Dimensionality Reduction

Latent Diffusion Model

Introduced by Rombach et al. in High-Resolution Image Synthesis with Latent Diffusion Models

Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.

Source: High-Resolution Image Synthesis with Latent Diffusion Models

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Generation 55 16.92%
Denoising 24 7.38%
Decoder 13 4.00%
Text-to-Image Generation 11 3.38%
Video Generation 7 2.15%
Virtual Try-on 6 1.85%
Semantic Segmentation 6 1.85%
Image Reconstruction 6 1.85%
Translation 5 1.54%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories