Google launched Veo, an advanced AI model, at its I/O 2024 developer conference. This model can reportedly generate high-quality, 1080 p video clips up to one minute in length from a text prompt.
Veo captures various visual and film styles, such as landscapes and time lapses, and is capable of editing and adjusting the footage produced. Some unique features of Veo include its ability to handle camera movements like "pan," "zoom," and "explosion,” understand physics like fluid dynamics and gravity to add realism, support masked editing for specific video sections, and generate videos from a still image.
Analyst QuickTake: This model offers an alternative to current leading video generation models, including OpenAI’s Sora, and solutions offered by startups like Runway, Pika, and Irreverent Labs.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.