jagilley / controlnet-pose

Modify images with humans using pose detection

  • Public
  • 174.4K runs
  • A100 (80GB)
  • GitHub
  • License

Run jagilley/controlnet-pose with an API

Input schema

etanumber

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

seedinteger

Seed

imageuri

Input image

scalenumber

Scale for classifier-free guidance

Default
9
Minimum
0.1
Maximum
30
promptstring

Prompt for the model

a_promptstring

Additional text to be appended to prompt

Default
"best quality, extremely detailed"
n_promptstring

Negative Prompt

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

Steps

Default
20
num_samplesstring

Number of samples (higher values may OOM)

Default
"1"
low_thresholdinteger

Canny line detection low threshold

Default
100
Minimum
1
Maximum
255
high_thresholdinteger

Canny line detection high threshold

Default
200
Minimum
1
Maximum
255
image_resolutionstring

Image resolution to be generated

Default
"512"
detect_resolutioninteger

Resolution at which detection method will be applied)

Default
512
Minimum
128
Maximum
1024

Output schema

Type
uri[]