Google’s latest generative AI video model, Veo, is now available for businesses to incorporate into their content creation pipelines. Veo can generate high-quality 1080p videos in various styles from text or image-based prompts, rivaling human-created clips.
The model was initially announced with short clips, but the preview release allows for longer content. The latest version of Google’s Imagen 3 text-to-image generator will also be available on Vertex AI starting next week, expanding its initial US release.
Veo carries built-in safeguards to prevent harmful or copyrighted content and features DeepMind’s SynthID technology, which can reduce misinformation concerns. This technology is similar to Adobe’s Content Credentials system.
As Veo enters the market, OpenAI’s competing Sora product lags behind, prompting companies to invest in generative AI now rather than waiting for its release by the end of 2024. With 86% of organizations seeing revenue increases using generative AI, businesses are taking advantage of this technology.
Source: https://www.theverge.com/2024/12/4/24312938/google-veo-generative-ai-video-model-available-preview