Google has been quick to follow OpenAI's lead, with the search engine and technology company releasing its version just three months after announcing Sora, a text-to-video generator.
Veo was announced at the annual Google I/O developer conference event on Tuesday (May 14).
This is Google's newest and most advanced video generation model that allows you to create 1080p resolution videos in a variety of cinematic and visual styles.
“Veo builds on our years of generative video modeling work, including Generative Query Network, DVD-GAN, Imagen-Video, Phenaki, WALT, VideoPoet, and Lumiere, and improves architectures, scaling laws, and other emerging technologies. Combines quality and output resolution.
The ability to generate videos is described as an “unprecedented level of creative control.”
Similar to OpenAI's Sora, Google's latest debut is not yet available to the public as the team is only working with selected creators in a private preview for testing purposes.
Some of Veo's features will be used in future YouTube Shorts and other products.
Google Developer Conference Announcements – Veo and Imagen 3
Veo isn't the only new tool Google released this week, as the annual event brought more surprises.
In addition to the video model, the newly released Imagen 3 was also revealed. This is a text-to-image model that can produce photorealistic images.
Google says: “Imagen 3 better understands the natural language, the intent behind a prompt, and incorporates the finer details of long prompts. The advanced understanding of the model allows you to master different styles.”
Image created by Imagen 3. Prompt: Photo of a man with short hair and a beard smiling at the camera. The background is blurred and the buildings are brightly colored.
Again, image models are only available to a select few.
As the company shifts its focus to artificial intelligence, it announced details about its liability practices related to video and image models.
“We are mindful not only of advancing cutting-edge technology, but also of doing so responsibly. That is why we are addressing the challenges posed by generation technologies and ensuring that people and organizations are held accountable. We are taking steps to help customers work with AI-generated content.”
Featured image: Photo by Kai Wenzel on Unsplash
