qr2ai
/
mb
- Public
- 798 runs
Run qr2ai/mb 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 for img2img or inpaint mode
|
|
| prompt |
string
|
An acrylic painting featuring flowing, elegant strokes, set against a swirling backdrop of deep charcoal, slate gray, and ethereal white. Accents of radiant gold and soft amber cascade across the canvas, highlighted by delicate specks of luminescent gold dust.
|
Input prompt
|
| suffix_prompt |
string
|
Imagine the harmonious blend of graceful forms and cosmic elegance, where each curve and line tells a story amidst the celestial backdrop, captured in a luxurious interplay of dark and light hues.
|
Additional prompt
|
| negative_prompt |
string
|
worst quality, low quality, low resolution, blurry, ugly, disfigured, uncrafted, filled ring, packed ring, cross, star, distorted, stagnant, watermark
|
Input Negative Prompt
|
| sketch_type |
string
(enum)
|
HedPidNet
Options: PidiNet, HED, Lineart, LineartAnime, Canny, CannyPidNet, CannyHed, HedPidNet, MLSD |
Choose the type of sketch detector
|
| weight_primary |
number
|
0.7
|
Weight for the primary sketch in the combination (e.g., PidiNet in PidiNetCanny).
|
| weight_secondary |
number
|
0.6
|
Weight for the secondary sketch in the combination (e.g., Canny in PidiNetCanny).
|
| blur_size |
integer
|
3
|
Gaussian blur kernel size (must be an odd number).
|
| kernel_size |
integer
|
3
|
Kernel size for morphological operations (must be an odd number).
|
| dilation_iterations |
integer
|
5
|
Number of iterations for dilation.
|
| erosion_iterations |
integer
|
2
|
Number of iterations for erosion.
|
| use_canny |
boolean
|
False
|
Whether to combine with canny detector for better details
|
| lora_input |
string
|
|
Comma-separated list of LoRA models from Hugging Face or local paths. Leave empty to skip LoRA.
|
| lora_scale |
string
|
|
Comma-separated list of scales for each LoRA model. Must match the number of LoRAs. Leave empty if no LoRA is used.
|
| width |
integer
|
1920
|
Width of output image
|
| height |
integer
|
1088
|
Height of output image
|
| generate_square |
boolean
|
False
|
Whether to generate a square image (assert height == width)
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output.
|
| num_inference_steps |
integer
|
35
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
12
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| adapter_conditioning_scale |
number
|
0.97
Max: 2 |
Scale for adapter module
|
| seed |
integer
|
0
|
Random seed. Enter 0 to randomize the seed.
|
| sampler |
string
(enum)
|
Euler a
Options: DPM++ 2M Karras, DPM++ 2M SDE Karras, DPM++ Karras SDE, DPM++ Karras, Euler, Euler a |
The sampling method
|
{
"type": "object",
"title": "Input",
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"default": 0,
"x-order": 21,
"description": "Random seed. Enter 0 to randomize the seed."
},
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 0,
"description": "Input image for img2img or inpaint mode"
},
"width": {
"type": "integer",
"title": "Width",
"default": 1920,
"x-order": 14,
"description": "Width of output image"
},
"height": {
"type": "integer",
"title": "Height",
"default": 1088,
"x-order": 15,
"description": "Height of output image"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "An acrylic painting featuring flowing, elegant strokes, set against a swirling backdrop of deep charcoal, slate gray, and ethereal white. Accents of radiant gold and soft amber cascade across the canvas, highlighted by delicate specks of luminescent gold dust.",
"x-order": 1,
"description": "Input prompt"
},
"sampler": {
"enum": [
"DPM++ 2M Karras",
"DPM++ 2M SDE Karras",
"DPM++ Karras SDE",
"DPM++ Karras",
"Euler",
"Euler a"
],
"type": "string",
"title": "sampler",
"description": "The sampling method",
"default": "Euler a",
"x-order": 22
},
"blur_size": {
"type": "integer",
"title": "Blur Size",
"default": 3,
"x-order": 7,
"description": "Gaussian blur kernel size (must be an odd number)."
},
"use_canny": {
"type": "boolean",
"title": "Use Canny",
"default": false,
"x-order": 11,
"description": "Whether to combine with canny detector for better details"
},
"lora_input": {
"type": "string",
"title": "Lora Input",
"default": "",
"x-order": 12,
"description": "Comma-separated list of LoRA models from Hugging Face or local paths. Leave empty to skip LoRA."
},
"lora_scale": {
"type": "string",
"title": "Lora Scale",
"default": "",
"x-order": 13,
"description": "Comma-separated list of scales for each LoRA model. Must match the number of LoRAs. Leave empty if no LoRA is used."
},
"kernel_size": {
"type": "integer",
"title": "Kernel Size",
"default": 3,
"x-order": 8,
"description": "Kernel size for morphological operations (must be an odd number)."
},
"num_outputs": {
"type": "integer",
"title": "Num Outputs",
"default": 1,
"maximum": 4,
"minimum": 1,
"x-order": 17,
"description": "Number of images to output."
},
"sketch_type": {
"enum": [
"PidiNet",
"HED",
"Lineart",
"LineartAnime",
"Canny",
"CannyPidNet",
"CannyHed",
"HedPidNet",
"MLSD"
],
"type": "string",
"title": "sketch_type",
"description": "Choose the type of sketch detector",
"default": "HedPidNet",
"x-order": 4
},
"suffix_prompt": {
"type": "string",
"title": "Suffix Prompt",
"default": "Imagine the harmonious blend of graceful forms and cosmic elegance, where each curve and line tells a story amidst the celestial backdrop, captured in a luxurious interplay of dark and light hues.",
"x-order": 2,
"description": "Additional prompt"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 12,
"maximum": 50,
"minimum": 1,
"x-order": 19,
"description": "Scale for classifier-free guidance"
},
"weight_primary": {
"type": "number",
"title": "Weight Primary",
"default": 0.7,
"x-order": 5,
"description": "Weight for the primary sketch in the combination (e.g., PidiNet in PidiNetCanny)."
},
"generate_square": {
"type": "boolean",
"title": "Generate Square",
"default": false,
"x-order": 16,
"description": "Whether to generate a square image (assert height == width)"
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"default": "worst quality, low quality, low resolution, blurry, ugly, disfigured, uncrafted, filled ring, packed ring, cross, star, distorted, stagnant, watermark",
"x-order": 3,
"description": "Input Negative Prompt"
},
"weight_secondary": {
"type": "number",
"title": "Weight Secondary",
"default": 0.6,
"x-order": 6,
"description": "Weight for the secondary sketch in the combination (e.g., Canny in PidiNetCanny)."
},
"erosion_iterations": {
"type": "integer",
"title": "Erosion Iterations",
"default": 2,
"x-order": 10,
"description": "Number of iterations for erosion."
},
"dilation_iterations": {
"type": "integer",
"title": "Dilation Iterations",
"default": 5,
"x-order": 9,
"description": "Number of iterations for dilation."
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 35,
"maximum": 500,
"minimum": 1,
"x-order": 18,
"description": "Number of denoising steps"
},
"adapter_conditioning_scale": {
"type": "number",
"title": "Adapter Conditioning Scale",
"default": 0.97,
"maximum": 2,
"minimum": 0,
"x-order": 20,
"description": "Scale for adapter module"
}
}
}
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"
}