usamaehsan
/
controlnet-x-realistic-vision
- Public
- 69 runs
Run usamaehsan/controlnet-x-realistic-vision 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
|
Prompt - using compel, use +++ to increase words weight:: doc: https://github.com/damian0815/compel/tree/main/doc || https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#attention-weighting
|
|
| negative_prompt |
string
|
Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
|
Negative prompt - using compel, use +++ to increase words weight//// negative-embeddings available ///// FastNegativeV2 , boring_e621_v4 , verybadimagenegative_v1 || to use them, write their keyword in negative prompt
|
| num_inference_steps |
integer
|
20
|
Steps to run denoising
|
| guidance_scale |
number
|
7
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
|
| guess_mode |
boolean
|
False
|
In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts. The `guidance_scale` between 3.0 and 5.0 is recommended.
|
| disable_safety_check |
boolean
|
False
|
Disable safety check. Use at your own risk!
|
| num_outputs |
integer
|
1
Min: 1 Max: 10 |
Number of images to generate
|
| max_width |
integer
|
512
|
Max width/Resolution of image
|
| max_height |
integer
|
512
|
Max height/Resolution of image
|
| scheduler |
string
(enum)
|
DDIM
Options: DDIM, DPMSolverMultistep, HeunDiscrete, K_EULER_ANCESTRAL, K_EULER, KLMS, PNDM, UniPCMultistep, KDPM2DiscreteScheduler, KDPM2AncestralDiscreteScheduler |
Choose a scheduler.
|
| lineart_image |
string
|
Control image for canny controlnet
|
|
| lineart_conditioning_scale |
number
|
1
|
Conditioning scale for canny controlnet
|
| depth_image |
string
|
Control image for depth controlnet
|
|
| depth_conditioning_scale |
number
|
1
|
Conditioning scale for depth controlnet
|
| canny_image |
string
|
Control image for canny controlnet
|
|
| canny_conditioning_scale |
number
|
1
|
Conditioning scale for canny controlnet
|
| mlsd_image |
string
|
Control image for mlsd controlnet
|
|
| mlsd_conditioning_scale |
number
|
1
|
Conditioning scale for mlsd controlnet
|
| inpainting_image |
string
|
Control image for inpainting controlnet
|
|
| mask_image |
string
|
mask image for inpainting controlnet
|
|
| positive_auto_mask_text |
string
|
comma seperated list of objects for mask, AI will auto create mask of these objects, if mask text is given, mask image will not work
|
|
| negative_auto_mask_text |
string
|
comma seperated list of objects you dont want to mask, AI will auto delete these objects from mask, only works if positive_auto_mask_text is given
|
|
| inpainting_conditioning_scale |
number
|
1
|
Conditioning scale for brightness controlnet
|
| sorted_controlnets |
string
|
tile, inpainting, lineart
|
Comma seperated string of controlnet names, list of names: tile, inpainting, lineart,depth ,scribble , brightness /// example value: tile, inpainting, lineart
|
| ip_adapter_ckpt |
string
(enum)
|
ip-adapter_sd15.bin
Options: ip-adapter_sd15.bin, ip-adapter-plus_sd15.bin, ip-adapter-plus-face_sd15.bin |
IP Adapter checkpoint
|
| ip_adapter_image |
string
|
IP Adapter image
|
|
| ip_adapter_weight |
number
|
1
|
IP Adapter weight
|
| img2img_image |
string
|
Image2image image
|
|
| img2img_strength |
number
|
0.5
|
img2img strength, does not work when inpainting image is given, 0.1-same image, 0.99-complete destruction of image
|
| add_more_detail_lora_scale |
number
|
0.5
|
Scale/ weight of more_details lora, more scale = more details, disabled on 0
|
| detail_tweaker_lora_weight |
number
|
0
|
disabled on 0
|
| film_grain_lora_weight |
number
|
0
|
disabled on 0
|
| epi_noise_offset_lora_weight |
number
|
0
|
disabled on 0
|
| color_temprature_slider_lora_weight |
number
|
0
|
disabled on 0
|
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"eta": {
"type": "number",
"title": "Eta",
"default": 0,
"x-order": 5,
"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": 4,
"description": "Seed"
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 0,
"description": "Prompt - using compel, use +++ to increase words weight:: doc: https://github.com/damian0815/compel/tree/main/doc || https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#attention-weighting"
},
"max_width": {
"type": "integer",
"title": "Max Width",
"default": 512,
"x-order": 9,
"description": "Max width/Resolution of image"
},
"scheduler": {
"enum": [
"DDIM",
"DPMSolverMultistep",
"HeunDiscrete",
"K_EULER_ANCESTRAL",
"K_EULER",
"KLMS",
"PNDM",
"UniPCMultistep",
"KDPM2DiscreteScheduler",
"KDPM2AncestralDiscreteScheduler"
],
"type": "string",
"title": "scheduler",
"description": "Choose a scheduler.",
"default": "DDIM",
"x-order": 11
},
"guess_mode": {
"type": "boolean",
"title": "Guess Mode",
"default": false,
"x-order": 6,
"description": "In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts. The `guidance_scale` between 3.0 and 5.0 is recommended."
