Latent diffusion model
id:
latent-diffusion-model-189-6314740
title:
Latent diffusion model
text:
The Latent Diffusion Model (LDM) is a diffusion model architecture developed developed by the CompVis group at LMU Munich. Introduced in 2015, diffusion models (DM) are trained with the objective of removing successive applications of Gaussian noise on training images. The LDM is an improvement on standard DM by performing diffusion modeling in latent space, and by allowing self-attention and cross-attention conditioning. LDM are widely used in practical diffusion models. The Stable Diffusion 1.
brand slug:
wiki
category slug:
encyclopedia
description:
Deep generative model
original url:
https://en.wikipedia.org/wiki/Latent_diffusion_model
date created:
2024-09-07T21:15:16Z
date modified:
2024-09-09T06:48:45Z
main entity:
image:
fields total:
13
integrity:
14