NVIDIA’s New AI: Wow, 30X Faster Than Stable Diffusion!

Köszönjük a feliratkozóinkat! Ez volt 2 Minute Papers képessége Dr. Károly Zsolnai-Fehérről. Majdnem nézzük meg az NVIDIA-t az inkredible új AI-t, ami képességeket és többet készít. Now, wait a second! Stop right there! Every fellow scholar knows that today, there are plenty of text-to-image AIs out there, where in goes a piece of text, and out comes an image. They come in all kinds of flavors these days. Everyone knows. So our question today is, why publish this paper? Do we really need more of these? Well, this new paper is called StyleGAN-T. Keep your eyes on this part, because this means that this is a GAN-based technique. A GAN is a Generative Adversarial Network. This roughly means that we have not one, but two neural networks competing against each other, and as they compete, they get better together. Okay, that all sounds great, but I am still not convinced. What does this give us? Miért kéne ezt használnunk? Hát, ott van két egészség. Egészség növben, a GAN-ok egészségesek, a latent space interpellációban. Mi ez azt jelenti? Ez azt jelenti, hogy meg tudjuk készíteni ezeket az érdekes 2D állapotokat, képviselünk egy pontot a helyen, amely ebben a törvényben fontos, és a pontok közelében hide other fonts that are similar to this one. So as we start exploring nearby, we get a beautiful, smooth morphing animation between these fonts. In our earlier paper, we did something similar with photorealistic material models, so artists can find, or even better, adjust a material so that it fits their virtual worlds best. Hmm. So this new technique supposedly can do proper latent space exploration for not fonts and not materials, but for text-to-image. Supposedly. Nagyon köszönöm, hogy megnézted ezt a videót! Oh yes, now that's what I'm talking about! With this, we can get more continuous results, and can explore these latent spaces as much as we desire, and that is going to be super useful. You see, what we can do with this is that we write a prompt, for instance, a corgis head depicted as an explosion of a nebula. And we don't just get an image anymore, No, no, due to its amazing interpolation capabilities, we get an opportunity to not only witness the birth of the universe, but to choose the good boy that we find to be the most adorable. I choose this one, right before it morphs into a cat. Yes, this one will do. Which one is your favorite? Let me know in the comments below! So its latent space exploration capability is not only an afterthought here, it is one of the new technique's key features. Now, remember, I mentioned that this is reason number one of why we should use it. So what is reason number two? Well, two, it is fast. Real fast. But to know how fast exactly, let's pop the hood and have a look! Now, hold on to your papers, fellow scholars, and… What? 0.1 seconds per image? Is that really possible? Wow! These animations can be made practically in real time! The age of real-time AI image and even video synthesis is here! My goodness! It did not take decades, és még nem készült években. Más mint egy év múlva az OpenAI Dolly 2-t, amelynek kb. 10-15 percig kérdezett, itt vagyunk. Igazi idő. Nem igazán bízom. Wow. Ez igazán megmondható. De még nem ez a technika perfekt. Nézzük meg egy félretesztőt. Ez egy színtől, aki mondja, hogy képes lepni. Come on! This one again? Remember our moment with Dolly 2? It had the same issue. There are techniques out there that do much better on text, for instance, image and video is better for this, however, it is not nearly as fast as this one. Yes, that one is about a hundred times slower per image. So the perfect text-to-image AI still doesn't exist, every technique offers its own little trade-off, but man… a történetet. Tényleg a műsorokat. Thanks for watching and for your generous support, and I'll see you next time!