viktorfa
/
instant-id-multicontrolnet-multiple-images
- Public
- 57 runs
Run viktorfa/instant-id-multicontrolnet-multiple-images 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 |
|---|---|---|---|
| face_image_path |
string
|
Image of your face
|
|
| face_image_path2 |
string
|
Image of your face
|
|
| face_image_path3 |
string
|
Image of your face
|
|
| face_image_path4 |
string
|
Image of your face
|
|
| pose_image_path |
string
|
Reference pose image
|
|
| prompt |
string
|
a person
|
Input prompt
|
| negative_prompt |
string
|
(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy
|
Input negative prompt
|
| model |
string
(enum)
|
RealVisXL V4.0
Options: AlbedoBase XL V2, Juggernaut XL V8, Animagine XL V3, HelloWorld XL 5.0 GPT4V, SDXL RongHua V4, RealVisXL V4.0 |
Select SDXL model
|
| enable_fast_mode |
boolean
|
False
|
Enable SDXL-lightning fast inference. If pose, canny or depth map is used, disable it for better quality images.
|
| lightning_steps |
string
(enum)
|
4step
Options: 2step, 4step, 8step |
if enable fast mode, choose number of denoising steps
|
| scheduler |
string
(enum)
|
DPMSolverMultistepScheduler-Karras-SDE
Options: DEISMultistepScheduler, HeunDiscreteScheduler, EulerDiscreteScheduler, DPMSolverMultistepScheduler, DPMSolverMultistepScheduler-Karras, DPMSolverMultistepScheduler-Karras-SDE |
Scheduler options. If enable fast mode, this is not used.
|
| adapter_strength_ratio |
number
|
0.8
Max: 1 |
Image adapter strength (for detail)
|
| identitynet_strength_ratio |
number
|
0.9
Max: 1 |
IdentityNet strength (for fidelity)
|
| pose |
boolean
|
False
|
Use pose for skeleton inference
|
| pose_strength |
number
|
1
Max: 1.5 |
None
|
| canny |
boolean
|
False
|
Use canny for edge detection
|
| canny_strength |
number
|
0.5
Max: 1.5 |
None
|
| depth_map |
boolean
|
False
|
Use depth for depth map estimation
|
| depth_strength |
number
|
0.5
Max: 1.5 |
None
|
| num_steps |
integer
|
25
Min: 1 Max: 50 |
Number of denoising steps. If enable fast mode, this is not used.
|
| guidance_scale |
number
|
7
Max: 10 |
Scale for classifier-free guidance. Optimum is 4-8. If enable fast mode, this is not used.
|
| seed |
integer
|
0
Max: 2147483647 |
Seed number. Set to non-zero to make the image reproducible.
|
| enhance_non_face_region |
boolean
|
True
|
Enhance non-face region
|
| num_images |
integer
|
1
Min: 1 Max: 4 |
Number of images to generate
|
| safety_checker |
boolean
|
True
|
Safety checker is enabled by default. Un-tick to expose unfiltered results.
|
{
"type": "object",
"title": "Input",
"required": [
"face_image_path"
],
"properties": {
"pose": {
"type": "boolean",
"title": "Pose",
"default": false,
"x-order": 13,
"description": "Use pose for skeleton inference"
},
"seed": {
"type": "integer",
"title": "Seed",
"default": 0,
"maximum": 2147483647,
"minimum": 0,
"x-order": 21,
"description": "Seed number. Set to non-zero to make the image reproducible."
},
"canny": {
"type": "boolean",
"title": "Canny",
"default": false,
"x-order": 15,
"description": "Use canny for edge detection"
},
"model": {
"enum": [
"AlbedoBase XL V2",
"Juggernaut XL V8",
"Animagine XL V3",
"HelloWorld XL 5.0 GPT4V",
"SDXL RongHua V4",
"RealVisXL V4.0"
],
"type": "string",
"title": "model",
"description": "Select SDXL model",
"default": "RealVisXL V4.0",
"x-order": 7
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "a person",
"x-order": 5,
"description": "Input prompt"
},
"depth_map": {
"type": "boolean",
"title": "Depth Map",
"default": false,
"x-order": 17,
"description": "Use depth for depth map estimation"
},
"num_steps": {
"type": "integer",
"title": "Num Steps",
"default": 25,
"maximum": 50,
"minimum": 1,
"x-order": 19,
"description": "Number of denoising steps. If enable fast mode, this is not used."
