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

jagilley /stable-diffusion-upscaler:223ccd9f

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
Image to be upscaled
scale
number
1.5

Max: 10

Factor to scale image by
prompt
string
Prompt. Not strictly required but can subtly affect the upscaling result.
num_samples
integer
1
Number of samples to generate
guidance_scale
number
1

Max: 10

Scale factor for guidance
decoder
string (enum)
finetuned_840k

Options:

finetuned_840k, finetuned_560k

Decoder to use
noise_aug_level
number
0

Max: 0.6

Noise augmentation level
noise_aug_type
string (enum)
gaussian

Options:

gaussian, fake

Noise augmentation type
sampler
string (enum)
k_dpm_adaptive

Options:

k_euler, k_euler_ancestral, k_dpm_2_ancestral, k_dpm_fast, k_dpm_adaptive

Sampler to use
steps
integer
10
Number of steps to take in the diffusion process
tol_scale
number
0.25
Tolerance scale
eta
number
1
ETA

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'}