juergengunz/sdxl-openpose-lora

juergengunz / sdxl-openpose-lora

SDXL ControlNet OpenPose with LoRA Support

Public
7.3K runs

Playground API Examples Train README Versions

Run juergengunz/sdxl-openpose-lora 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
prompt	string	An portrait of an astronaut standing on the moon	Input prompt
negative_prompt	string		Input Negative Prompt
image	string		Input image for img2img or inpaint mode
condition_scale	number	0.9 Max: 1	The bigger this number is, the more ControlNet interferes
num_outputs	integer	1 Min: 1 Max: 4	Number of images to output
scheduler	string (enum)	K_EULER Options: DDIM, DPMSolverMultistep, HeunDiscrete, KarrasDPM, K_EULER_ANCESTRAL, K_EULER, PNDM	scheduler
num_inference_steps	integer	50 Min: 1 Max: 500	Number of denoising steps
guidance_scale	number	5 Min: 1 Max: 50	Scale for classifier-free guidance
seed	integer		Random seed. Leave blank to randomize the seed
refine	string (enum)	no_refiner Options: no_refiner, base_image_refiner	Whether to use refinement steps or not
refine_steps	integer	10	For base_image_refiner, the number of steps to refine
apply_watermark	boolean	False	Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
lora_scale	number	0.8 Max: 1	LoRA additive scale. Only applicable on trained models.
lora_weights	string		Replicate LoRA weights to use. Leave blank to use the default weights.

{
  "type": "object",
  "title": "Input",
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 8,
      "description": "Random seed. Leave blank to randomize the seed"
    },
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 2,
      "description": "Input image for img2img or inpaint mode"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "default": "An portrait of an astronaut standing on the moon",
      "x-order": 0,
      "description": "Input prompt"
    },
    "refine": {
      "enum": [
        "no_refiner",
        "base_image_refiner"
      ],
      "type": "string",
      "title": "refine",
      "description": "Whether to use refinement steps or not",
      "default": "no_refiner",
      "x-order": 9
    },
    "scheduler": {
      "enum": [
        "DDIM",
        "DPMSolverMultistep",
        "HeunDiscrete",
        "KarrasDPM",
        "K_EULER_ANCESTRAL",
        "K_EULER",
        "PNDM"
      ],
      "type": "string",
      "title": "scheduler",
      "description": "scheduler",
      "default": "K_EULER",
      "x-order": 5
    },
    "lora_scale": {
      "type": "number",
      "title": "Lora Scale",
      "default": 0.8,
      "maximum": 1,
      "minimum": 0,
      "x-order": 12,
      "description": "LoRA additive scale. Only applicable on trained models."
    },
    "num_outputs": {
      "type": "integer",
      "title": "Num Outputs",
      "default": 1,
      "maximum": 4,
      "minimum": 1,
      "x-order": 4,
      "description": "Number of images to output"
    },
    "lora_weights": {
      "type": "string",
      "title": "Lora Weights",
      "x-order": 13,
      "description": "Replicate LoRA weights to use. Leave blank to use the default weights."
    },
    "refine_steps": {
      "type": "integer",
      "title": "Refine Steps",
      "default": 10,
      "x-order": 10,
      "description": "For base_image_refiner, the number of steps to refine"
    },
    "guidance_scale": {
      "type": "number",
      "title": "Guidance Scale",
      "default": 5,
      "maximum": 50,
      "minimum": 1,
      "x-order": 7,
      "description": "Scale for classifier-free guidance"
    },
    "apply_watermark": {
      "type": "boolean",
      "title": "Apply Watermark",
      "default": false,
      "x-order": 11,
      "description": "Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking."
    },
    "condition_scale": {
      "type": "number",
      "title": "Condition Scale",
      "default": 0.9,
      "maximum": 1,
      "minimum": 0,
      "x-order": 3,
      "description": "The bigger this number is, the more ControlNet interferes"
    },
    "negative_prompt": {
      "type": "string",
      "title": "Negative Prompt",
      "default": "",
      "x-order": 1,
      "description": "Input Negative Prompt"
    },
    "num_inference_steps": {
      "type": "integer",
      "title": "Num Inference Steps",
      "default": 50,
      "maximum": 500,
      "minimum": 1,
      "x-order": 6,
      "description": "Number of denoising steps"
    }
  }
}

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"
}