You're looking at a specific version of this model. Jump to the model overview.
usamaehsan /instant-id-x-yamermix-v8:9e1f8007
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
|
analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality
|
Input prompt
|
| image |
string
|
Input image
|
|
| image2 |
string
|
face image2 (experiment --)
|
|
| pose_image |
string
|
pose image (experiment --)
|
|
| negative_prompt |
string
|
|
Input Negative Prompt
|
| width |
integer
|
640
Max: 2048 |
Width for face detection
|
| height |
integer
|
640
Max: 2048 |
Height for face detection
|
| scheduler |
string
(enum)
|
LCMScheduler
Options: LCMScheduler, DDIM, DPMSolverMultistep, HeunDiscrete, K_EULER_ANCESTRAL, K_EULER, KLMS, PNDM, UniPCMultistep, KDPM2DiscreteScheduler, KDPM2AncestralDiscreteScheduler |
Choose a scheduler.
|
| min_side |
integer
|
1024
Max: 2048 |
min resolution // if resize image is on
|
| max_side |
integer
|
1280
Max: 2048 |
min resolution // if resize image is on
|
| resize_image |
boolean
|
True
|
None
|
| enhance_face_region |
boolean
|
True
|
None
|
| ip_adapter_scale |
number
|
0.8
Max: 1 |
Scale for IP adapter
|
| controlnet_conditioning_scale |
number
|
0.8
Max: 1 |
Scale for ControlNet conditioning
|
| num_inference_steps |
integer
|
30
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
5
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| micro_detail_lora_weight |
number
|
0
|
disabled on 0
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}