You're looking at a specific version of this model. Jump to the model overview.
zsxkib /instant-id:f1ca369d
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 face image
|
|
| pose_image |
string
|
(Optional) reference pose image
|
|
| prompt |
string
|
a person
|
Input prompt
|
| negative_prompt |
string
|
|
Input Negative Prompt
|
| sdxl_weights |
string
(enum)
|
stable-diffusion-xl-base-1.0
Options: stable-diffusion-xl-base-1.0, juggernaut-xl-v8, afrodite-xl-v2, albedobase-xl-20, albedobase-xl-v13, animagine-xl-30, anime-art-diffusion-xl, anime-illust-diffusion-xl, dreamshaper-xl, dynavision-xl-v0610, guofeng4-xl, nightvision-xl-0791, omnigen-xl, pony-diffusion-v6-xl, protovision-xl-high-fidel, RealVisXL_V3.0_Turbo, RealVisXL_V4.0_Lightning |
Pick which base weights you want to use
|
| face_detection_input_width |
integer
|
640
Min: 640 Max: 4096 |
Width of the input image for face detection
|
| face_detection_input_height |
integer
|
640
Min: 640 Max: 4096 |
Height of the input image for face detection
|
| scheduler |
string
(enum)
|
EulerDiscreteScheduler
Options: DEISMultistepScheduler, HeunDiscreteScheduler, EulerDiscreteScheduler, DPMSolverMultistepScheduler, DPMSolverMultistepScheduler-Karras, DPMSolverMultistepScheduler-Karras-SDE |
Scheduler
|
| num_inference_steps |
integer
|
30
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| ip_adapter_scale |
number
|
0.8
Max: 1.5 |
Scale for image adapter strength (for detail)
|
| controlnet_conditioning_scale |
number
|
0.8
Max: 1.5 |
Scale for IdentityNet strength (for fidelity)
|
| enable_pose_controlnet |
boolean
|
True
|
Enable Openpose ControlNet, overrides strength if set to false
|
| pose_strength |
number
|
0.4
Max: 1 |
Openpose ControlNet strength, effective only if `enable_pose_controlnet` is true
|
| enable_canny_controlnet |
boolean
|
False
|
Enable Canny ControlNet, overrides strength if set to false
|
| canny_strength |
number
|
0.3
Max: 1 |
Canny ControlNet strength, effective only if `enable_canny_controlnet` is true
|
| enable_depth_controlnet |
boolean
|
False
|
Enable Depth ControlNet, overrides strength if set to false
|
| depth_strength |
number
|
0.5
Max: 1 |
Depth ControlNet strength, effective only if `enable_depth_controlnet` is true
|
| enable_lcm |
boolean
|
False
|
Enable Fast Inference with LCM (Latent Consistency Models) - speeds up inference steps, trade-off is the quality of the generated image. Performs better with close-up portrait face images
|
| lcm_num_inference_steps |
integer
|
5
Min: 1 Max: 10 |
Only used when `enable_lcm` is set to True, Number of denoising steps when using LCM
|
| lcm_guidance_scale |
number
|
1.5
Min: 1 Max: 20 |
Only used when `enable_lcm` is set to True, Scale for classifier-free guidance when using LCM
|
| enhance_nonface_region |
boolean
|
True
|
Enhance non-face region
|
| output_format |
string
(enum)
|
webp
Options: webp, jpg, png |
Format of the output images
|
| output_quality |
integer
|
80
Max: 100 |
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| num_outputs |
integer
|
1
Min: 1 Max: 8 |
Number of images to output
|
| disable_safety_checker |
boolean
|
False
|
Disable safety checker for generated images
|
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'}