You're looking at a specific version of this model. Jump to the model overview.
nsfw-api /sdxl-pulid:e3c8b5ca
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
|
Main text prompt.
|
|
| negative_prompt |
string
|
|
Optional negative.
|
| reference_image |
string
|
An image containing a face that you want to use as reference for face swapping.
|
|
| width |
integer
|
512
Min: 64 Max: 1536 |
None
|
| height |
integer
|
512
Min: 64 Max: 1536 |
None
|
| steps |
integer
|
30
Min: 1 Max: 150 |
None
|
| cfg |
number
|
3
Min: 1 Max: 20 |
None
|
| sampler_name |
None
|
euler_ancestral
|
None
|
| scheduler |
None
|
normal
|
None
|
| seed |
integer
|
0
|
0 = random
|
| method |
None
|
fidelity
|
PuLID method to use: fidelity for face swapping, style for style transfer, both for a mix.
|
| face_weight |
number
|
0.8
Max: 1 |
Weight of the face adaptation effect (0.0 to 1.0)
|
| scene_image |
string
|
A full-scene image whose pose **and** depth will guide generation.
|
|
| pose_weight |
number
|
0.8
Max: 1 |
Weight for the OpenPose ControlNet (node 21).
|
| depth_weight |
number
|
0.6
Max: 1 |
Weight for the Depth ControlNet (node 24).
|
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'}