What Does Each Model of ControlNet v1.1 Do?

ControlNet 1.1 includes 14 models (11 production-ready models and 3 experimental models). Here is a list of the models and their brief descriptions:

Model	Description
control_v11p_sd15_canny	Edge detection.
control_v11p_sd15_mlsd	Multi-line segment detection.
control_v11f1p_sd15_depth	Depth estimation.
control_v11p_sd15_normalbae	Normal map estimation.
control_v11p_sd15_seg	Semantic segmentation.
control_v11p_sd15_inpaint	Image inpainting.
control_v11p_sd15_lineart	Line art generation.
control_v11p_sd15s2_lineart_anime	Anime line art generation.
control_v11p_sd15_openpose	Human pose estimation.
control_v11p_sd15_scribble	Scribble-based image colorization.
control_v11p_sd15_softedge	Soft edge detection.
control_v11e_sd15_shuffle	Experimental model that shuffles input image pixels to generate a new image.
control_v11e_sd15_ip2p	Experimental model that generates an image from a given input point cloud.
control_v11f1e_sd15_tile	Experimental model that generates a tiled image.

You can download all these models from the HuggingFace Model Page. All these models should be put in the folder "models".