You're looking at a specific version of this model. Jump to the model overview.
nsfw-api /realvis-hyper-lora:2bca5aa4
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
|
lowres, bad anatomy
|
Negative prompt.
|
| reference_image |
string
|
An image containing a face that you want to use as reference for face swapping.
|
|
| depth_image |
string
|
RGB image that will be converted to a depth map and used as ControlNet guidance (optional).
|
|
| width |
integer
|
768
Min: 64 Max: 1536 |
None
|
| height |
integer
|
1024
Min: 64 Max: 1536 |
None
|
| steps |
integer
|
30
Min: 1 Max: 150 |
None
|
| cfg |
number
|
7
Min: 1 Max: 20 |
None
|
| sampler_name |
None
|
dpmpp_2m_sde
|
None
|
| scheduler |
None
|
karras
|
None
|
| seed |
integer
|
0
|
0 = random
|
| face_weight |
number
|
0.8
Max: 1 |
Weight of the face adaptation effect (0.0 to 1.0)
|
| instantid_weight |
number
|
0.8
Max: 1 |
Weight of the InstantID effect (0.0 to 1.0)
|
| depth_strength |
number
|
1
Max: 2 |
How strongly the depth map constrains generation (only used if depth_image provided)
|
| facedetail_strength |
number
|
0.5
Max: 1 |
Strength of face detail enhancement
|
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'}