Google announced Veo, its latest generative AI video model and answer to OpenAI. sky creation engine. According to the company, the unique model can produce over 1 minute of “high quality” 1080p resolution video in a variety of visual and cinematic styles.
Veo features an “advanced understanding of natural language,” which is said to allow it to understand film terms such as “time-lapse” and “aerial landscape photography.” Users can direct the desired output and generate footage using text, image, or video-based prompts.
Google claims that the resulting videos are “more coherent and consistent” and depict more realistic movement of people, animals, and objects throughout the shot. This can be further adjusted using additional prompts, but additional features are currently being considered that will allow you to create storyboards and longer scenes in Veo.
To show off the model's capabilities, the company partnered with Donald Glover and his creative studio Gilga. Very short promotional videos show celebrities and staff using text to create videos of different scenes and scenarios.
Google's new generative AI model will be rolled out “in the coming weeks” as a special preview of the VideoFX tool for some creators, but those interested can Join the waiting list This is your chance to try it out early. Additionally, Google says it plans to add some of Veo's features to YouTube Shorts “in the future.”
(Source: Google [official blog])
follow me Instagram, Facebook, twitter or telegram For more updates and the latest news, please visit here.
