jagilley/controlnet-normal

Modify images using normal maps

Capabilities

Reference ImagesNegative PromptSeed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`image`*	string(uri)	Input image	`—`	—
`prompt`*	string	Prompt for the model	`—`	—
`a_prompt`	string	Added Prompt	`"best quality, extremely detailed"`	—
`bg_threshold`	number	Background Threshold (only applicable when model type is 'normal')	`0`	min: 0, max: 1
`ddim_steps`	integer	Steps	`20`	—
`detect_resolution`	integer	Resolution for detection)	`512`	min: 128, max: 1024
`eta`	number	eta (DDIM)	`0`	—
`image_resolution`	string	Image resolution to be generated	`"512"`	256512768
`n_prompt`	string	Negative Prompt	`"longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"`	—
`num_samples`	string	Number of samples (higher values may OOM)	`"1"`	14
`scale`	number	Guidance Scale	`9`	min: 0.1, max: 30
`seed`	integer	Seed	`—`	—

imagerequiredstring

Input image

promptrequiredstring

Prompt for the model

a_promptstring

Added Prompt

Default: "best quality, extremely detailed"

bg_thresholdnumber

Background Threshold (only applicable when model type is 'normal')

Default: 0min: 0, max: 1

ddim_stepsinteger

Steps

Default: 20

detect_resolutioninteger

Resolution for detection)

Default: 512min: 128, max: 1024

etanumber

eta (DDIM)

Default: 0

image_resolutionstring

Image resolution to be generated

Default: "512"

256512768

n_promptstring

Negative Prompt

Default:

"longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"

num_samplesstring

Number of samples (higher values may OOM)

Default: "1"

scalenumber

Guidance Scale

Default: 9min: 0.1, max: 30

seedinteger

Seed

Version: cc8066f617b6Updated: 7/25/2026330.8K runs