|
gptkbp:instanceOf
|
text-to-image model
|
|
gptkbp:architecture
|
latent diffusion model
|
|
gptkbp:category
|
gptkb:artificial_intelligence
gptkb:model
generative AI
|
|
gptkbp:developedBy
|
gptkb:Stability_AI
|
|
gptkbp:hasVersion
|
gptkb:Stable_Diffusion
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Stable Diffusion XL 1.0
|
|
gptkbp:improves
|
gptkb:Stable_Diffusion_2.1
|
|
gptkbp:input
|
text prompt
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
gptkb:CreativeML_Open_RAIL-M
|
|
gptkbp:notableFeature
|
faster inference
higher image resolution
improved prompt understanding
better photorealism
native 1024x1024 output
|
|
gptkbp:openSource
|
true
|
|
gptkbp:output
|
gptkb:illustrator
|
|
gptkbp:platform
|
gptkb:Hugging_Face
gptkb:DreamStudio
gptkb:Stability_AI_API
|
|
gptkbp:releaseDate
|
2023-07-26
|
|
gptkbp:size
|
2.6 billion parameters
|
|
gptkbp:supports
|
image generation
inpainting
image-to-image generation
outpainting
|
|
gptkbp:trainer
|
gptkb:LAION-5B
|
|
gptkbp:uses
|
gptkb:CLIP_text_encoder
gptkb:UNet_architecture
diffusion process
VAE decoder
|
|
gptkbp:website
|
https://stability.ai/stablediffusion
|
|
gptkbp:bfsParent
|
gptkb:Diffusers
|
|
gptkbp:bfsLayer
|
6
|