
chuckchen/supir-v0f

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild, using tiled VAE and Juggernaut XL lightning to eliminate plastic skin and smooth textures.
Run chuckchen/supir-v0f with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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
|
Low quality input image.
|
|
upscale |
integer
|
1
|
Upsampling ratio of given inputs.
|
min_size |
number
|
1024
|
Minimum resolution of output images.
|
edm_steps |
integer
|
8
Min: 1 Max: 500 |
Number of steps for EDM Sampling Schedule.
|
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 |
None
|
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
|
2
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
|
2
|
Start point of linearly increasing CFG.
|
spt_linear_s_stage2 |
number
|
0
|
Start point of linearly increasing s_stage2.
|
output_format |
None
|
jpeg
|
Output image format.
|
output_quality |
integer
|
90
Min: 1 Max: 100 |
Quality for JPEG output (1-100).
|
seed |
integer
|
Random seed. Leave blank to randomize the seed
|
{
"type": "object",
"title": "Input",
"required": [
"image"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 18,
"description": "Random seed. Leave blank to randomize the seed"
},
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 0,
"description": "Low quality input image."
},
"s_cfg": {
"type": "number",
"title": "S Cfg",
"default": 2,
"maximum": 20,
"minimum": 1,
"x-order": 10,
"description": " Classifier-free guidance scale for prompts."
},
"s_churn": {
"type": "number",
"title": "S Churn",
"default": 5,
"x-order": 8,
"description": "Original churn hy-param of EDM."
},
"s_noise": {
"type": "number",
"title": "S Noise",
"default": 1.003,
"x-order": 9,
"description": "Original noise hy-param of EDM."
},
"upscale": {
"type": "integer",
"title": "Upscale",
"default": 1,
"x-order": 1,
"description": "Upsampling ratio of given inputs."
},
"a_prompt": {
"type": "string",
"title": "A Prompt",
"default": "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.",
"x-order": 4,
"description": "Additive positive prompt for the inputs."
},
"min_size": {
"type": "number",
"title": "Min Size",
"default": 1024,
"x-order": 2,
"description": "Minimum resolution of output images."
},
"n_prompt": {
"type": "string",
"title": "N Prompt",
"default": "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",
"x-order": 5,
"description": "Negative prompt for the inputs."
},
"s_stage1": {
"type": "integer",
"title": "S Stage1",
"default": -1,
"x-order": 7,
"description": "Control Strength of Stage1 (negative means invalid)."
},
"s_stage2": {
"type": "number",
"title": "S Stage2",
"default": 1,
"x-order": 11,
"description": "Control Strength of Stage2."
},
"edm_steps": {
"type": "integer",
"title": "Edm Steps",
"default": 8,
"maximum": 500,
"minimum": 1,
"x-order": 3,
"description": "Number of steps for EDM Sampling Schedule."
},
"linear_CFG": {
"type": "boolean",
"title": "Linear Cfg",
"default": false,
"x-order": 12,
"description": "Linearly (with sigma) increase CFG from 'spt_linear_CFG' to s_cfg."
},
"output_format": {
"enum": [
"png",
"jpeg"
],
"type": "string",
"title": "output_format",
"description": "Output image format.",
"default": "jpeg",
"x-order": 16
},
"color_fix_type": {
"enum": [
"None",
"AdaIn",
"Wavelet"
],
"type": "string",
"title": "color_fix_type",
"description": "Color Fixing Type..",
"default": "Wavelet",
"x-order": 6
},
"output_quality": {
"type": "integer",
"title": "Output Quality",
"default": 90,
"maximum": 100,
"minimum": 1,
"x-order": 17,
"description": "Quality for JPEG output (1-100)."
},
"spt_linear_CFG": {
"type": "number",
"title": "Spt Linear Cfg",
"default": 2,
"x-order": 14,
"description": "Start point of linearly increasing CFG."
},
"linear_s_stage2": {
"type": "boolean",
"title": "Linear S Stage2",
"default": false,
"x-order": 13,
"description": "Linearly (with sigma) increase s_stage2 from 'spt_linear_s_stage2' to s_stage2."
},
"spt_linear_s_stage2": {
"type": "number",
"title": "Spt Linear S Stage2",
"default": 0,
"x-order": 15,
"description": "Start point of linearly increasing s_stage2."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}