AI image generators were all the rage in 2023, but now companies are shifting their focus to the next frontier: AI video generation. With OpenAI announcing its AI text video generator Sora in February 2024, it was only a matter of time before Google did something similar.
On Tuesday, at the annual Google I/O developer conference, Google announced Veo, its most advanced text-to-video generator, capable of producing 1080p resolution videos over a minute long.
Google says that in addition to high-quality output, Veo offers users an “unprecedented level of creative control.” The AI generator's deep understanding of natural language allows Veo to provide more detailed information from longer prompts and understand film terms like “time-lapse” and “aerial shot.”
Related article: Everything announced at Google I/O 2024: Gemini, search, Android 15 and more
Additionally, the video generator can also address a common problem with video generation: shot fluidity. Google says Veo can create consistent footage where a variety of subjects, including people, animals, and objects, move realistically within the shot.
Google is not new to video generation. The company noted that this model is based on all previous video generation projects, including Imagen-Video, VideoPoet, and Lumiere.
Like OpenAI's Sora, Google's Veo is not yet publicly available. Rather, Google is first sharing Veo with selected creators in a private preview within his VideoFX. However, Google recommends that you join the waiting list to finally try this model.
Additionally, Google announced Imagen 3, its highest quality text-to-image conversion model to date. Imagen 3 has improved image quality and reduced visual artifacts, but private previews within ImageFX are limited to some creators and have their own waiting list.
