runvnc/controlnet4 | API reference

Public

88.6K runs

Run runvnc/controlnet4 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

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
structure	None		Structure to condition on
num_samples	None	1	Number of samples (higher values may OOM)
image_resolution	None	512	Resolution of image (square)
ddim_steps	integer	20	Steps
strength	number	1	Control strength
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
preprocessor_resolution	integer	512	Preprocessor resolution
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
low_threshold	integer	100 Min: 1 Max: 255	[canny only] Line detection low threshold
high_threshold	integer	200 Min: 1 Max: 255	[canny only] Line detection high threshold

{
  "type": "object",
  "title": "Input",
  "required": [
    "image",
    "prompt",
    "structure"
  ],
  "properties": {
    "eta": {
      "type": "number",
      "title": "Eta",
      "default": 0,
      "x-order": 9,
      "description": "Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise"
    },
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 8,
      "description": "Seed"
    },
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 0,
      "description": "Input image"
    },
    "scale": {
      "type": "number",
      "title": "Scale",
      "default": 9,
      "maximum": 30,
      "minimum": 0.1,
      "x-order": 7,
      "description": "Scale for classifier-free guidance"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "x-order": 1,
      "description": "Prompt for the model"
    },
    "a_prompt": {
      "type": "string",
      "title": "A Prompt",
      "default": "Best quality, extremely detailed",
      "x-order": 11,
      "description": "Additional text to be appended to prompt"
    },
    "n_prompt": {
      "type": "string",
      "title": "N Prompt",
      "default": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "x-order": 12,
      "description": "Negative prompt"
    },
    "strength": {
      "type": "number",
      "title": "Strength",
      "default": 1,
      "x-order": 6,
      "description": "Control strength"
    },
    "structure": {
      "enum": [
        "canny",
        "depth",
        "hed",
        "hough",
        "normal",
        "pose",
        "scribble",
        "seg"
      ],
      "type": "string",
      "title": "structure",
      "description": "Structure to condition on",
      "x-order": 2
    },
    "ddim_steps": {
      "type": "integer",
      "title": "Ddim Steps",
      "default": 20,
      "x-order": 5,
      "description": "Steps"
    },
    "num_samples": {
      "enum": [
        "1",
        "4"
      ],
      "type": "string",
      "title": "num_samples",
      "description": "Number of samples (higher values may OOM)",
      "default": "1",
      "x-order": 3
    },
    "low_threshold": {
      "type": "integer",
      "title": "Low Threshold",
      "default": 100,
      "maximum": 255,
      "minimum": 1,
      "x-order": 13,
      "description": "[canny only] Line detection low threshold"
    },
    "high_threshold": {
      "type": "integer",
      "title": "High Threshold",
      "default": 200,
      "maximum": 255,
      "minimum": 1,
      "x-order": 14,
      "description": "[canny only] Line detection high threshold"
    },
    "image_resolution": {
      "enum": [
        "256",
        "512",
        "768"
      ],
      "type": "string",
      "title": "image_resolution",
      "description": "Resolution of image (square)",
      "default": "512",
      "x-order": 4
    },
    "preprocessor_resolution": {
      "type": "integer",
      "title": "Preprocessor Resolution",
      "default": 512,
      "x-order": 10,
      "description": "Preprocessor resolution"
    }
  }
}

Output schema

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

Schema

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