underthestar2021
/
realistic-vision-v15-with-vae-public
- Public
- 37.9K runs
Run underthestar2021/realistic-vision-v15-with-vae-public 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 |
string
|
Input face image
|
|
| remark |
string
|
备注项，随便填
|
|
| prompt |
string
|
a photo of an astronaut riding a horse on mars
|
Input prompt
|
| negative_prompt |
string
|
Specify things to not see in the output
|
|
| prompt_strength |
number
|
0.7
Max: 1 |
Prompt strength when providing the image. 1.0 corresponds to full destruction of information in init image
|
| pipe_type |
string
(enum)
|
txt2img
Options: img2img, txt2img |
画图类型，文生图还是图生图。不可以选空
|
| clip_skip |
integer
|
2
Min: 1 |
None
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output.
|
| num_inference_steps |
integer
|
26
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 20 |
Scale for classifier-free guidance
|
| target_width |
integer
|
512
Min: 1 Max: 1024 |
Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
|
| target_height |
integer
|
720
Min: 1 Max: 1024 |
Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
|
| scheduler |
string
(enum)
|
DPM++ SDE Karras
Options: PNDM, KLMS, DDIM, K_EULER, K_EULER_ANCESTRAL, DPMSolverMultistep, DPM++ SDE Karras, DPM++ 2M Karras |
Choose a scheduler.
|
| controlnet_enable |
boolean
|
True
|
是否启用Controlnet
|
| controlnet_type |
string
(enum)
|
canny
Options: canny, openpose |
An enumeration.
|
| controlnet_conditioning_scale |
number
|
1
Max: 2 |
Control Weight
|
| canny_low_threshold |
integer
|
100
Min: 1 Max: 255 |
Canny line detection low threshold
|
| canny_high_threshold |
integer
|
200
Min: 1 Max: 255 |
Canny line detection high threshold
|
| control_guidance_start |
number
|
0
Max: 1 |
The percentage of total steps at which the controlnet starts applying
|
| control_guidance_end |
number
|
1
Max: 1 |
The percentage of total steps at which the controlnet stops applying
|
| lora_model |
string
(enum)
|
Options: empty, add_detail, barbie, Clothing_Sexy_Firemen_Outfit, Clothing_SilkPunk_Armor, drow_offset, ela_(rainbow_six_siege), evening_dress_S2, jack_sparrow_offset, jackNicholson, KimonoClothes, LORA-XenoDetailer-v2, national_attire, PW_nurse_v1.1, quinn, sanguogirls_v1, skinny_new_skin, Spider-Man_Costume_v1 |
An enumeration.
|
| lora_model_extra_url |
string
|
测试lora时使用；lora模型的下载地址，如果填写会复盖掉lora_model参数
|
|
| cross_attention_scale |
number
|
0.8
|
lora权重，区间0-1. A scale value of 0 is the same as not using your LoRA weights and you’re only using the base model weights, and a scale value of 1 means you’re only using the fully fine-tuned LoRA weights.
|
| swap_face_enable |
boolean
|
True
|
是否使用swap_face(roop的换脸功能),默认True
|
| restore_face_enable |
boolean
|
True
|
是否使用restore_face,默认True
|
| restore_face_upscale |
integer
|
1
Min: 1 Max: 4 |
Restore face upscaling
|
| restore_face_upsample |
boolean
|
True
|
Restore face upsampling
|
| restore_face_background_enhance |
boolean
|
True
|
Restore face background enhance
|
| codeformer_fidelity |
number
|
0.7
Max: 1 |
Codeformer fidelity
|
| face_editor_enable |
boolean
|
False
|
是否使用face editor,默认False
|
| face_editor_strength1 |
number
|
0.4
Min: 0.1 Max: 0.8 |
Step 0.05, face editor, denoising strength for face images, sdwebui:(3) Recreate the Faces
|
| face_editor_strength2 |
number
|
0.05
Max: 1 |
Step 0.05, face editor, denoising strength for the entire image, sdwebui:(5) Blend the entire image
|
| face_editor_mask_size |
integer
|
6
|
Face editor mask size
|
| face_editor_mask_blur |
integer
|
12
|
Face editor mask blur
|
| face_editor_confidence |
number
|
0.97
Min: 0.7 Max: 1 |
Confidence threshold for face detection. Set a lower value if you want to detect more faces.
|
| resize_mode |
string
(enum)
|
fill
Options: fill, crop, cover |
fill - The image is resized to fill the given dimension. cover - The image keeps its aspect ratio and fills the given dimension. The image will be clipped to fit. crop - The image keeps its aspect ratio and scales to the target size.
|
| uid |
string
|
Unique identifier for this run. Will be used in callback.
|
|
| task_id |
string
|
Task ID for this run. Will be used in callback.
|
|
| firebase_api_version |
integer
|
4
|
api version
|
| on_process_callback |
string
|
Process callback URL for this .
|
|
| complete_callback |
string
|
Complete callback URL for this run.
|
|
| callback_steps |
integer
|
4
Min: 1 Max: 100 |
Callback URL for this run.
|
| ai_random |
string
|
ai_random
|
random seed
|
| show_system_info |
boolean
|
False
|
Show system info
|
{
"type": "object",
"title": "Input",
"properties": {
"uid": {
"type": "string",
"title": "Uid",
"x-order": 37,
"description": "Unique identifier for this run. Will be used in callback."
