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 |
---|---|---|---|
prompt |
string
|
Prompt for image generation
|
|
ref_image1 |
string
|
Reference image 1 (optional)
|
|
ref_task1 |
string
(enum)
|
ip
Options: ip, id, style |
Task for reference image 1 ('ip': object/character, 'id': face identity, 'style': preserve style/background)
|
ref_image2 |
string
|
Reference image 2 (optional)
|
|
ref_task2 |
string
(enum)
|
ip
Options: ip, id, style |
Task for reference image 2 ('ip': object/character, 'id': face identity, 'style': preserve style/background)
|
width |
integer
|
1024
Min: 768 Max: 1024 |
Width of the output image (must be multiple of 16)
|
height |
integer
|
1024
Min: 768 Max: 1024 |
Height of the output image (must be multiple of 16)
|
num_steps |
integer
|
12
Min: 8 Max: 30 |
Number of inference steps
|
guidance |
number
|
3.5
Min: 1 Max: 10 |
Guidance scale. Lower for less intensity/more realism (e.g., faces), higher for stronger prompt adherence.
|
seed |
integer
|
Random seed. Leave blank or set to -1 for random.
|
|
ref_res |
integer
|
512
Min: 256 Max: 1024 |
Resolution for non-ID reference image preprocessing (target pixel area)
|
neg_prompt |
string
|
|
Negative prompt
|
neg_guidance |
number
|
3.5
Min: 1 Max: 10 |
Negative guidance scale
|
true_cfg |
number
|
1
Min: 1 Max: 5 |
True CFG scale (advanced, requires distilled CFG LoRA)
|
cfg_start_step |
integer
|
0
Max: 30 |
CFG start step (advanced)
|
cfg_end_step |
integer
|
0
Max: 30 |
CFG end step (advanced)
|
first_step_guidance |
number
|
0
Max: 10 |
First step guidance scale override (advanced, 0 uses main guidance)
|
output_format |
string
(enum)
|
webp
Options: webp, jpg, png |
Format of the output image
|
output_quality |
integer
|
90
Min: 1 Max: 100 |
Output quality for lossy formats (jpg, webp)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}