You're looking at a specific version of this model. Jump to the model overview.
lucataco /demofusion-enhance:687b4197
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
|
|
| scale |
integer
(enum)
|
2
Options: 1, 2, 4 |
Scale factor for input image
|
| prompt |
string
|
A high resolution photo
|
Input prompt
|
| auto_prompt |
boolean
|
False
|
Select to use auto-generated CLIP prompt instead of using the above custom prompt
|
| negative_prompt |
string
|
blurry, ugly, duplicate, poorly drawn, deformed, mosaic
|
Input Negative Prompt
|
| num_inference_steps |
integer
|
40
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
8.5
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| view_batch_size |
integer
|
16
|
The batch size for multiple denoising paths
|
| stride |
integer
|
64
|
The stride of moving local patches
|
| cosine_scale_1 |
number
|
3
|
Control the strength of skip-residual
|
| cosine_scale_2 |
number
|
1
|
Control the strength of dilated sampling
|
| cosine_scale_3 |
number
|
1
|
Control the strength of the Gaussian filter
|
| sigma |
number
|
0.8
|
The standard value of the Gaussian filter
|
| multi_decoder |
boolean
|
False
|
Use multiple decoders
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}