← Back to all generators

jagilley/controlnet-hough

Modify images using M-LSD line detection

Capabilities

Reference Images Negative Prompt Seed

Cost

Community model (estimated from hardware time)

Input Parameters

image required string

Input image

prompt required string

Prompt for the model

a_prompt string

Added Prompt

Default: "best quality, extremely detailed"
ddim_steps integer

Steps

Default: 20
detect_resolution integer

Resolution for detection (only applicable when model type is 'HED', 'Segmentation', or 'MLSD')

Default: 512 min: 128, max: 1024
distance_threshold number

Distance Threshold (only applicable when model type is 'MLSD')

Default: 0.1 min: 0.01, max: 20
eta number

eta (DDIM)

Default: 0
image_resolution string

Image resolution to be generated

Default: "512"
256 512 768
n_prompt string

Negative Prompt

Default: "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)

Default: "1"
1 4
scale number

Guidance Scale

Default: 9 min: 0.1, max: 30
seed integer

Seed

value_threshold number

Value Threshold (only applicable when model type is 'MLSD')

Default: 0.1 min: 0.01, max: 2
Version: 854e8727697a Updated: 2/26/2026 10.0M runs