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
|
Modern skyscraper, glass facade, urban skyline, clear day.
|
Input prompt
|
| model_name |
string
|
stabilityai/stable-diffusion-xl-base-1.0
|
The model name to use. Defaults to 'stabilityai/stable-diffusion-xl-base-1.0'
|
| suffix_prompt |
string
|
Futuristic Concept, Cutting-Edge Technology, Historical Landmark, Timeless Aesthetics, sharp focus, 8k, uhd, file grain, masterpiece
|
Additional prompt
|
| negative_prompt |
string
|
deformed, animation, anime, cartoon, comic, cropped, out of frame, low res, draft, cgi, low quality render, thumbnail
|
Input Negative Prompt
|
| lora_input |
string
|
|
Comma-separated list of LoRA models from Hugging Face or local paths. Leave empty to skip LoRA.
|
| lora_scale |
string
|
|
Comma-separated list of scales for each LoRA model. Must match the number of LoRAs. Leave empty if no LoRA is used.
|
| width |
integer
|
1024
|
Width of output image
|
| height |
integer
|
1024
|
Height of output image
|
| generate_square |
boolean
|
False
|
Whether generate square image, assert height == width
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output.
|
| num_inference_steps |
integer
|
35
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| adapter_conditioning_scale |
number
|
0.9
Max: 2 |
Scale for adapter module
|
| seed |
integer
|
0
|
Random seed. Enter 0 to randomize the seed
|
| sampler |
string
(enum)
|
Euler a
Options: DPM++ 2M Karras, DPM++ 2M SDE Karras, DPM++ Karras SDE, DPM++ Karras, Euler, Euler a |
The sampling method
|
| use_canny |
boolean
|
False
|
Whether to use canny detector for better details
|
| dilation_iterations |
integer
|
1
Max: 5 |
Number of dilation iterations to thicken Canny edges
|
| blur_kernel_size |
integer
|
11
Max: 31 |
Kernel size for Gaussian blur to smooth edges before Canny detection. Set to 0 to skip blur.
|
| dilation_kernel_size |
integer
|
3
Min: 1 Max: 31 |
Kernel size for dilation to thicken edges. Adjust to make edges smoother or thicker.
|
| image |
string
|
Input image for img2img or inpaint mode
|
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'}