AI mage generators were all the craze last year, but now companies are shifting focus to the next frontier — AI video generation. With OpenAI launching its AI text-to-video generator, Sora, earlier this year, it was time for Google to launch its own — and the company delivered.
On Tuesday, at its annual Google I/O developer conference, Google revealed Veo, its most advanced text-to-video generator, capable of generating videos with 1080p resolution that are over one minute long.
Also: Everything announced during Google I/O 2024: Gemini, Search, Android 15, and more
In addition to the high quality of the outputs, Google said, Veo provides users with an “unprecedented level of creative control.” The AI generator’s deeper understanding of natural language enables Veo to deliver more details from longer prompts and to understand cinematic terms like “timelapse” or “aerial shots.”
Additionally, the video generator can tackle a common problem with video generation — the fluidity of shots. According to Google, Veo can create consistent footage, with different subjects such as people, animals, and objects moving realistically in the shots.
Google isn’t new to video generation: The company acknowledged that this model builds on all of the company’s prior video-generating projects, including Imagen-Video, VideoPoet, and Lumiere.
Like OpenAI’s Sora, Google’s Veo is not available to the public just yet. Rather, Veo is being shared first with a select number of creators in a private preview inside VideoFX. However, the public is invited to join a waitlist if they are interested in trying the model for themselves.
Additionally, Google unveiled Imagen 3, its highest-quality text-to-image model to date. The model, which boasts improved image quality and fewer visual artifacts, also will be limited to a private preview inside ImageFX for select creators and a waitlist for the public.
