|
gptkbp:instanceOf
|
text-to-image model
|
|
gptkbp:abilities
|
text-to-image synthesis
inpainting
depth-to-image
image upscaling
|
|
gptkbp:architecture
|
latent diffusion model
|
|
gptkbp:developer
|
gptkb:Stability_AI
|
|
gptkbp:hasVersion
|
gptkb:Stable_Diffusion
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Stable Diffusion 2.0
|
|
gptkbp:input
|
text prompt
|
|
gptkbp:language
|
gptkb:Python
|
|
gptkbp:license
|
gptkb:CreativeML_Open_RAIL-M
|
|
gptkbp:notableFeature
|
depth-guided generation
higher resolution output
improved image quality
new text encoder
|
|
gptkbp:openSource
|
true
|
|
gptkbp:output
|
gptkb:illustrator
|
|
gptkbp:platform
|
gptkb:Windows
gptkb:macOS
gptkb:Linux
|
|
gptkbp:predecessor
|
gptkb:Stable_Diffusion_1.5
|
|
gptkbp:releaseDate
|
2022-11-24
|
|
gptkbp:repository
|
https://github.com/Stability-AI/stablediffusion
|
|
gptkbp:resolution
|
768x768
|
|
gptkbp:size
|
865M parameters
|
|
gptkbp:successor
|
gptkb:Stable_Diffusion_XL
|
|
gptkbp:trainer
|
gptkb:LAION-5B
|
|
gptkbp:uses
|
gptkb:CLIP_text_encoder
gptkb:UNet_architecture
diffusion process
|
|
gptkbp:bfsParent
|
gptkb:Stable_Diffusion
|
|
gptkbp:bfsLayer
|
5
|