You're looking at a specific version of this model. Jump to the model overview.
underthestar2021 /test:5931b6eb
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
|
| controlnet_enable |
boolean
|
True
|
是否启用Controlnet
|
| controlnet_conditioning_scale |
number
|
1
Max: 2 |
Control Weight
|
| 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.
|
| 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
|
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| 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
|
| swap_face_enable |
boolean
|
True
|
是否使用swap_face(roop的换脸功能),默认True
|
| negative_prompt |
string
|
Specify things to not see in the output
|
|
| face_analyze |
string
|
人脸信息识别，用逗号分隔的字符串. 举例: gender,race,age,emotion
|
|
| restore_face_enable |
boolean
|
True
|
是否使用restore_face,默认True
|
| 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.
|
| clip_skip |
integer
|
2
Min: 1 |
None
|
| 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
|
700
Min: 1 Max: 1024 |
Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
|
| 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
|
| 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.
|
| 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
|
| 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.
|
| 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
|
| 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.
|
| show_system_info |
boolean
|
False
|
Show system info
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}