|
gptkbp:instanceOf
|
gptkb:model
generative model
|
|
gptkbp:architecture
|
diffusion model
|
|
gptkbp:author
|
gptkb:Björn_Ommer
gptkb:Andreas_Blattmann
gptkb:Dominik_Lorenz
gptkb:Patrick_Esser
gptkb:Robin_Rombach
|
|
gptkbp:citation
|
high
|
|
gptkbp:developedBy
|
gptkb:CompVis
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Latent Diffusion Model
|
|
gptkbp:implementedIn
|
gptkb:PyTorch
|
|
gptkbp:input
|
text prompt
|
|
gptkbp:introducedIn
|
2022
|
|
gptkbp:license
|
gptkb:CreativeML_Open_RAIL-M
|
|
gptkbp:notableFor
|
efficient high-resolution image synthesis
reduced computational cost compared to pixel-space diffusion
|
|
gptkbp:notablePublication
|
gptkb:High-Resolution_Image_Synthesis_with_Latent_Diffusion_Models
|
|
gptkbp:openSource
|
true
|
|
gptkbp:operatesIn
|
latent space
|
|
gptkbp:output
|
gptkb:illustrator
|
|
gptkbp:publicationDate
|
gptkb:CVPR_2022
|
|
gptkbp:relatedTo
|
gptkb:Stable_Diffusion
|
|
gptkbp:usedFor
|
image generation
text-to-image synthesis
|
|
gptkbp:website
|
https://github.com/CompVis/latent-diffusion
|
|
gptkbp:bfsParent
|
gptkb:AudioLDM
gptkb:Diffusion_Model
|
|
gptkbp:bfsLayer
|
7
|