Hi professor, can I understand this like that the entire training is to find an approximate latent representation of the input images as real as possible?
Your question is quite big and to answer it i would suggest you to please have a look at this video to clear your fundamentals. th-cam.com/video/mMa2PmYJlCo/w-d-xo.html
![The moment we stopped understanding AI [AlexNet]](http://i.ytimg.com/vi/UZDiGooFs54/mqdefault.jpg)
![VQGAN: Taming Transformers for High-Resolution Image Synthesis [Paper Explained]](/img/n.gif)
Love it, great content. Will you share diffusion model content too?
Yes, definitely, it is live now.. th-cam.com/video/W2udr9Z73sA/w-d-xo.html
Hi professor, can I understand this like that the entire training is to find an approximate latent representation of the input images as real as possible?
Your question is quite big and to answer it i would suggest you to please have a look at this video to clear your fundamentals. th-cam.com/video/mMa2PmYJlCo/w-d-xo.html
Walker Lisa Rodriguez Anthony Lopez Frank