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
|
Make the person smile
|
Text prompt describing the desired image edit
|
| image |
string
|
Input image to edit
|
|
| image_2 |
string
|
Optional second input image for multi-image operations
|
|
| image_3 |
string
|
Optional third input image for multi-image operations
|
|
| negative_prompt |
string
|
(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar
|
Negative prompt to guide what should not be in the image
|
| width |
integer
|
1024
Min: 256 Max: 1024 |
Width of output image
|
| height |
integer
|
1024
Min: 256 Max: 1024 |
Height of output image
|
| num_inference_steps |
integer
|
50
Min: 20 Max: 100 |
Number of denoising steps
|
| text_guidance_scale |
number
|
5
Min: 1 Max: 8 |
Guidance scale for text prompt
|
| image_guidance_scale |
number
|
2
Min: 1 Max: 3 |
Guidance scale for input image. Higher values increase consistency with input image
|
| cfg_range_start |
number
|
0
Max: 1 |
CFG range start
|
| cfg_range_end |
number
|
1
Max: 1 |
CFG range end
|
| scheduler |
string
(enum)
|
euler
Options: euler, dpmsolver |
Scheduler to use
|
| max_input_image_side_length |
integer
|
2048
Min: 256 Max: 2048 |
Maximum input image side length
|
| max_pixels |
integer
|
1048576
Min: 65536 Max: 2359296 |
Maximum number of pixels in output
|
| seed |
integer
|
-1
|
Random seed. Set to -1 for random seed
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}