AI picture mills have been all the craze in 2023, however now corporations are shifting focus to the following frontier — AI video technology. With OpenAI unveiling its AI text-to-video generator, Sora, in February 2024, it was solely a matter of time earlier than Google did the identical.
On Tuesday, at its annual Google I/O developer convention, Google unveiled Veo, its most superior text-to-video generator, able to producing movies with 1080p decision which are over one minute lengthy.
Along with the high-quality output, Google says that Veo supplies customers with an “unprecedented degree of artistic management.” The AI generator’s deeper understanding of pure language permits Veo to ship extra particulars from longer prompts and to grasp cinematic phrases like “timelapse” or “aerial photographs.”
Moreover, the video generator can deal with a typical downside with video technology — the fluidity of photographs. Based on Google, Veo can create constant footage, with completely different topics akin to folks, animals, and objects transferring realistically within the photographs.
Google is not new to video technology. The corporate famous that this mannequin builds on all its prior video-generating tasks, together with Imagen-Video, VideoPoet, and Lumiere.
Like OpenAI’s Sora, Google’s Veo shouldn’t be out there to the general public but. Relatively, Google is sharing Veo first with choose creators in a personal preview inside VideoFX. Google does, nonetheless, invite that you just be a part of a waitlist to finally strive the mannequin.
Moreover, Google unveiled Imagen 3, its highest-quality text-to-image mannequin thus far. Imagen 3, which boasts improved picture high quality and fewer visible artifacts, can also be restricted to a personal preview inside ImageFX for choose creators and has its personal waitlist.
