You're looking at a specific version of this model. Jump to the model overview.

cjwbw /stable-diffusion-aesthetic-gradients:1c590b90

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
a painting of a rvirus monster playing guita
The prompt to render.
n_samples
integer (enum)
1

Options:

1, 4

How many samples to produce for each given prompt. A.k.a. batch size.
width
integer (enum)
512

Options:

128, 256, 512, 768, 1024

Width of the output image. Scale down if run out of memory.
height
integer (enum)
512

Options:

128, 256, 512, 768, 1024

Height of the output image. Scale down if run out of memory.
scale
number
7.5
Unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty)).
ddim_steps
integer
50
Number of ddim sampling steps.
plms
boolean
True
Set to true to use plms sampling
aesthetic_embedding
string (enum)
sac_8plus

Options:

gloomcore, flower_plant, sac_8plus, cloudcore, aivazovsky, glowwave, fantasy, laion_7plus

aesthetic embedding file
aesthetic_steps
integer
10
Number of steps for the aesthetic personalization.
seed
integer
The seed (for reproducible sampling).

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'}