Artificial intelligence is coming for video but that’s not really anything new.
Hey, we’ve covered articles about AI-generated holograms impersonating dead people, among other topics.
But what is big news is when a major name like Stable Diffusion enters this space.
And that’s exactly what just happened as the company just announced Stable Video Diffusion, a generative AI platform capable of transforming thoughts into video.
One of the major techniques demonstrated is the ability of Stable Video Diffusion to take a still image and turn it into a video. Of course, the technical language behind this process is a little more involved.
“Our video model can be easily adapted to various downstream tasks, including multi-view synthesis from a single image with finetuning on multi-view datasets. We are planning a variety of models that build on and extend this base, similar to the ecosystem that has built around stable diffusion.”
Specific use cases that Stable Video Diffusion envisions for its platform include “advertising, education, entertainment, and beyond,” or, essentially, everything.
So, if you were someone worried about whether or not AI was coming after your job, you probably wouldn’t find any comfort here. The company then compares SVD to notable competitors in the space to show that, even though they’re just coming out of the gate with this, they’re pretty much on par with the rest of the playing field. As mentioned in the beginning of the article, Stable Diffusion is sort of a big deal in the AI world and their move into video is a pretty big moment for that nascent technology.
You can watch a video showing it off on YouTube at this link.
Let us know what you think of generative AI for video in the comments below.
We have some more photography news at this link right here.