},
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 7,
"description": "Random seed. Leave blank to randomize the seed"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "a photo of an astronaut riding a horse on mars",
"x-order": 2,
"description": "Input prompt"
},
"remark": {
"type": "string",
"title": "Remark",
"x-order": 1,
"description": "\u5907\u6ce8\u9879\uff0c\u968f\u4fbf\u586b"
},
"task_id": {
"type": "string",
"title": "Task Id",
"x-order": 38,
"description": "Task ID for this run. Will be used in callback."
},
"ai_random": {
"type": "string",
"title": "Ai Random",
"default": "ai_random",
"x-order": 43,
"description": "random seed"
},
"clip_skip": {
"type": "integer",
"title": "Clip Skip",
"default": 2,
"minimum": 1,
"x-order": 6
},
"pipe_type": {
"enum": [
"img2img",
"txt2img"
],
"type": "string",
"title": "pipe_type",
"description": "\u753b\u56fe\u7c7b\u578b\uff0c\u6587\u751f\u56fe\u8fd8\u662f\u56fe\u751f\u56fe\u3002\u4e0d\u53ef\u4ee5\u9009\u7a7a",
"default": "txt2img",
"x-order": 5
},
"scheduler": {
"enum": [
"PNDM",
"KLMS",
"DDIM",
"K_EULER",
"K_EULER_ANCESTRAL",
"DPMSolverMultistep",
"DPM++ SDE Karras",
"DPM++ 2M Karras"
],
"type": "string",
"title": "scheduler",
"description": "Choose a scheduler.",
"default": "DPM++ SDE Karras",
"x-order": 13
},
"face_image": {
"type": "string",
"title": "Face Image",
"format": "uri",
"x-order": 0,
"description": "Input face image"
},
"lora_model": {
"enum": [
"empty",
"add_detail",
"barbie",
"Clothing_Sexy_Firemen_Outfit",
"Clothing_SilkPunk_Armor",
"drow_offset",
"ela_(rainbow_six_siege)",
"evening_dress_S2",
"jack_sparrow_offset",
"jackNicholson",
"KimonoClothes",
"LORA-XenoDetailer-v2",
"national_attire",
"PW_nurse_v1.1",
"quinn",
"sanguogirls_v1",
"skinny_new_skin",
"Spider-Man_Costume_v1"
],
"type": "string",
"title": "lora_model",
"description": "An enumeration.",
"x-order": 21
},
"num_outputs": {
"type": "integer",
"title": "Num Outputs",
"default": 1,
"maximum": 4,
"minimum": 1,
"x-order": 8,
"description": "Number of images to output."
},
"resize_mode": {
"enum": [
"fill",
"crop",
"cover"
],
"type": "string",
"title": "resize_mode",
"description": "fill - The image is resized to fill the given dimension. cover - The image keeps its aspect ratio and fills the given dimension. The image will be clipped to fit. crop - The image keeps its aspect ratio and scales to the target size.",
"default": "fill",
"x-order": 36
},
"target_width": {
"type": "integer",
"title": "Target Width",
"default": 512,
"maximum": 1024,
"minimum": 1,
"x-order": 11,
"description": "Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits"
},
"target_height": {
"type": "integer",
"title": "Target Height",
"default": 720,
"maximum": 1024,
"minimum": 1,
"x-order": 12,
"description": "Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits"
},
"callback_steps": {
"type": "integer",
"title": "Callback Steps",
"default": 4,
"maximum": 100,
"minimum": 1,
"x-order": 42,
"description": "Callback URL for this run."
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 7.5,
"maximum": 20,
"minimum": 1,
"x-order": 10,
"description": "Scale for classifier-free guidance"
},
"controlnet_type": {
"enum": [
"canny",
"openpose"
],
"type": "string",
"title": "controlnet_type",
"description": "An enumeration.",
"default": "canny",
"x-order": 15
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"x-order": 3,
"description": "Specify things to not see in the output"
},
"prompt_strength": {
"type": "number",
"title": "Prompt Strength",
"default": 0.7,
"maximum": 1,
"minimum": 0,
"x-order": 4,
"description": "Prompt strength when providing the image. 1.0 corresponds to full destruction of information in init image"
},
"show_system_info": {
"type": "boolean",
"title": "Show System Info",
"default": false,
"x-order": 44,
"description": "Show system info"
},
"swap_face_enable": {
"type": "boolean",
"title": "Swap Face Enable",
"default": true,
"x-order": 24,
"description": "\u662f\u5426\u4f7f\u7528swap_face(roop\u7684\u6362\u8138\u529f\u80fd),\u9ed8\u8ba4True"
},
"complete_callback": {
"type": "string",
"title": "Complete Callback",
"x-order": 41,
"description": "Complete callback URL for this run."
