"Creators' New Generative Media Tools Unveiled"

Over the past year, we've made significant strides in improving our generative media technologies. Our focus has been on collaborating with the creative community to understand how generative AI can enhance the creative process at every stage. We're excited to introduce Veo, our most advanced video generation model to date, and Imagen 3, our highest quality text-to-image model yet.

We're also thrilled to share some of our recent partnerships, including those with filmmaker Donald Glover and his creative studio, Gilga, as well as new demo recordings from artists Wyclef Jean, Marc Rebillet, and songwriter Justin Tranter, all created with the assistance of our Music AI Sandbox.

Veo: Our Most Capable Video Generation Model

Veo is designed to generate high-quality videos at 1080p resolution, accommodating a variety of cinematic and visual styles that can extend beyond a minute. Thanks to its advanced understanding of natural language and visual semantics, Veo can produce videos that closely align with a user's creative vision, accurately capturing the tone and details specified in longer prompts.

This model offers an unprecedented level of creative control, understanding cinematic terms like "timelapse" or "aerial shots of a landscape." Veo ensures that the footage remains consistent and coherent, with realistic movement of people, animals, and objects throughout the shots.

[ttpp]Examples of Veo's high-quality video generation capabilities. All videos were generated by Veo and have not been modified.[yyxx]

To better understand how Veo can enhance the storytelling process, we're inviting a diverse group of filmmakers and creators to experiment with the model. These collaborations not only help us refine our technology but also ensure that creators have a say in its development.

Here's a sneak peek at our work with filmmaker Donald Glover and his creative studio, Gilga, who have been experimenting with Veo for a film project.

[ttpp]Veo builds upon years of our generative video model work, including Generative Query Network (GQN), DVD-GAN, Imagen-Video, Phenaki, WALT, VideoPoet, and Lumiere — combining architecture, scaling laws, and other novel techniques to improve quality and output resolution.[yyxx]

With Veo, we've enhanced techniques for understanding video content, rendering high-definition images, and simulating real-world physics. These advancements will drive further progress in our AI research and help us develop even more useful products that enhance how people interact and communicate.

Starting today, Veo is available to select creators in a private preview on VideoFX. You can join our waitlist to try it out. In the future, we'll also integrate some of Veo's capabilities into YouTube Shorts and other products.

Learn more about Veo's capabilities.

Imagen 3: Our Highest Quality Text-to-Image Model

Over the past year, we've seen remarkable improvements in the quality and fidelity of our image generation models and tools.

Imagen 3 stands out as our highest quality text-to-image model, capable of generating incredibly detailed, photorealistic, and lifelike images with far fewer visual artifacts than our previous models.

[ttpp]Prompt: A close up of a sleek wolf perched regally in front of gray background, in a high-resolution photograph with detailed fine details, isolated on a plain stock photo with color grading in the style of a hyper-realistic style.

Prompt: Close-up of a jellyfish pulsating through crystal-clear water, tentacles trailing, vibrant coral reef background, macro photography, stock photo, high resolution, very detailed, soft lighting, professional color grading, shallow depth of field, sharp focus, taken with a DSLR camera in the style of professional photographers.

Prompt: View from above of beautiful river canyon with trees, showcasing its stunning natural beauty with green mountains and blue waters. The photo captures the vastness of nature's creation in the style of its creation.

Prompt: Shot in the style of DSLR camera with the polarizing filter. A photo of two hot air balloons floating over the unique rock formations in Cappadocia, Turkey. The colors and patterns on these balloons contrast beautifully against the earthy tones of the landscape below. This shot captures the sense of adventure that comes with enjoying such an experience.

Prompt: A pair of well-worn hiking boots, caked in mud and resting on a rocky trail. The head of a squirrel is poking out of one of the boots, and it looks lazily at the camera, a little king of its shoe. The laces of both boots fall loosely to the ground. There's a mountainous landscape in the background. Cinematic movie still, high quality DSLR photo.

Prompt: Three women stand together laughing, with one woman slightly out of focus in the foreground. The sun is setting behind the women, creating a lens flare and a warm glow that highlights their hair and creates a bokeh effect in the background. The photography style is candid and captures a genuine moment of connection and happiness between friends. The warm light of golden hour lends a nostalgic and intimate feel to the image.[yyxx]

Imagen 3 has a better grasp of natural language, understanding the intent behind your prompt and incorporating small details from longer prompts. Its advanced understanding allows it to master a variety of styles.

[ttpp]Prompt: A photo of a man with short hair and beard smiling at the camera. The background is blurry and it shows trees and buildings in light colors.

