philz1337x/clarity-upscaler

High resolution image Upscaler and Enhancer. Use at ClarityAI.co. A free Magnific alternative. Twitter/X: @philz1337x

Capabilities

Reference Images Negative Prompt Seed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`image` *	string (uri)	input image	`—`	—
`creativity`	number	Creativity, try from 0.3 - 0.9	`0.35`	min: 0, max: 1
`custom_sd_model`	string	—	`""`	—
`downscaling`	boolean	Downscale the image before upscaling. Can improve quality and speed for images with high resolution but lower quality	`false`	—
`downscaling_resolution`	integer	Downscaling resolution	`768`	—
`dynamic`	number	HDR, try from 3 - 9	`6`	min: 1, max: 50
`handfix`	string	Use clarity to fix hands in the image	`"disabled"`	disabled hands_only image_and_hands
`lora_links`	string	Link to a lora file you want to use in your upscaling. Multiple links possible, seperated by comma	`""`	—
`mask`	string (uri)	Mask image to mark areas that should be preserved during upscaling	`—`	—
`negative_prompt`	string	Negative Prompt	`"(worst quality, low quality, normal quality:2) JuggernautNegative-neg"`	—
`num_inference_steps`	integer	Number of denoising steps	`18`	min: 1, max: 100
`output_format`	string	Format of the output images	`"png"`	webp jpg png
`pattern`	boolean	Upscale a pattern with seamless tiling	`false`	—
`prompt`	string	Prompt	`"masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>"`	—
`resemblance`	number	Resemblance, try from 0.3 - 1.6	`0.6`	min: 0, max: 3
`scale_factor`	number	Scale factor	`2`	—
`scheduler`	string	scheduler	`"DPM++ 3M SDE Karras"`	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
`sd_model`	string	Stable Diffusion model checkpoint	`"juggernaut_reborn.safetensors [338b85bc4f]"`	epicrealism_naturalSinRC1VAE.safetensors [84d76a0328] juggernaut_reborn.safetensors [338b85bc4f] flat2DAnimerge_v45Sharp.safetensors
`seed`	integer	Random seed. Leave blank to randomize the seed	`1337`	—
`sharpen`	number	Sharpen the image after upscaling. The higher the value, the more sharpening is applied. 0 for no sharpening	`0`	min: 0, max: 10
`tiling_height`	integer	Fractality, set lower tile height for a high Fractality	`144`	16 32 48 64 80 96 112 128 144 160 176 192 208 224 240 256
`tiling_width`	integer	Fractality, set lower tile width for a high Fractality	`112`	16 32 48 64 80 96 112 128 144 160 176 192 208 224 240 256

image required string

input image

creativity number

Creativity, try from 0.3 - 0.9

Default: 0.35 min: 0, max: 1

custom_sd_model string

Default: ""

downscaling boolean

Downscale the image before upscaling. Can improve quality and speed for images with high resolution but lower quality

Default: false

downscaling_resolution integer

Downscaling resolution

Default: 768

dynamic number

HDR, try from 3 - 9

Default: 6 min: 1, max: 50

handfix string

Use clarity to fix hands in the image

Default: "disabled"

disabled hands_only image_and_hands

lora_links string

Link to a lora file you want to use in your upscaling. Multiple links possible, seperated by comma

Default: ""

mask string

Mask image to mark areas that should be preserved during upscaling

negative_prompt string

Negative Prompt

Default: "(worst quality, low quality, normal quality:2) JuggernautNegative-neg"

num_inference_steps integer

Number of denoising steps

Default: 18 min: 1, max: 100

output_format string

Format of the output images

Default: "png"

webp jpg png

pattern boolean

Upscale a pattern with seamless tiling

Default: false

prompt string

Prompt

Default: "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>"

resemblance number

Resemblance, try from 0.3 - 1.6

Default: 0.6 min: 0, max: 3

scale_factor number

Scale factor

Default: 2

scheduler string

scheduler

Default: "DPM++ 3M SDE Karras"

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

sd_model string

Stable Diffusion model checkpoint

Default: "juggernaut_reborn.safetensors [338b85bc4f]"

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

seed integer

Random seed. Leave blank to randomize the seed

Default: 1337

sharpen number

Sharpen the image after upscaling. The higher the value, the more sharpening is applied. 0 for no sharpening

Default: 0 min: 0, max: 10

tiling_height integer

Fractality, set lower tile height for a high Fractality

Default: 144

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

tiling_width integer

Fractality, set lower tile width for a high Fractality

Default: 112

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

Version: dfad41707589 Updated: 6/8/2026 27.1M runs