You're looking at a specific version of this model. Jump to the model overview.
jyoung105 /instant-style:a11eb1cb
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 |
|---|---|---|---|
| style_image |
string
|
Input reference image
|
|
| prompt |
string
|
Input prompt
|
|
| negative_prompt |
string
|
Input negative prompt
|
|
| width |
integer
|
1024
Min: 512 Max: 2048 |
Width of output image
|
| height |
integer
|
1024
Min: 512 Max: 2048 |
Height of output image
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of output images
|
| num_inference_steps |
integer
|
30
Min: 1 Max: 50 |
Number of denoising steps
|
| guidance_scale |
number
|
5
Min: 1 Max: 20 |
Scale for classifier-free guidance
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| style_strength |
number
|
1
Max: 2 |
Conditioning scale for ip-adapter
|
| block_mode |
string
(enum)
|
style-only
Options: original, style-only, style-and-layout |
Mode to reference the image: original, style with or without layout
|
| adapter_mode |
string
(enum)
|
original
Options: original, plus |
Mode to reference the image: high flexibility but low fidelity or low flexibility but high fidelity
|
| enable_negative_content |
boolean
|
False
|
Choose whether you extract only style part of prompt or not
|
| negative_content |
string
|
Input negative prompt
|
|
| negative_content_strength |
number
|
0.5
Max: 1 |
Conditioning scale for content you want to exclude
|
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'}