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 |
|---|---|---|---|
| image |
string
|
Input image for img2img or inpaint mode
|
|
| prompt |
string
|
a robot in a futuristic city, 4k
|
Input prompt
|
| negative_prompt |
string
|
low quality, bad quality, sketches
|
Input Negative Prompt
|
| num_inference_steps |
integer
|
35
Min: 1 Max: 500 |
Number of denoising steps
|
| adapter_conditioning_scale |
number
|
0.9
|
T2I-Adapter conditioning scale
|
| seed |
integer
|
0
|
Random seed. Set to 0 to randomize the seed
|
| guidance_scale |
number
|
7.5
Max: 20 |
Guidance scale for prompt adherence
|
| 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 images to generate
|
| use_canny |
boolean
|
False
|
Use Canny edge detection
|
| canny_threshold1 |
integer
|
100
Min: 1 Max: 255 |
Lower threshold for Canny edge detection
|
| canny_threshold2 |
integer
|
200
Min: 1 Max: 255 |
Upper threshold for Canny edge detection
|
| dilation_iterations |
integer
|
1
Max: 5 |
Number of dilation iterations to thicken Canny edges
|
| sampler |
string
(enum)
|
Euler a
Options: Euler, Euler a, DPM++ 2M Karras, DPM++ 2M SDE Karras, DPM++ Karras SDE, DPM++ Karras |
Choose the sampler
|
| generate_square |
boolean
|
False
|
Whether to generate square image
|
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'}