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

garg-aayush /clarity-upscaler:8f0b827c

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
prompt
string
masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>
Prompt
negative_prompt
string
(worst quality, low quality, normal quality:2) JuggernautNegative-neg
Negative Prompt
scale_factor
number
2
Scale factor
dynamic
number
6

Min: 1

Max: 50

HDR, try from 3 - 9
creativity
number
0.35

Max: 1

Creativity, try from 0.3 - 0.9
resemblance
number
0.6

Max: 3

Resemblance, try from 0.3 - 1.6
tiling_width
integer (enum)
112

Options:

16, 32, 48, 64, 80, 96, 112, 128, 144, 160, 176, 192, 208, 224, 240, 256

Fractality, set lower tile width for a high Fractality
tiling_height
integer (enum)
144

Options:

16, 32, 48, 64, 80, 96, 112, 128, 144, 160, 176, 192, 208, 224, 240, 256

Fractality, set lower tile height for a high Fractality
sd_model
string (enum)
juggernaut_reborn.safetensors [338b85bc4f]

Options:

epicrealism_naturalSinRC1VAE.safetensors [84d76a0328], juggernaut_reborn.safetensors [338b85bc4f], flat2DAnimerge_v45Sharp.safetensors

Stable Diffusion model checkpoint
scheduler
string (enum)
DPM++ 3M SDE Karras

Options:

DPM++ 2M Karras, DPM++ SDE Karras, DPM++ 2M SDE Exponential, DPM++ 2M SDE Karras, Euler a, Euler, LMS, Heun, DPM2, DPM2 a, DPM++ 2S a, DPM++ 2M, DPM++ SDE, DPM++ 2M SDE, DPM++ 2M SDE Heun, DPM++ 2M SDE Heun Karras, DPM++ 2M SDE Heun Exponential, DPM++ 3M SDE, DPM++ 3M SDE Karras, DPM++ 3M SDE Exponential, DPM fast, DPM adaptive, LMS Karras, DPM2 Karras, DPM2 a Karras, DPM++ 2S a Karras, Restart, DDIM, PLMS, UniPC

scheduler
num_inference_steps
integer
18

Min: 1

Max: 100

Number of denoising steps
seed
integer
1337
Random seed. Leave blank to randomize the seed
multistep_factor
number
0.8

Max: 2

Multiplier for the number of denoising steps. 0.9 for 90% less steps, 1.1 for 10% more steps
downscaling
boolean
False
Downscale the image before upscaling. Can improve quality and speed for images with high resolution but lower quality
downscaling_resolution
integer
768
Downscaling resolution
lora_links
string
Link to a lora file you want to use in your upscaling. Multiple links possible, seperated by comma
custom_sd_model
string
None
sharpen
number
0

Max: 10

Sharpen the image after upscaling. The higher the value, the more sharpening is applied. 0 for no sharpening
mask
string
Mask image to mark areas that should be preserved during upscaling
handfix
string (enum)
disabled

Options:

disabled, hands_only, image_and_hands

Use clarity to fix hands in the image
pattern
boolean
False
Upscale a pattern with seamless tiling
output_format
string (enum)
png

Options:

webp, jpg, png

Format of the output images

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'}