/w=3840,quality=90,fit=scale-down)
Raphael Thys
image excerpt from Google’s 2022 AI@event
Google just recently hosted its AI@ event in which the company shares the latest research in the fields of robotics, natural language understanding, accessibility, healthcare, and creativity.
I highly recommend that you watch the whole event available here, but there was one reveal I want to mention that simply blew me away.
I know this technology is already available in some capacity but seeing it demonstrated with such simplicity, solidifies how magical this really is.
The technology I am referring to is the ability to produce high-resolution, long form video, generated entirely from a sequence of prompts.
How Is This Done?
Google has been working on two complimentary text-to-video models, from two different research groups, and has now merged the best of both models.
The first is Imagen Video, similar to how Imagen Image AI works (diffusion technique), is a text-to-video generator that can produce short video clips.
The second is Phenaki, a language model capable of realistic video synthesis when given a sequence of textual prompts.
When you combine the high-quality generative model of Imagen with the token sequence coherence of Phenaki, you get long-form high-resolution video output.
If you want to see the demo that was presented on this at the event, simply click play… (the demo of this video feature is only several minutes).
A New Form Of Storytelling
Imagine simply writing a story with a sequence of prompts, and having AI generate a video for you.
This new AI magic will unlock the power of storytelling for anyone, everywhere, driven by the power of creative imagination.
While it looks a bit rudimentary right now, we have seen how fast AI art has matured in just a short amount of time. There is no doubt that this AI video technology will progress rapidly.
According to Alonso Martinez, a lead AI researcher at Google, he predicts that we may see a major television show produced using AI in as little as two years.
Final Thoughts
Just like we are seeing AI images in our twitter, discord, and instagram feeds, it won’t be long before we start seeing AI videos in our YouTube and TikTok feeds.
I understand this might be a bit scary for videographers and video editors, just like AI art has been with artists and illustrators, but this is simply a new tool, a new camera for the video artist.
This opens up new and exciting possibilities for video storytelling. It’s a magical time.
If you liked this article, please hit the follow button for more articles like this in the future.