities for visual storytelling. 

Imagen 3: Our highest quality image generation model, now generally available on Vertex AI 

Imagen 3 is our highest quality text-to-image model. It generates an incredible level of detail, producing photorealistic, lifelike images, with far fewer distracting visual artifacts than our prior models. 

Starting next week, all Google Cloud customers will be able to access Imagen 3 on Vertex AI. With Imagen 3 on Vertex AI, you can generate high definition images and videos from a simple text prompt. See examples of Imagen 3’s image generation capabilities below:

Additionally, we’re making new features generally available to customers on our allowlist that help companies edit and customize images to meet their business needs. To join the allowlist, apply here. 

• Imagen 3 editing provides a powerful and user-friendly way to refine and tailor any image. You can edit photos with a simple text prompt, edit only parts of an image (mask-based editing) including updating product backgrounds, or upscale the image to meet size requirements.

• Imagen 3 Customization provides greater control by guiding the model to generate images with your desired characteristics. It is now  possible to infuse your own brand, style, logo, subject or product features when generating new images. This opens up new creative possibilities as it accelerates development by augmenting the marketing process for advertising and marketing assets.

Build with enterprise safety and security 

Designing and developing AI to be secure, safe, and responsible is paramount. Consistent with our AI Principles, Veo and Imagen 3 on Vertex AI were built with safety at the core. 

• Digital watermarking: Google DeepMind’s SynthID embeds invisible watermarks into every image and frame that Imagen 3 and Veo produce, helping decrease misinformation and misattribution concerns.

• Safety filters: Veo and Imagen 3 both have built-in safeguards to help protect against the creation of harmful content and adhere to Google’s Responsible AI Principles. We will continue investing in new techniques to improve the safety and privacy protections of our models. 

• Data governance: We do not use customer data to train our models, in accordance with Google Cloud’s built-in data governance and privacy controls. Your customer data is only processed according to your instructions.

• Copyright indemnity: Our indemnity for generative AI services offers peace of mind with an industry-first approach to copyright concerns.

Customers delivering value with Veo and Imagen on Vertex AI

Leading consumer packaged goods company Mondelez International, which includes brands such as Chips Ahoy!, Cadbury, Oreo, and Milka, is using generative AI to accelerate and enhance campaign content creation, allowing rapid development of consumer-ready visuals at scale for 100+ brands sold in 150 countries.

“Our collaboration with Google Cloud has been instrumental in harnessing the power of generative AI, notably through Imagen 3, to revolutionize content production. This technology has enabled us to produce hundreds of thousands of customized assets, enhancing creative quality while significantly reducing both time to market and costs. With the introduction of Veo, Mondelez and its agency partners (Accenture, Publicis, The Martin Agency, VCCP, Vayner and WPP) are poised to expand these capabilities into video content, further streamlining production processes and setting new benchmarks in marketing.” — Jon Halvorson, SVP of Consumer Experience & Digital Commerce, Mondelez International

“Mondelez is embarking on a bold journey of AI-driven transformation, partnering strategically with Google Cloud as our core AI platform. This is not simply a technology adoption; it’s a deep, collaborative partnership leveraging Google’s cutting-edge AI capabilities and infrastructure to fuel our innovation and growth ambitions. This partnership reinforces Mondelez’s commitment to continuous adoption of leading-edge technology to advance our business capabilities.” — Tiffani Sossei, SVP Chief Digital Experience Officer, Mondelez International

WPP is a world leader in marketing and communication services. Its AI-powered operating system for marketing transformation, WPP Open, already utilizes Imagen 3 for image generation and will soon incorporate Veo for video generation, streamlining the ideation and production of content. This expansion empowers WPP to unlock even greater levels of creativity and efficiency.

“At WPP, we believe in the transformative power of AI to enable our people to do their best work. We built WPP Open from the ground up and leverage Google Cloud’s AI capabilities within it to help bring to life the creative vision of clients such as L’Oréal, resulting in the production of compelling content and making iteration and concepting easier than ever before. With Veo and Imagen, we are narrowing the gap between imagination and execution, enabling our people to develop high-quality, photo-realistic, campaign-ready visuals in a matter of minutes.” – Stephan Pretorius, Chief Technology Officer, WPP

Agoda is a digital travel platform that helps travelers see the world for less with its great value deals on a global network of over 4.5M hotels and holiday properties worldwide, plus flights, activities, and more. They’re now testing Imagen and Veo on Vertex AI to create visuals, allowing Agoda teams to generate unique images of travel destinations which would then be used to generate videos.

“At Agoda, we’re committed to helping people see the world for less and making travel experiences more accessible. We are exploring the media generation capabilities of Google Cloud AI, using Imagen to create unique visuals of dream destinations in various styles. These images are then brought to life as videos through experiments with Veo’s image-to-video technology. These technologies hold the potential to streamline our content creation process from days to hours. By continuing our testing, we aim to explore how this combination can enhance creative possibilities and personalized advertising efficiently. With these tools, we hope to engage customers meaningfully and inspire future adventures.” – Matteo Frigerio, Chief Marketing Officer, Agoda

Quora, a leading online platform for people worldwide to share knowledge and learn from each other, has developed Poe, a platform that allows users to interact with leading gen AI models, including Gemini, Imagen, and now Veo through Vertex AI. With Veo and Imagen, Poe users can unlock new levels of creativity and bring their ideas to life with incredible ease and speed.

“We created Poe to democratize access to the world’s best gen AI models. With Veo, we’re now enabling millions of users to bring their ideas to life through stunning, high-quality generative video. Through partnerships with leaders like Google, we’re expanding creative possibilities across all AI modalities. We can’t wait to see what our community creates with Veo.” – Spencer Chan, Product Lead, Poe by Quora 

Honor is a leading global provider of smart devices. They are now bringing the power of AI image generation directly to consumers’ fingertips by integrating Imagen into millions of smartphones. This allows users to easily enhance and customize their photos with features like outpainting and stylization.

“At Honor, we’re committed to delivering cutting-edge technology that our millions of users can implement to enhance their daily lives. We chose to integrate Imagen on Vertex AI because it provides outstanding image generation capabilities that are both powerful and user-friendly. With Imagen, our customers can effortlessly create, edit, and reimagine images directly on their smartphones, transforming everyday moments into extraordinary visuals. We look forward to innovating with Google Cloud as their latest generative media models continue to push the boundaries of creative expression.” – George Zhao, CEO, Honor

Get started

To get started with Veo on Vertex AI,  reach out to your Google Cloud account representative. To get started with Imagen on Vertex AI, find our documentation. You’ll be able to access Imagen 3 on Vertex AI starting next week.

_{1. Source}