},
"controlnet_enable": {
"type": "boolean",
"title": "Controlnet Enable",
"default": true,
"x-order": 14,
"description": "\u662f\u5426\u542f\u7528Controlnet"
},
"face_editor_enable": {
"type": "boolean",
"title": "Face Editor Enable",
"default": false,
"x-order": 30,
"description": "\u662f\u5426\u4f7f\u7528face editor,\u9ed8\u8ba4False"
},
"canny_low_threshold": {
"type": "integer",
"title": "Canny Low Threshold",
"default": 100,
"maximum": 255,
"minimum": 1,
"x-order": 17,
"description": "Canny line detection low threshold"
},
"codeformer_fidelity": {
"type": "number",
"title": "Codeformer Fidelity",
"default": 0.7,
"maximum": 1,
"minimum": 0,
"x-order": 29,
"description": "Codeformer fidelity"
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 26,
"maximum": 500,
"minimum": 1,
"x-order": 9,
"description": "Number of denoising steps"
},
"on_process_callback": {
"type": "string",
"title": "On Process Callback",
"x-order": 40,
"description": "Process callback URL for this ."
},
"restore_face_enable": {
"type": "boolean",
"title": "Restore Face Enable",
"default": true,
"x-order": 25,
"description": "\u662f\u5426\u4f7f\u7528restore_face,\u9ed8\u8ba4True"
},
"canny_high_threshold": {
"type": "integer",
"title": "Canny High Threshold",
"default": 200,
"maximum": 255,
"minimum": 1,
"x-order": 18,
"description": "Canny line detection high threshold"
},
"control_guidance_end": {
"type": "number",
"title": "Control Guidance End",
"default": 1,
"maximum": 1,
"minimum": 0,
"x-order": 20,
"description": "The percentage of total steps at which the controlnet stops applying"
},
"firebase_api_version": {
"type": "integer",
"title": "Firebase Api Version",
"default": 4,
"x-order": 39,
"description": "api version"
},
"lora_model_extra_url": {
"type": "string",
"title": "Lora Model Extra Url",
"x-order": 22,
"description": "\u6d4b\u8bd5lora\u65f6\u4f7f\u7528\uff1blora\u6a21\u578b\u7684\u4e0b\u8f7d\u5730\u5740\uff0c\u5982\u679c\u586b\u5199\u4f1a\u590d\u76d6\u6389lora_model\u53c2\u6570"
},
"restore_face_upscale": {
"type": "integer",
"title": "Restore Face Upscale",
"default": 1,
"maximum": 4,
"minimum": 1,
"x-order": 26,
"description": "Restore face upscaling"
},
"cross_attention_scale": {
"type": "number",
"title": "Cross Attention Scale",
"default": 0.8,
"x-order": 23,
"description": "lora\u6743\u91cd\uff0c\u533a\u95f40-1. A scale value of 0 is the same as not using your LoRA weights and you\u2019re only using the base model weights, and a scale value of 1 means you\u2019re only using the fully fine-tuned LoRA weights."
},
"face_editor_mask_blur": {
"type": "integer",
"title": "Face Editor Mask Blur",
"default": 12,
"x-order": 34,
"description": "Face editor mask blur"
},
"face_editor_mask_size": {
"type": "integer",
"title": "Face Editor Mask Size",
"default": 6,
"x-order": 33,
"description": "Face editor mask size"
},
"face_editor_strength1": {
"type": "number",
"title": "Face Editor Strength1",
"default": 0.4,
"maximum": 0.8,
"minimum": 0.1,
"x-order": 31,
"description": "Step 0.05, face editor, denoising strength for face images, sdwebui:(3) Recreate the Faces"
},
"face_editor_strength2": {
"type": "number",
"title": "Face Editor Strength2",
"default": 0.05,
"maximum": 1,
"minimum": 0,
"x-order": 32,
"description": "Step 0.05, face editor, denoising strength for the entire image, sdwebui:(5) Blend the entire image"
},
"restore_face_upsample": {
"type": "boolean",
"title": "Restore Face Upsample",
"default": true,
"x-order": 27,
"description": "Restore face upsampling"
},
"control_guidance_start": {
"type": "number",
"title": "Control Guidance Start",
"default": 0,
"maximum": 1,
"minimum": 0,
"x-order": 19,
"description": "The percentage of total steps at which the controlnet starts applying"
},
"face_editor_confidence": {
"type": "number",
"title": "Face Editor Confidence",
"default": 0.97,
"maximum": 1,
"minimum": 0.7,
"x-order": 35,
"description": "Confidence threshold for face detection. Set a lower value if you want to detect more faces. "
},
"controlnet_conditioning_scale": {
"type": "number",
"title": "Controlnet Conditioning Scale",
"default": 1,
"maximum": 2,
"minimum": 0,
"x-order": 16,
"description": "Control Weight"
},
"restore_face_background_enhance": {
"type": "boolean",
"title": "Restore Face Background Enhance",
"default": true,
"x-order": 28,
"description": "Restore face background enhance"
}
}
}
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"
}