Statements (55)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:model
|
gptkbp:application |
image generation
image-to-image translation |
gptkbp:architecture |
gptkb:convolutional_neural_network
|
gptkbp:basedOn |
gptkb:Stable_Diffusion
|
gptkbp:citation |
Zhang, Lvmin, et al. 'Adding Conditional Control to Text-to-Image Diffusion Models.' arXiv preprint arXiv:2302.05543 (2023).
|
gptkbp:compatibleWith |
gptkb:Stable_Diffusion_1.5
gptkb:Stable_Diffusion_2.1 |
gptkbp:controls |
gptkb:Canny_edge
gptkb:MLSD pose estimation segmentation depth map lineart normal map openpose reference image scribble |
gptkbp:developedBy |
gptkb:Lvmin_Zhang
gptkb:Mingyuan_Zhang |
gptkbp:enables |
fine-grained control over image generation
|
https://www.w3.org/2000/01/rdf-schema#label |
ControlNet
|
gptkbp:input |
gptkb:illustrator
text prompt conditioning map |
gptkbp:language |
gptkb:Python
|
gptkbp:license |
gptkb:CreativeML_Open_RAIL-M
|
gptkbp:notableFeature |
adds trainable copy of network blocks
preserves original model weights supports multiple control types |
gptkbp:notableFor |
animation
AI art creative design image editing image inpainting image restoration depth-to-image image outpainting virtual try-on edge-to-image line art colorization photo-to-anime pose transfer semantic segmentation to image sketch-to-image |
gptkbp:openSource |
true
|
gptkbp:platform |
gptkb:PyTorch
|
gptkbp:releaseYear |
2023
|
gptkbp:repository |
https://github.com/lllyasviel/ControlNet
|
gptkbp:usedFor |
controlling diffusion models
|
gptkbp:bfsParent |
gptkb:IEC_61158
gptkb:Diffusers gptkb:Stable_Diffusion_XL gptkb:Stable_Diffusion_model |
gptkbp:bfsLayer |
6
|