Google Unveils Veo and Imagen 3 at Developer Conference

Google introduces Veo, an advanced video generation model, and Imagen 3, a text-to-image model, at the annual Google I/O developer conference, emphasizing creative control and responsibility

Google Unveils Veo and Imagen 3 at Developer Conference

Google is quickly catching up to OpenAI, as just three months after the announcement of OpenAI's text-to-video generator, Sora, Google has introduced its own version. At the annual Google I/O developer conference on Tuesday (May 14), Google unveiled Veo, its latest and most advanced video generation model capable of creating 1080p resolution videos in a variety of cinematic and visual styles.

According to Google, "Veo builds upon years of our generative video model work, including Generative Query Network, DVD-GAN, Imagen-Video, Phenaki, WALT, VideoPoet, and Lumiere – combining architecture, scaling laws, and other novel techniques to improve quality and output resolution." The technology giant describes Veo's ability to generate videos as offering "an unprecedented level of creative control."

Similar to OpenAI's Sora, Google's newest tool is not yet available to the public. The company is currently working with select creators in a private preview to test its capabilities. Some features of Veo are expected to be integrated into YouTube Shorts and other products in the future.

In addition to Veo, Google has also introduced Imagen 3 at the conference. Imagen 3 is a text-to-image model that can produce photorealistic and lifelike images. Google states, "Imagen 3 better understands natural language, the intent behind your prompt, and incorporates small details from longer prompts. The model’s advanced understanding helps it master a range of styles." Like Veo, Imagen 3 will initially be available only to a select few users.

As Google shifts its focus to artificial intelligence, the company has also detailed its responsibility practices related to these new models. "We’re mindful about not only advancing the state of the art but doing so responsibly. So we’re taking measures to address the challenges raised by generative technologies and helping enable people and organizations to responsibly work with AI-generated content," the company stated.

Overall, the Google I/O developer conference revealed numerous surprises and significant advancements in AI technology, highlighting the company's commitment to innovation and responsible development.