May 15, 2024 – In the wake of the groundbreaking launch of Sora, a text-to-video technology introduced by OpenAI three months ago, Google has unveiled its rival product, Veo, at the 2024 I/O Developer Conference today. Veo boasts the ability to generate “high-quality” videos exceeding one minute in length, with a resolution of up to 1080P, and offers a diverse range of visual and cinematic styles.
According to Google’s official press release, Veo possesses advanced comprehension of natural language, comprehending cinematic terms such as “time-lapse photography” and “aerial landscape shots.” Users can guide their desired outputs using text, image, or video prompts, and Google claims that the resulting videos are “more coherent and consistent,” with lifelike movements for characters, animals, and objects throughout the scenes.
In a media preview on Monday, Google DeepMind’s CEO Demis Hassabis revealed that video results can be further refined through additional prompts, and the company is exploring additional features to enable Veo to create storyboards and longer sequences. The introduction of Veo marks a significant step in Google’s efforts to leverage artificial intelligence for video content creation, positioning it as a formidable competitor in the rapidly evolving field of text-to-video technologies.