},
"scheduler": {
"enum": [
"DEISMultistepScheduler",
"HeunDiscreteScheduler",
"EulerDiscreteScheduler",
"DPMSolverMultistepScheduler",
"DPMSolverMultistepScheduler-Karras",
"DPMSolverMultistepScheduler-Karras-SDE"
],
"type": "string",
"title": "scheduler",
"description": "Scheduler options. If enable fast mode, this is not used.",
"default": "DPMSolverMultistepScheduler-Karras-SDE",
"x-order": 10
},
"num_images": {
"type": "integer",
"title": "Num Images",
"default": 1,
"maximum": 4,
"minimum": 1,
"x-order": 23,
"description": "Number of images to generate"
},
"pose_strength": {
"type": "number",
"title": "Pose Strength",
"default": 1,
"maximum": 1.5,
"minimum": 0,
"x-order": 14
},
"canny_strength": {
"type": "number",
"title": "Canny Strength",
"default": 0.5,
"maximum": 1.5,
"minimum": 0,
"x-order": 16
},
"depth_strength": {
"type": "number",
"title": "Depth Strength",
"default": 0.5,
"maximum": 1.5,
"minimum": 0,
"x-order": 18
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 7,
"maximum": 10,
"minimum": 0,
"x-order": 20,
"description": "Scale for classifier-free guidance. Optimum is 4-8. If enable fast mode, this is not used."
},
"safety_checker": {
"type": "boolean",
"title": "Safety Checker",
"default": true,
"x-order": 24,
"description": "Safety checker is enabled by default. Un-tick to expose unfiltered results."
},
"face_image_path": {
"type": "string",
"title": "Face Image Path",
"format": "uri",
"x-order": 0,
"description": "Image of your face"
},
"lightning_steps": {
"enum": [
"2step",
"4step",
"8step"
],
"type": "string",
"title": "lightning_steps",
"description": "if enable fast mode, choose number of denoising steps",
"default": "4step",
"x-order": 9
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"default": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, glitch, deformed, mutated, cross-eyed, ugly, disfigured, blurry, grainy",
"x-order": 6,
"description": "Input negative prompt"
},
"pose_image_path": {
"type": "string",
"title": "Pose Image Path",
"format": "uri",
"x-order": 4,
"description": "Reference pose image"
},
"enable_fast_mode": {
"type": "boolean",
"title": "Enable Fast Mode",
"default": false,
"x-order": 8,
"description": "Enable SDXL-lightning fast inference. If pose, canny or depth map is used, disable it for better quality images."
},
"face_image_path2": {
"type": "string",
"title": "Face Image Path2",
"format": "uri",
"x-order": 1,
"description": "Image of your face"
},
"face_image_path3": {
"type": "string",
"title": "Face Image Path3",
"format": "uri",
"x-order": 2,
"description": "Image of your face"
},
"face_image_path4": {
"type": "string",
"title": "Face Image Path4",
"format": "uri",
"x-order": 3,
"description": "Image of your face"
},
"adapter_strength_ratio": {
"type": "number",
"title": "Adapter Strength Ratio",
"default": 0.8,
"maximum": 1,
"minimum": 0,
"x-order": 11,
"description": "Image adapter strength (for detail)"
},
"enhance_non_face_region": {
"type": "boolean",
"title": "Enhance Non Face Region",
"default": true,
"x-order": 22,
"description": "Enhance non-face region"
},
"identitynet_strength_ratio": {
"type": "number",
"title": "Identitynet Strength Ratio",
"default": 0.9,
"maximum": 1,
"minimum": 0,
"x-order": 12,
"description": "IdentityNet strength (for fidelity)"
}
}
}
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"
}