Google Unveils Veo Video and Imagen 3 Image Generators
Google introduces Veo, a high-definition video generation model, and Imagen 3, an advanced text-to-image tool, both developed alongside artists. The company emphasizes responsible deployment through safety filters and digital watermarks.
Google unveils Veo, its most advanced video generation model capable of producing high-quality 1080p resolution videos that extend beyond a minute. The model understands natural language and visual semantics deeply, allowing it to accurately capture the tone and specific details of user prompts across a wide range of cinematic styles.
Alongside Veo, Google releases Imagen 3, its highest quality text-to-image model to date, which creates photorealistic images with significantly fewer artifacts than previous versions. The tech giant also shares new demo recordings created with its Music AI Sandbox through collaborations with notable artists like Donald Glover, Wyclef Jean, Marc Rebillet, and Justin Tranter.
To ensure safe deployment, Google implements rigorous safety tests, filters, and guardrails alongside digital watermarks for all AI-generated content. Users can currently join a waitlist to access Veo and Imagen 3 as the company continues to refine these generative media tools in partnership with the creative community.