The world of image generation through artificial intelligence it is moving too fast. It is even difficult to keep up with everything that is coming out. Last week, Meta it showed the world that they were in this business too. Zuckerberg's people showed a series of short videos that they had managed to generate with a simple text input. It's barely been a week, but Google has already surpassed the level of those of Facebook with Image Video, an intelligence that seems to have a lot of potential.
Keeping up with advances in AI is exhausting
We are in an unprecedented historical moment. Some artificial intelligence applications they are developing so fast that there is barely time to process one new technology when the next one has arrived to surpass it. A little over a month ago stable diffusion it was billed as a free and open source AI. A true revolution.
Last week, dreambooth It changed the way of using Stable Diffusion, since the system allows you to train the AI with your face or any type of concept that comes to mind. DreamBooth initially required professional Nvidia hardware, but in a matter of hours, the community had made as many forks that it ended up being possible to run the program on a home computer. It was not the only important news of the week either. Meta also showed the world his progress in this sector. They showed a series of short videos of AI-generated figures. as we said, Google has not taken long to surpass its competition.
Google takes a step forward with the 'text to video'
A few weeks ago, the popularizer Carlos Santana (dotcsv) asked on YouTube if it was possible make a movie with an AI. In his presentation, the artificial intelligence expert saw that the scenario was still complicated, but not impossible.
As we say, this world advances at a very frenetic pace. Just yesterday, Google taught the world Image Video, an artificial intelligence capable of generating short videos using a natural language text command. The project was introduced on Twitter by Jonathan Ho. The programmer showed a small five-second video of leaves falling into a lake forming the words 'Image Video'. On the surface, it doesn't seem like anything spectacular, but the truth is that, to date, virtually none of the AIs we know of can generate text within images.
Excited to announce Image Video, our new text-conditioned video diffusion model that generates 1280×768 24fps HD videos! #ImageVideohttps://t.co/JWj3L7MpBU
Work w/ @wchan212 @chitwan_saharia @jaywhang_ @RuiqiGao @agritsenko @dpkingma @poolio @mo_norouzi @fleet_dj @TimSalimans pic.twitter.com/eN81LqZW7I— Jonathan Ho (@hojonathanho) October 5, 2022
The post link shows a bit more about this technology. It is a extra application of Google Image Research, which works very similar to Dall-E 2. Google Image Video allows you to create clips with HD resolution (1280 by 768 pixels) at 24 frames per second. The difference compared to what Meta showed last week is notable, since Mark Zuckerberg's company simply showed some renders of vector objects that rotated around a camera. Not at all, a result as striking and useful as this technology that those from Mountain View have just presented.
The aim of this publication is clearly to show the world that they are ahead of Meta in this field. However, it is still early to know what future plans Google has with this program.