You're looking at a specific version of this model. Jump to the model overview.

jagilley /controlnet:8ebda4c7

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
image
string
Input image
prompt
string
Prompt for the model
model_type
string (enum)
canny

Options:

canny, depth, hed, normal, mlsd, scribble, seg, openpose

ControlNet model type to use
num_samples
string (enum)
1

Options:

1, 4

Number of samples (higher values may OOM)
image_resolution
string (enum)
512

Options:

256, 512, 768

Image resolution to be generated
ddim_steps
integer
20
Steps
scale
number
9

Min: 0.1

Max: 30

Scale for classifier-free guidance
seed
integer
Seed
eta
number
0
Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise
a_prompt
string
best quality, extremely detailed
Additional text to be appended to prompt
n_prompt
string
longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
Negative Prompt
detect_resolution
integer
512

Min: 128

Max: 1024

Resolution at which detection method will be applied)
low_threshold
integer
100

Min: 1

Max: 255

Canny line detection low threshold (only applicable when model type is 'canny')
high_threshold
integer
200

Min: 1

Max: 255

Canny line detection high threshold (only applicable when model type is 'canny')
bg_threshold
number
0

Max: 1

Background Threshold (only applicable when model type is 'normal')
value_threshold
number
0.1

Min: 0.01

Max: 2

Value Threshold (only applicable when model type is 'MLSD')
distance_threshold
number
0.1

Min: 0.01

Max: 20

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

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'items': {'format': 'uri', 'type': 'string'},
 'title': 'Output',
 'type': 'array'}