Controlnet (alpha)

Time	Status	User Agent
Retrieving recent requests…

Time

Status

User Agent

Retrieving recent requests…

image

string

required

Input image

prompt

string

required

Prompt for the model

structure

string

Controlnet structure to condition on Allowed values:canny, depth, hed, hough, normal, pose, scribble, seg

num_outputs

number

Number of images to output (higher values may OOM) Default value: 1

image_resolution

number

Resolution of output image (will be scaled to this as its smaller dimension) Allowed values:256, 512, 768 Default value: 512

scheduler

string

Choose a scheduler. Allowed values:DDIM, DPMSolverMultistep, HeunDiscrete, K_EULER_ANCESTRAL, K_EULER, KLMS, PNDM, UniPCMultistep Default value: DDIM

steps

number

Steps Default value: 20

scale

number

Scale for classifier-free guidance Default value: 9

seed

number

Seed

eta

number

Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise 0

negative_prompt

string

Negative prompt Default value: Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality return_reference_image boolean whether to return the reference image along with the output

low_threshold

number

[canny only] Line detection low threshold Default value: 100

high_threshold

number

[canny only] Line detection high threshold Default value: 200

200Standard response