pnyompen / sd-lineart-controlnet
This AI model generates new images while preserving the original image characteristics by applying Lineart ControlNet to the input image and performing Stable Diffusion's Image2Image generation. Combined with IP-Adapter, it enables generation that better
- Public
- 39 runs
Run pnyompen/sd-lineart-controlnet 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 astronaut riding a rainbow unicorn
|
Input prompt
|
| image |
string
|
Input image for img2img or inpaint mode
|
|
| condition_scale |
number
|
1.1
Max: 2 |
The bigger this number is, the more ControlNet interferes
|
| strength |
number
|
0.8
Max: 1 |
When img2img is active, the denoising strength. 1 means total destruction of the input image.
|
| ip_adapter_scale |
number
|
1
|
Scale for the IP Adapter
|
| negative_prompt |
string
|
|
Input Negative Prompt
|
| num_inference_steps |
integer
|
30
Min: 1 Max: 500 |
Number of denoising steps
|
| 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
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| color |
array
|
[0, 0, 0, 0]
|
RGBA color
|
{
"type": "object",
"title": "Input",
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 10,
"description": "Random seed. Leave blank to randomize the seed"
},
"color": {
"type": "array",
"items": {
"type": "integer"
},
"title": "Color",
"default": [
0,
0,
0,
0
],
"x-order": 11,
"description": "RGBA color"
},
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 1,
"description": "Input image for img2img or inpaint mode"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "An astronaut riding a rainbow unicorn",
"x-order": 0,
"description": "Input prompt"
},
"strength": {
"type": "number",
"title": "Strength",
"default": 0.8,
"maximum": 1,
"minimum": 0,
"x-order": 3,
"description": "When img2img is active, the denoising strength. 1 means total destruction of the input image."
},
"scheduler": {
"enum": [
"DDIM",
"DPMSolverMultistep",
"HeunDiscrete",
"KarrasDPM",
"K_EULER_ANCESTRAL",
"K_EULER",
"PNDM"
],
"type": "string",
"title": "scheduler",
"description": "scheduler",
"default": "K_EULER",
"x-order": 8
},
"num_outputs": {
"type": "integer",
"title": "Num Outputs",
"default": 1,
"maximum": 4,
"minimum": 1,
"x-order": 7,
"description": "Number of images to output"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 7.5,
"maximum": 50,
"minimum": 1,
"x-order": 9,
"description": "Scale for classifier-free guidance"
},
"condition_scale": {
"type": "number",
"title": "Condition Scale",
"default": 1.1,
"maximum": 2,
"minimum": 0,
"x-order": 2,
"description": "The bigger this number is, the more ControlNet interferes"
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"default": "",
"x-order": 5,
"description": "Input Negative Prompt"
},
"ip_adapter_scale": {
"type": "number",
"title": "Ip Adapter Scale",
"default": 1,
"minimum": 0,
"x-order": 4,
"description": "Scale for the IP Adapter"
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 30,
"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.
{
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"title": "Output"
}