Porovnat metody

	Latent Diffusion Models	Vision Transformer
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2022	2021
Tvůrce	Robin Rombach	Dosovitskiy, A. et al.
Typ	Neural network architecture	Transformer architecture for images (self-attention over patches)
Původní zdroj	Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10684-10695).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Další názvy	LDM, Stable Diffusion, Latent Diffusion	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Příbuzné	4	5
Shrnutí	Latent Diffusion Models (LDMs) are a generative approach introduced by Rombach et al. in 2022 that performs the diffusion process in a compressed latent space rather than pixel space, enabling efficient high-resolution image synthesis. By compressing images into a low-dimensional latent representation using a variational autoencoder, diffusion becomes computationally tractable while maintaining visual quality.	The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).