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
|
|
None
|
negative_prompt |
string
|
|
Things you do not want to see in your image
|
number_of_images |
integer
|
1
Min: 1 Max: 10 |
Number of images to generate
|
width |
integer
|
1024
|
None
|
height |
integer
|
1024
|
None
|
lora_strength |
number
|
1
Max: 3 |
Strength of the lora to use for the generation. Default is 1.0.
|
image |
string
|
Optional. Image to use for img2img generation. Leave empty to use just a prompt.
|
|
denoise_strength |
number
|
0.65
Max: 1 |
How much of the original input image to destroy when using img2img. 1 is total destruction. 0 is untouched. 0.65 is a good balance.
|
output_format |
None
|
webp
|
Format of the output images
|
output_quality |
integer
|
80
Max: 100 |
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
|
seed |
integer
|
Set a seed for reproducibility. Random by default.
|
|
disable_safety_checker |
boolean
|
False
|
Disable safety checker for generated images.
|
sampler |
None
|
Default
|
Advanced. Change the sampler used for generation. Default is what we think gives the best images.
|
scheduler |
None
|
Default
|
Advanced. Change the scheduler used for generation. Default is what we think gives the best images.
|
steps |
integer
|
Min: 1 Max: 50 |
Advanced. Leave empty to use recommended steps. Set it only if you want to customise the number of steps to run the sampler for.
|
cfg |
number
|
Max: 20 |
Advanced. Leave empty to use recommended CFG (classifier free guidance). This changes how much the prompt influences the output. Set it only if you want to customise.
|
controlnet_image |
string
|
Advanced. The image to use with a controlnet. Leave empty to use no controlnet.
|
|
controlnet_model |
None
|
None
|
Advanced. Change the model used for the controlnet. Make sure it matches the checkpoint type (eg SD15 or SDXL) and pick an appropriate controlnet preprocessor to go with it.
|
controlnet_preprocessor |
None
|
None
|
Advanced. Change the preprocessor used for the controlnet. Make sure it matches the controlnet model you're using.
|
controlnet_return_preprocessor_image |
boolean
|
False
|
Advanced. Return the processed image from the controlnet preprocessor. Useful for debugging.
|
controlnet_strength |
number
|
1
Max: 3 |
Advanced. Strength of the controlnet. Default is 1.0.
|
controlnet_start |
number
|
0
Max: 1 |
Advanced. When to begin applying the controlnet.
|
controlnet_end |
number
|
1
Max: 1 |
Advanced. When to stop applying the controlnet.
|
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'}