Google held its annual developer conference in Mountain View, California, focused on artificial intelligence announcements.
At the event, Google introduced Veo, a new generative AI model for video creation, and announced Imagen 3, its most advanced text-to-image model.
According to a Google blog post, “Over the past year, we've made incredible progress in improving the quality of generative media technology. We're working closely with the creative community to ensure that generative AI optimizes the creative process. We've been exploring ways in which we can support you and make sure our AI tools are as helpful as possible at every step of the way. Introducing the Imagen 3, a conversion model of We also share a new demo recording that writer Justin Tranter released with the help of Music AI Sandbox.
Google and the creative community have worked closely together to unlock the full potential of Google's AI products.
Veo: Google's VideoFX
Veo uses text cues to create stunning 1080p videos and understand cinematic ideas like “time-lapse” and “aerial shots.” Veo competes with Sora, a recently released text-to-video generator from OpenAI.
To highlight Veo's potential, Google partnered with director Donald Glover and his creative agency Gilga.
This partnership demonstrated how artificial intelligence is an important element in professional film production.
A select group of creators will be invited to participate in a private preview to learn more about VideoFX's Veo capabilities.
imagen 3
Imagen 3 produces highly detailed, photorealistic photos with low visual noise. Imagen 3 is very good at deciphering and understanding the subtleties of text prompts. Imagen 3 lets you create photos that include intricate wildlife portraits, dramatic landscapes, customized messages, and sophisticated presentations.
Imagen 3 demonstrated its ability to capture the complexity and beauty of a particular prompt through a series of produced photographs. Text rendering enhancements in Imagen 3 expand your application range.
Due to other users' queues, a limited number of creators can access Imagen 3 in a private preview within ImageFX.
Vertex AI will have Imagen 3 available soon.
