May 20, 2025

[[read-time]] min read

Eli Collins

VP, Google DeepMind

Today, we’re announcing our newest generative media models, which mark significant breakthroughs. These models create breathtaking images, videos and music, empowering artists to bring their creative vision to life. They also power amazing tools for everyone to express themselves.

Veo 3 and Imagen 4, our newest video and image generation models, push the frontier of media generation, with their groundbreaking new capabilities. We’re also expanding access to Lyria 2, giving musicians more tools to create music. Finally, we’re inviting visual storytellers to try Flow, our new AI filmmaking tool. Using Google DeepMind’s most advanced models, Flow lets you weave cinematic films with more sophisticated control of characters, scenes and styles, to bring your story to life.

We’ve partnered closely with the creative industries — filmmakers, musicians, artists, YouTube creators — to help shape these models and products responsibly and to give creators new tools to realize the possibilities of AI in their art.

Veo 3: Video, meet audio

Veo 3, our new state-of-the-art video generation model, not only improves on the quality of Veo 2, but for the first time, can also generate videos with audio — traffic noises in the background of a city street scene, birds singing in a park, even dialogue between characters.

Across the board, Veo 3 excels from text and image prompting to real-world physics and accurate lip syncing. It’s great at understanding; you can tell a short story in your prompt, and the model gives you back a clip that brings it to life. Veo 3 is available today for Ultra subscribers in the United States in the Gemini app and in Flow. It’s also available for enterprise users on Vertex AI.

Veo 2 updates: New capabilities built with and for filmmakers

As we advance Veo 3, we’ve also added new capabilities to our popular Veo 2 model informed by our work with creators and filmmakers. Today, we’re launching several of these new capabilities, including:

• Our state-of-the-art reference powered video capability allows you to give Veo images of characters, scenes, objects, and even styles for better creative control and consistency.
• Camera controls help you define precise camera movements, including rotations, dollies and zooms, to achieve the perfect shot.
• Outpainting allows you to broaden your frame, turning your video from portrait to landscape, and making it easier to fit any screen size, intelligently adding to the scene.
• Object add and remove lets you add or erase objects from your videos. Veo understands scale, interactions, and shadows, and uses this understanding to create a natural, realistic-looking scene.

Reference powered video and camera controls are available now in Flow. We’re excited to bring all these new capabilities to the Vertex AI API in the coming weeks, and to more products over the next few months.

Flow: An AI filmmaking tool designed for Veo

Built with and for creatives, Flow is an AI filmmaking tool that lets you seamlessly create cinematic clips, scenes and stories by bringing together Google DeepMind’s most advanced models: Veo, Imagen and Gemini. Use natural language to describe your shots to Flow, manage the ingredients for your story — cast, locations, objects and styles — in a single convenient place, and use Flow to weave your narrative into beautiful scenes.

Flow is available today for Google AI Pro and Ultra plan subscribers in the U.S., with more countries coming soon.

Imagen 4: Stunning quality and superior typography

Our latest Imagen model combines speed with precision to create stunning images. Imagen 4 has remarkable clarity in fine details like intricate fabrics, water droplets, and animal fur, and excels in both photorealistic and abstract styles. Imagen 4 can create images in a range of aspect ratios and up to 2k resolution – even better for printing or presentations. It is also significantly better at spelling and typography, making it easier to create your own greeting cards, posters and even comics.

Imagen 4 is available today in the Gemini app, Whisk, Vertex AI and across Slides, Vids, Docs and more in Workspace.

Soon we’ll also be launching a fast variant of Imagen 4 that’s up to 10x faster than Imagen 3 — so you can explore ideas even faster.

Lyria 2: Powerful composition and endless exploration

In April, we expanded access to Music AI Sandbox, powered by Lyria 2. Music AI Sandbox offers musicians, producers and songwriters a set of experimental tools, which can spark new creative possibilities and help artists explore unique musical ideas. The expertise and valuable feedback from the music industry help us ensure our tools empower creators, while inviting creatives to realize the possibilities of AI in their art.

Lyria 2 brings powerful composition and endless exploration, and is now available for creators through YouTube Shorts and enterprises in Vertex AI. We’ve also made Lyria RealTime, our interactive music generation model which powers MusicFX DJ, available via an API and in AI Studio. Lyria RealTime allows anyone to interactively create, control, and perform generative music in real time.

Responsible creation and collaboration with the creative community

Since launching in 2023, SynthID has watermarked over 10 billion images, videos, audio files and texts, helping identify them as AI-generated and reduce the chances of misinformation and misattribution. Outputs generated by Veo 3, Imagen 4 and Lyria 2 will continue to have SynthID watermarks.

Today, we’re launching SynthID Detector, a verification portal to help people identify AI-generated content. Upload a piece of content and the SynthID Detector will identify if either the entire file or just a part of it has SynthID in it.

With all our generative AI models, we aim to unleash human creativity and enable artists and creators to bring their ideas to life faster and more easily than ever before.