You're looking at a specific version of this model. Jump to the model overview.
s-henmind /xz-ctr-dunhuang-dt:c8788fff
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
|
Prompt for generated image
|
|
| conditioning_scale |
number
|
0.5
Max: 1 |
ControlNet strength, depth works best at 0.2, canny works best at 0.4. Recommended range is 0.3-0.8
|
| image |
string
|
The image to restyle
|
|
| strength |
number
|
1
Max: 1 |
Img2Img strength
|
| guidance_scale |
number
|
3.5
Max: 30 |
Guidance scale
|
| keep_hair |
boolean
|
False
|
keep hair or not
|
| use_canny |
boolean
|
False
|
use_canny
|
| use_depth |
boolean
|
False
|
use_depth
|
| use_pose |
boolean
|
True
|
use_pose
|
| num_inference_steps |
integer
|
22
Min: 1 Max: 38 |
Number of inference steps
|
| seed |
integer
|
Random seed. Set for reproducible generation
|
|
| output_format |
None
|
jpg
|
Format of the output images
|
| output_quality |
integer
|
100
Max: 100 |
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
|
| style |
string
|
唐风
|
style
|
| lora_scale |
number
|
0.99
Max: 2 |
Scale for the LoRA weights
|
| id_image |
string
|
id image
|
|
| id_image_1 |
string
|
id image
|
|
| id_image_2 |
string
|
id image
|
|
| id_weight |
number
|
0.85
Max: 1 |
id weight
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output.
|
| dilate_pixels |
integer
|
2
Max: 30 |
dilate pixels
|
| repaint_steps |
integer
|
4
Max: 30 |
Number of repaint steps
|
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'}