|
gptkbp:instanceOf
|
text-to-image diffusion model
|
|
gptkbp:accuracy
|
fp16
fp32
|
|
gptkbp:architecture
|
gptkb:U-Net
|
|
gptkbp:canBe
|
gptkb:Diffusers_library
gptkb:AUTOMATIC1111_WebUI
gptkb:InvokeAI
|
|
gptkbp:category
|
generative AI
diffusion model
AI art model
|
|
gptkbp:conditioning
|
gptkb:CLIP_text_encoder
|
|
gptkbp:developedBy
|
gptkb:Stability_AI
|
|
gptkbp:displayType
|
768x768
|
|
gptkbp:downloads
|
https://huggingface.co/stabilityai/stable-diffusion-2-1
|
|
gptkbp:format
|
.ckpt
.safetensors
|
|
gptkbp:hasModel
|
latent diffusion model
|
|
gptkbp:hasVersion
|
gptkb:Stable_Diffusion
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Stable Diffusion 2.1-768
|
|
gptkbp:improves
|
gptkb:Stable_Diffusion_1.5
|
|
gptkbp:input
|
text prompt
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
gptkb:CreativeML_Open_RAIL-M
|
|
gptkbp:notableFeature
|
higher resolution output
improved prompt understanding
better negative prompt support
|
|
gptkbp:openSource
|
true
|
|
gptkbp:output
|
gptkb:illustrator
|
|
gptkbp:platform
|
gptkb:GitHub
gptkb:Hugging_Face
|
|
gptkbp:releaseDate
|
2022
|
|
gptkbp:requires
|
GPU for fast inference
|
|
gptkbp:size
|
5.2 GB
|
|
gptkbp:supportsNegativePrompts
|
true
|
|
gptkbp:trainer
|
gptkb:LAION-5B_dataset
|
|
gptkbp:uses
|
image synthesis
art generation
creative content creation
|
|
gptkbp:website
|
https://stability.ai
|
|
gptkbp:bfsParent
|
gptkb:Diffusers
|
|
gptkbp:bfsLayer
|
6
|