You're looking at a specific version of this model. Jump to the model overview.
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 |
|---|---|---|---|
| input_fg |
string
|
Input foreground image
|
|
| prompt |
string
|
Prompt for relighting
|
|
| image_width |
integer
|
512
Min: 256 Max: 1024 |
Width of the output image
|
| image_height |
integer
|
640
Min: 256 Max: 1024 |
Height of the output image
|
| num_samples |
integer
|
1
Min: 1 Max: 12 |
Number of images to generate
|
| seed |
integer
|
12345
|
Random seed
|
| steps |
integer
|
25
Min: 1 Max: 100 |
Number of sampling steps
|
| a_prompt |
string
|
best quality
|
Additional prompt
|
| n_prompt |
string
|
lowres, bad anatomy, bad hands, cropped, worst quality
|
Negative prompt
|
| cfg |
number
|
2
Min: 1 Max: 32 |
CFG scale
|
| highres_scale |
number
|
1.5
Min: 1 Max: 3 |
Highres scale
|
| highres_denoise |
number
|
0.5
Min: 0.1 Max: 1 |
Highres denoise
|
| lowres_denoise |
number
|
0.9
Min: 0.1 Max: 1 |
Lowres denoise (for initial latent)
|
| bg_source |
string
(enum)
|
None
Options: None, Left Light, Right Light, Top Light, Bottom Light |
Lighting preference (initial latent)
|
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'}