You're looking at a specific version of this model. Jump to the model overview.
nightmareai /k-diffusion:d688fdd8
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 |
|---|---|---|---|
| text_prompt |
string
|
A mysterious orb by Ernst Fuchs
|
Prompt
|
| sampling_mode |
string
(enum)
|
DPM-2
Options: Huen, DPM-2 |
Sampling mode
|
| height |
integer
|
256
|
Output Height (divisible by 64)
|
| width |
integer
|
256
|
Output Width (divisible by 64)
|
| churn |
number
|
50
|
The amount of noise to add during sampling
|
| init_image |
string
|
Initial image for the generation
|
|
| sigma_start |
integer
|
10
|
The starting noise level when using an init image
|
| init_scale |
integer
|
1000
|
This enhances the effect of the init image, a good value is 1000.
|
| image_prompt |
string
|
Image prompt (CLIP only)
|
|
| n_steps |
integer
|
500
Min: 50 Max: 1000 |
The number of timesteps to use
|
| latent_scale |
integer
|
5
|
Latent guidance scale, higher for stronger latent guidance.
|
| clip_guidance_scale |
integer
|
1000
|
CLIP guidance scale, higher for stronger clip guidance. 0 to disable CLIP guidance.
|
| cutn |
integer
|
16
|
The number of random crops per step.
|
| cut_pow |
number
|
0.5
|
Cut power
|
| seed |
integer
|
Max: 4294967295 |
Seed (leave empty to use a random seed)
|
| output_steps |
integer
|
10
Max: 50 |
Display an image after this many steps.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array',
'x-cog-array-type': 'iterator'}