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

shanginn /supir:2721bb51

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
model_name
string (enum)
SUPIR-v0Q

Options:

SUPIR-v0Q, SUPIR-v0F

Choose a model. SUPIR-v0Q is the default training settings with paper. SUPIR-v0F is high generalization and high image quality in most cases. Training with light degradation settings. Stage1 encoder of SUPIR-v0F remains more details when facing light degradations.
image
string
Low quality input image.
upscale
integer
1
Upsampling ratio of given inputs.
min_size
number
1024
Minimum resolution of output images.
edm_steps
integer
50

Min: 1

Max: 500

Number of steps for EDM Sampling Schedule.
use_llava
boolean
True
Use LLaVA model to get captions.
a_prompt
string
Cinematic, High Contrast, highly detailed, taken using a Canon EOS R camera, hyper detailed photo - realistic maximum detail, 32k, Color Grading, ultra HD, extreme meticulous detailing, skin pore detailing, hyper sharpness, perfect without deformations.
Additive positive prompt for the inputs.
n_prompt
string
painting, oil painting, illustration, drawing, art, sketch, oil painting, cartoon, CG Style, 3D render, unreal engine, blurring, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth
Negative prompt for the inputs.
color_fix_type
string (enum)
Wavelet

Options:

None, AdaIn, Wavelet

Color Fixing Type..
s_stage1
integer
-1
Control Strength of Stage1 (negative means invalid).
s_churn
number
5
Original churn hy-param of EDM.
s_noise
number
1.003
Original noise hy-param of EDM.
s_cfg
number
7.5

Min: 1

Max: 20

Classifier-free guidance scale for prompts.
s_stage2
number
1
Control Strength of Stage2.
linear_CFG
boolean
False
Linearly (with sigma) increase CFG from 'spt_linear_CFG' to s_cfg.
linear_s_stage2
boolean
False
Linearly (with sigma) increase s_stage2 from 'spt_linear_s_stage2' to s_stage2.
spt_linear_CFG
number
1
Start point of linearly increasing CFG.
spt_linear_s_stage2
number
0
Start point of linearly increasing s_stage2.
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'}