Google hosted its annual developers conference in Mountain View, California, focusing on artificial intelligence announcements.
At the event, Google introduced Veo, a new generative AI model for video creation, and unveiled Imagen 3, its most advanced text-to-image model.
As per Google’s blog post, “Over the past year, we’ve made incredible progress in enhancing the quality of our generative media technologies. We’ve been working closely with the creative community to explore how generative AI can best support the creative process, and to make sure our AI tools are as useful as possible at each stage. Today, we’re introducing Veo, our latest and most advanced video generation model, and Imagen 3, our highest quality text-to-image model yet. We’re also sharing some of our recent collaborations with filmmaker Donald Glover and his creative studio, Gilga, and new demo recordings being released by artists Wyclef Jean, Marc Rebillet and songwriter Justin Tranter, made with help from our Music AI Sandbox.”
Google and the creative community have been collaborating closely to maximize the potential of Google’s AI products.
Veo: Google’s VideoFX
With text cues, Veo can create stunning 1080p videos and comprehend cinematic ideas like “timelapse” and “aerial shots.” Veo is in competition with Sora, the recently released text-to-video generator from OpenAI.
To highlight Veo’s potential, Google partnered with director Donald Glover and his creative agency, Gilga.
The partnership showed how artificial intelligence might be a crucial component of professional filmmaking.
To learn more about Veo’s features in VideoFX, a select group of creators is invited to participate in a private preview.
Imagen 3
Imagen 3 produces highly detailed, photorealistic photos with less visual noise. Imagen 3 is quite good at deciphering and figuring out the subtleties of text prompts. Imagen 3 is capable of producing photographs for intricate wildlife portraits, dramatic landscapes, customized messages, and polished presentations.
Imagen 3 demonstrated its ability to capture the intricacy and aesthetic of particular prompts through a sequence of produced photos. Imagen 3’s increased text rendering increases its range of applications.
With a queue for others, Imagen 3 is accessible to a limited number of creators in a private preview within ImageFX.
Vertex AI will soon have Imagen 3 available.
