AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Control Net: A Language Vision Model
We are using off-the-shelf models like we use text encoder, we use G-lib, an image encoder. There is now 3D encoder as of now, you know, that we use. But of course, maybe I will mention about that we are working on such models as well. And then finally, we also wanted to kind of briefly talk about one of the demos that you're showing. This one is the control net demo. What's a demo trying to show? Absolutely. It's the generated AI, LDM, language vision model. You can type some textual description and give an image of a reference image. And then it will create AI