Statements (30)
Predicate | Object |
---|---|
gptkbp:instanceOf |
text-to-image model
|
gptkbp:architecture |
gptkb:transformation
gptkb:U-Net gptkb:convolutional_neural_network |
gptkbp:basedOn |
latent diffusion model
|
gptkbp:developedBy |
gptkb:LAION
gptkb:CompVis gptkb:Stability_AI |
gptkbp:hasVersion |
gptkb:Stable_Diffusion
|
https://www.w3.org/2000/01/rdf-schema#label |
Stable Diffusion 1.4
|
gptkbp:input |
text prompt
|
gptkbp:license |
gptkb:CreativeML_Open_RAIL-M
|
gptkbp:mode |
text-to-image
|
gptkbp:notableFeature |
customizable with fine-tuning
high-quality image generation prompt-based control runs on consumer GPUs |
gptkbp:openSource |
true
|
gptkbp:output |
gptkb:illustrator
|
gptkbp:parameter |
~890 million
|
gptkbp:predecessor |
gptkb:Stable_Diffusion_1.3
|
gptkbp:releaseYear |
2022
|
gptkbp:resolution |
512x512 pixels
|
gptkbp:successor |
gptkb:Stable_Diffusion_2.0
|
gptkbp:trainer |
gptkb:LAION-5B_dataset
|
gptkbp:usedFor |
generative art
image synthesis creative applications |
gptkbp:bfsParent |
gptkb:Stable_Diffusion
|
gptkbp:bfsLayer |
5
|