},
"mask_image": {
"type": "string",
"title": "Mask Image",
"format": "uri",
"x-order": 21,
"description": "mask image for inpainting controlnet"
},
"max_height": {
"type": "integer",
"title": "Max Height",
"default": 512,
"x-order": 10,
"description": "Max height/Resolution of image"
},
"mlsd_image": {
"type": "string",
"title": "Mlsd Image",
"format": "uri",
"x-order": 18,
"description": "Control image for mlsd controlnet"
},
"canny_image": {
"type": "string",
"title": "Canny Image",
"format": "uri",
"x-order": 16,
"description": "Control image for canny controlnet"
},
"depth_image": {
"type": "string",
"title": "Depth Image",
"format": "uri",
"x-order": 14,
"description": "Control image for depth controlnet"
},
"num_outputs": {
"type": "integer",
"title": "Num Outputs",
"default": 1,
"maximum": 10,
"minimum": 1,
"x-order": 8,
"description": "Number of images to generate"
},
"img2img_image": {
"type": "string",
"title": "Img2Img Image",
"format": "uri",
"x-order": 29,
"description": "Image2image image"
},
"lineart_image": {
"type": "string",
"title": "Lineart Image",
"format": "uri",
"x-order": 12,
"description": "Control image for canny controlnet"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 7,
"maximum": 30,
"minimum": 0.1,
"x-order": 3,
"description": "Scale for classifier-free guidance"
},
"ip_adapter_ckpt": {
"enum": [
"ip-adapter_sd15.bin",
"ip-adapter-plus_sd15.bin",
"ip-adapter-plus-face_sd15.bin"
],
"type": "string",
"title": "ip_adapter_ckpt",
"description": "IP Adapter checkpoint",
"default": "ip-adapter_sd15.bin",
"x-order": 26
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"default": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
"x-order": 1,
"description": "Negative prompt - using compel, use +++ to increase words weight//// negative-embeddings available ///// FastNegativeV2 , boring_e621_v4 , verybadimagenegative_v1 || to use them, write their keyword in negative prompt"
},
"img2img_strength": {
"type": "number",
"title": "Img2Img Strength",
"default": 0.5,
"x-order": 30,
"description": "img2img strength, does not work when inpainting image is given, 0.1-same image, 0.99-complete destruction of image"
},
"inpainting_image": {
"type": "string",
"title": "Inpainting Image",
"format": "uri",
"x-order": 20,
"description": "Control image for inpainting controlnet"
},
"ip_adapter_image": {
"type": "string",
"title": "Ip Adapter Image",
"format": "uri",
"x-order": 27,
"description": "IP Adapter image"
},
"ip_adapter_weight": {
"type": "number",
"title": "Ip Adapter Weight",
"default": 1,
"x-order": 28,
"description": "IP Adapter weight"
},
"sorted_controlnets": {
"type": "string",
"title": "Sorted Controlnets",
"default": "tile, inpainting, lineart",
"x-order": 25,
"description": "Comma seperated string of controlnet names, list of names: tile, inpainting, lineart,depth ,scribble , brightness /// example value: tile, inpainting, lineart "
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 20,
"x-order": 2,
"description": "Steps to run denoising"
},
"disable_safety_check": {
"type": "boolean",
"title": "Disable Safety Check",
"default": false,
"x-order": 7,
"description": "Disable safety check. Use at your own risk!"
},
"film_grain_lora_weight": {
"type": "number",
"title": "Film Grain Lora Weight",
"default": 0,
"x-order": 33,
"description": "disabled on 0"
},
"mlsd_conditioning_scale": {
"type": "number",
"title": "Mlsd Conditioning Scale",
"default": 1,
"x-order": 19,
"description": "Conditioning scale for mlsd controlnet"
},
"negative_auto_mask_text": {
"type": "string",
"title": "Negative Auto Mask Text",
"x-order": 23,
"description": "comma seperated list of objects you dont want to mask, AI will auto delete these objects from mask, only works if positive_auto_mask_text is given"
},
"positive_auto_mask_text": {
"type": "string",
"title": "Positive Auto Mask Text",
"x-order": 22,
"description": "comma seperated list of objects for mask, AI will auto create mask of these objects, if mask text is given, mask image will not work"
},
"canny_conditioning_scale": {
"type": "number",
"title": "Canny Conditioning Scale",
"default": 1,
"x-order": 17,
"description": "Conditioning scale for canny controlnet"
},
"depth_conditioning_scale": {
"type": "number",
"title": "Depth Conditioning Scale",
"default": 1,
"x-order": 15,
"description": "Conditioning scale for depth controlnet"
},
"add_more_detail_lora_scale": {
"type": "number",
"title": "Add More Detail Lora Scale",
"default": 0.5,
"x-order": 31,
"description": "Scale/ weight of more_details lora, more scale = more details, disabled on 0"
},
"detail_tweaker_lora_weight": {
"type": "number",
"title": "Detail Tweaker Lora Weight",
"default": 0,
"x-order": 32,
"description": "disabled on 0"
},
"lineart_conditioning_scale": {
"type": "number",
"title": "Lineart Conditioning Scale",
"default": 1,
"x-order": 13,
"description": "Conditioning scale for canny controlnet"
},
"epi_noise_offset_lora_weight": {
"type": "number",
"title": "Epi Noise Offset Lora Weight",
"default": 0,
"x-order": 34,
"description": "disabled on 0"
},
"inpainting_conditioning_scale": {
"type": "number",
"title": "Inpainting Conditioning Scale",
"default": 1,
"x-order": 24,
"description": "Conditioning scale for brightness controlnet"
},
"color_temprature_slider_lora_weight": {
"type": "number",
"title": "Color Temprature Slider Lora Weight",
"default": 0,
"x-order": 35,
"description": "disabled on 0"
}
}
}
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"
}