|
gptkbp:instanceOf
|
text-to-image diffusion model
|
|
gptkbp:application
|
image editing
art generation
inpainting
image-to-image generation
outpainting
|
|
gptkbp:architecture
|
latent diffusion model
|
|
gptkbp:citation
|
https://arxiv.org/abs/2112.10752
|
|
gptkbp:developedBy
|
gptkb:LAION
gptkb:CompVis
gptkb:Stability_AI
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Stable Diffusion model
|
|
gptkbp:influenced
|
gptkb:ControlNet
gptkb:DreamBooth
gptkb:Midjourney
Kandinsky model
|
|
gptkbp:influencedBy
|
gptkb:DALL-E
gptkb:Imagen
|
|
gptkbp:input
|
text prompt
|
|
gptkbp:interface
|
gptkb:AUTOMATIC1111_WebUI
gptkb:DreamStudio
gptkb:InvokeAI
DiffusionBee
|
|
gptkbp:latestReleaseVersion
|
gptkb:Stable_Diffusion_XL
2023-07-26
|
|
gptkbp:license
|
gptkb:CreativeML_Open_RAIL-M
|
|
gptkbp:memiliki_tugas
|
text-to-image generation
|
|
gptkbp:notableFeature
|
custom model training
prompt-based image generation
community model sharing
extensive plugin ecosystem
runs on consumer hardware
support for ControlNet
support for DreamBooth
support for LoRA fine-tuning
support for inpainting and outpainting
|
|
gptkbp:notableRelease
|
gptkb:Stable_Diffusion_1.5
gptkb:Stable_Diffusion_1.4
gptkb:Stable_Diffusion_2.0
gptkb:Stable_Diffusion_XL
|
|
gptkbp:openSource
|
true
|
|
gptkbp:output
|
gptkb:illustrator
|
|
gptkbp:platform
|
GPU recommended
|
|
gptkbp:programmingLanguage
|
gptkb:Python
|
|
gptkbp:releaseDate
|
2022-08-22
|
|
gptkbp:repository
|
https://github.com/CompVis/stable-diffusion
|
|
gptkbp:trainer
|
gptkb:LAION-5B_dataset
|
|
gptkbp:uses
|
gptkb:Variational_Autoencoder
gptkb:CLIP_text_encoder
gptkb:UNet_architecture
|
|
gptkbp:website
|
https://stability.ai/blog/stable-diffusion-public-release
|
|
gptkbp:bfsParent
|
gptkb:Stable_Diffusion_(collaboration)
|
|
gptkbp:bfsLayer
|
5
|