List ControlNet Models and Pre-processors

Action ListControlNets

Introduction

This interface is used to query the models and pre-processors of ControlNets. The common combinations and effects of the models are:

ControlNet Name	ControlNet ModelCode	PreProcessor Name	PreProcessor ModelCode	Effect
Consistent Face	ip-adapter-faceid-plusv2_sd15			Keeping the face unchanged when generating images.
Contents Migrate (Normal)	ip-adapter_sd15			Keeping the same style when generating images.
Depth	control_v11f1p_sd15_depth	Depth (LeRes)	depth_leres	Generating images according to the depth information of the reference image.
Depth	control_v11f1p_sd15_depth	Depth (MiDas)	depth	Same as above.
Depth	control_v11f1p_sd15_depth	Depth (ZoE)	depth_zoe	Same as above.
Hard Edge	control_v11p_sd15_canny	Hard Edge	canny	Generating images according to the lines information of the reference image.
Inpaint	control_v11p_sd15_inpaint			Generating contents in the marked area of the raw image.
Insruct Pix2Pix	control_v11e_sd15_ip2p			Editing the raw image by prompts.
Lineart	control_v11p_sd15_lineart	Lineart	lineart	Similar to the "Hard Edge" model, but more curvy and diverse.
Lineart	control_v11p_sd15_lineart	Lineart (Standard)	lineart_standard	Same as above.
Lineart Animie	control_v11p_sd15s2_lineart_anime	Lineart (Anime + Denoise)	lineart_anime_denoise	Similar to the "Hard Edge" model, but more curvy and diverse (optimize for anime style).
Lineart Animie	control_v11p_sd15s2_lineart_anime	Lineart (Anime)	lineart_anime	Same as above.
Normal Map	control_v11p_sd15_normalbae	Normal Map (Bae)	normal_bae	Similar to the "Depth" models, but base on a normal map.
Pose	control_v11p_sd15_openpose	Pose (Full)	openpose_full	Generating images according to the human's poses in the reference image.
Recolor	ioclab_sd15_recolor	Recolor (Intensity)	recolor_intensity	Recoloring images according to the intensity or luminance information of the reference image.
Recolor	ioclab_sd15_recolor	Recolor (Luminance)	recolor_luminance	Same as above.
Scribble	control_v11p_sd15_scribble	Scribble (Edge)	scribble_xdog	Similar to the "Hard Edge" models, but more rough and diverse.
Scribble	control_v11p_sd15_scribble	Scribble (HED)	scribble_hed	Same as above.
Shuffle	control_v11e_sd15_shuffle	Shuffle	shuffle	Generating new images by shuffling the colors and contents of the raw image.
Soft Edge	control_v11p_sd15_softedge	Soft Edge (HED)	softedge_hed	Similar to the "Hard Edge" model, but more rough and diverse.
Soft Edge	control_v11p_sd15_softedge	Soft Edge (PiDiNet)	softedge_pidinet	Same as above.
Straight Line	control_v11p_sd15_mlsd	Straight Line	mlsd	Generating images only according to straight lines in the reference image.
Tile	control_v11f1e_sd15_tile	Tile	tile	Generating images by tiling the reference image to add more details or upscale it.

Request

Parameter Name	Type	Description	Required
Action	`String`	The corresponding API instruction name	✓
PublicKey	`String`	User's public key, which can be obtained from the PICPIK User Center (opens in a new tab)	✓
Signature	`String`	User's signature generated based on the public key and API instruction, see Signature for details	✓
request_uuid	`String`	Request UUID, randomly generated by using the UUID generation method. This parameter can be utilized to manage the requests of your business and clients.

Request Example

{
    "Action":    "ListControlNets",
    "PublicKey": "ALLak9M4cNdHXKOJAJJ4k8Hh1hZS2EgJF1D0FlPwfl",
    "request_uuid":"b91fcfbe-bb35-47ce-a168-bd6252c75270",
    "Signature": "0131f4e4296f3ca8e1220b47247e83a4315ea8e1"
}

Response

Field Name	Type	Description	Required
RetCode	`Int`	Return status code: 0 indicates a successful return, while non-zero indicates a failure	✓
Action	`String`	Instruction name	✓
Message	`String`	The error message is returned when `RetCode` is non-zero, providing a detailed description
request_uuid	`String`	Returns the UUID that was included in the request

Field Name	Type	Description	Required
PreProcessors	`Map[String]PreProcessor`	Pre-processors list of ControlNets	✓
ControlModels	`Map[String]ControlModel`	Models list of ControlNets	✓

Intro to Complex Data Types

`PreProcessor`

Parameter Name	Type	Description	Required
ModelCode	`String`	The model code of a ControlNet pre-processor.	✓
InferenceParams	`InferenceParams`	Inference parameters of a pre-processor

`ControlModel`

Parameter Name	Type	Description	Required
ModelCode	`String`	ControlNet model code	✓
InferenceParams	`InferenceParams`	Inference parameters of a ControlNet model

`InferenceParams`

Note: Specific parameters are only valid for a particular model data type (parent) and are not generic.

Parameter Name	Type	Valid Parent Type	Description	Default	Range	Step
LoraWeight	`Float`	`Model`	The influence weight when inferencing. Only available with the LoRA model.	1	-1～2	0.01
Resolution	`Int`	`PreProcessor`	The resolution of images generated by the pre-processor.	512	64~2048	64
ControlWeight	`Float`	`ControlModel`	The influence weight of a ControlNet model when inferencing.	1	0~2	0.01
StartingStep	`Float`	`ControlModel`	Timing (ratio) of a ControlNet model to start intervening in the inference process.	0	0~1	0.01
EndingStep	`Float`	`ControlModel`	Timing (ratio) of a ControlNet model to stop intervening in the inference process.	1	0~1	0.01

Response Example

{
	"Action": "ListControlNets",
	"RetCode": 0,
	"Message": "",
	"request_uuid": "06e47e54-253e-40d7-9002-a3f7d9d4cbdd",
	"PreProcessors": {
		"canny": {
			"Name": "canny",
			"ModelCode": "canny",
			"InferenceParams": {
				"Resolution": 512
			}
		}
		// more...
	},
	"ControlModels": {
		"control_v11e_sd15_ip2p": {
			"Name": "control_v11e_sd15_ip2p",
			"ModelCode": "control_v11e_sd15_ip2p",
			"InferenceParams": {
				"ControlWeight": 1,
				"StartingStep": 0,
				"EndingStep": 1
			}
		}
		// more ...
	}
}

List Models Generate Images