Latent diffusion model
Deep generative model
The latent diffusion model (LDM) is a diffusion model architecture developed by the CompVis (Computer Vision & Learning) group at LMU Munich. Introduced in 2015, diffusion models (DMs) are trained with the objective of removing successive applications of noise (commonly Gaussian) on training images.
Nº Q130641540 ★
Common · Literature
Latent diffusion model
Deep generative model
The latent diffusion model (LDM) is a diffusion model architecture developed by the CompVis (Computer Vision & Learning) group at LMU Munich. Introduced in 2015, diffusion models (DMs) are trained with the objective of removing successive applications of noise (commonly Gaussian) on training images.
From Wikipedia
The latent diffusion model (LDM) is a diffusion model architecture developed by the CompVis (Computer Vision & Learning) group at LMU Munich. Introduced in 2015, diffusion models (DMs) are trained with the objective of removing successive applications of noise (commonly Gaussian) on training images. The LDM is an improvement on standard DM by performing diffusion modeling in a latent space, and by allowing self-attention and cross-attention conditioning. LDMs are widely used in practical diffusion models. For instance, Stable Diffusion versions 1.1 to 2.1 were based on the LDM architecture.
Text: Wikipédia, CC BY-SA 4.0. ·
Related cards
-
Stable Diffusion
Image-generating machine learning model
Nº Q113660857 ★★★★
Not listed
-
Latent Dirichlet allocation
Generative statistical model that allows sets of observations to be explained by unobserved groups that explain why some parts of the data are similar
Nº Q269236 ★
Not listed
-
Diffusion-limited aggregation
Process of particles clustering together
Nº Q1224521 ★
Not listed
-
G
Generalized linear mixed model
Statistical model
Nº Q5532490 ★
Not listed
-
U
U-Net
Convolutional neural network developed at University of Freiburg
Nº Q55636383 ★★
Not listed
-
L
LightGBM
Machine learning software
Nº Q57267665 ★★
Not listed