Prompt: A view of a person's hand as they hold a little clay figurine of a bird in their hand and sculpt it with a modeling tool in their other hand. You can see the sculptor's scarf. Their hands are covered in clay dust. a macro DSLR image highlighting the texture and craftsmanship.

Prompt: Abstract sketch: A blur of expressive lines and energy captures the dynamic movement of a dancer in a gestural charcoal drawing. Sketch on aged parchment paper.

Prompt: Elephant amigurumi walking in savanna, a professional photograph, blurry background.

Prompt: The girl in white dress stood on the bank of an endless lake, holding flowers and looking at the sky full of pink clouds. The sky is reflected by the water surface, creating a beautiful anime scene. There were small hills covered with wildflowers around her, adding to its beauty. Anime style background, purple blue tone, soft light, warm colors, dreamy atmosphere, and romantic emotions.

Prompt: A weathered, wooden mech robot covered in flowering vines stands peacefully in a field of tall wildflowers, with a small bluebird resting on its outstretched hand. Digital cartoon, with warm colors and soft lines. A large cliff with waterfall looms behind.[yyxx]

Imagen 3 is also our best model yet for rendering text, overcoming challenges that image generation models typically face. This opens up new possibilities for creating personalized birthday messages, title slides in presentations, and more.

[ttpp]Prompt: A photograph of a stately library entrance with the words "Central Library" carved into the stone.

Prompt: An origami owl made of brown paper is perched on a branch of an evergreen tree. The owl is facing forward with its eyes closed, giving it a peaceful appearance. The background is a blur of green foliage, creating a natural and serene setting.

Prompt: Photo of a felt puppet diorama scene of a tranquil nature scene of a secluded forest clearing with a large friendly, rounded robot is rendered in a risograph style. An owl sits on the robots shoulders and a fox at its feet. Soft washes of color, 5 color, and a light-filled palette create a sense of peace and serenity, inviting contemplation and the appreciation of natural beauty.

Prompt: Pixel art of a space shuttle blasting of. Cape Canaveral in the background, blue skies, with plumes of smoke billowing out. "STS-1" is written below it.

Prompt: Word “light” made from various colorful feathers, black background.

Prompt: Claymation scene. A medium wide shot of an elderly woman. She is wearing flowing clothing. She is standing in a lush garden watering the plants with an orange watering can.[yyxx]

Starting today, Imagen 3 is available to select creators in a private preview on ImageFX. Join our waitlist to try it out. Imagen 3 will soon be available on Vertex AI.

Learn more about Imagen 3's capabilities.

Our Collaborations with the Music Community

As we continue to explore the role of AI in art and music creation, we're partnering with YouTube and collaborating with talented musicians, songwriters, and producers.

These collaborations are helping us develop our generative music technologies, including Lyria, our most advanced model for AI music generation.

We've been working on a suite of music AI tools called Music AI Sandbox, designed to spark creativity by allowing users to create new instrumental sections, transform sounds in innovative ways, and much more.

[ttpp]Today, we're continuing that experimentation in music with Grammy-winning musician Wyclef Jean, Grammy-nominated songwriter Justin Tranter, and electronic musician Marc Rebillet — who are releasing new demo recordings on their YouTube channels, created with help from our music AI tools.[yyxx]

[ttpp]The first demos from Wyclef Jean, Justin Tranter, and Marc Rebillet are now available for listening on their YouTube channels. Each demo is a testament to the exciting possibilities that AI can bring to music creation.[yyxx]

Responsible from Design to Deployment

We're committed not only to advancing the state of the art but also to doing so responsibly. We're taking steps to address the challenges posed by generative technologies and to help people and organizations work responsibly with AI-generated content.

For each of these technologies, we've been engaging with the creative community and other external stakeholders, gathering insights and feedback to improve and deploy our technologies safely and responsibly.

We've conducted safety tests, applied filters, set guardrails, and placed our safety teams at the heart of development. Our teams are also developing tools like SynthID, which can embed imperceptible digital watermarks into AI-generated images, audio, text, and video. Starting today, all videos generated by Veo on VideoFX will be watermarked by SynthID.

The creative potential of generative AI is vast, and we're eager to see how people worldwide will use our new models and tools to bring their ideas to life.

[ttpp]Get more stories from Google in your inbox.Get more stories from Google in your inbox.

Email addressYour information will be used in accordance withGoogle's privacy policy.

SubscribeDone. Just one step more.

Check your inbox to confirm your subscription.

You are already subscribed to our newsletter.

You can also subscribe with adifferent email address.[yyxx]