Google unveils new AI models Veo and Imagen 3

Google has launched new generative media models Veo and Imagen 3 at Google I/O 2024.

Google unveils Veo and Imagen 3 to enhance video and image generation

At Google I/O 2024, Google introduced two new generative media models: Veo and Imagen 3. Veo targets high-definition video creation, capable of generating 1080p videos. Although it can create videos longer than a minute, specifics on the duration were not disclosed. The model's design involves understanding cinematic terms, demonstrated in a collaboration video featuring Donald Glover. Meanwhile, Imagen 3 is a text-to-image model that has improved natural language processing, rendering text more accurately. Both models are currently available to select users through VideoFX and ImageFX with a waiting list for others interested.

The release of Veo and Imagen 3 marks a significant step for Google in the competitive landscape of AI media generation. With Veo aiming to rival existing video generation tools, users will benefit from higher quality and more realistic content. Imagen 3 addresses previous shortcomings in text-to-image generation, potentially elevating the standard for AI tools in creative sectors. This could shift how marketing and content creation industries utilize AI, reflecting a progressive trend toward enhanced user experience in media.

Highlights

Such innovations reshape the digital landscape, influencing how creators work and engage with technology.