cjwbw/supir-v0f
Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This is the SUPIR-v0F model and does NOT use LLaVA-13b.
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
image* | string(uri) | Low quality input image. | — | — |
a_prompt | string | Additive positive prompt for the inputs. | "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." | — |
color_fix_type | string | Color Fixing Type.. | "Wavelet" | NoneAdaInWavelet |
edm_steps | integer | Number of steps for EDM Sampling Schedule. | 50 | min: 1, max: 500 |
linear_CFG | boolean | Linearly (with sigma) increase CFG from 'spt_linear_CFG' to s_cfg. | false | — |
linear_s_stage2 | boolean | Linearly (with sigma) increase s_stage2 from 'spt_linear_s_stage2' to s_stage2. | false | — |
min_size | number | Minimum resolution of output images. | 1024 | — |
n_prompt | string | Negative prompt for the inputs. | "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" | — |
s_cfg | number | Classifier-free guidance scale for prompts. | 7.5 | min: 1, max: 20 |
s_churn | number | Original churn hy-param of EDM. | 5 | — |
s_noise | number | Original noise hy-param of EDM. | 1.003 | — |
s_stage1 | integer | Control Strength of Stage1 (negative means invalid). | -1 | — |
s_stage2 | number | Control Strength of Stage2. | 1 | — |
seed | integer | Random seed. Leave blank to randomize the seed | — | — |
spt_linear_CFG | number | Start point of linearly increasing CFG. | 1 | — |
spt_linear_s_stage2 | number | Start point of linearly increasing s_stage2. | 0 | — |
upscale | integer | Upsampling ratio of given inputs. | 1 | — |
imagerequiredstringLow quality input image.
a_promptstringAdditive positive prompt for the inputs.
"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."color_fix_typestringColor Fixing Type..
"Wavelet"edm_stepsintegerNumber of steps for EDM Sampling Schedule.
50min: 1, max: 500linear_CFGbooleanLinearly (with sigma) increase CFG from 'spt_linear_CFG' to s_cfg.
falselinear_s_stage2booleanLinearly (with sigma) increase s_stage2 from 'spt_linear_s_stage2' to s_stage2.
falsemin_sizenumberMinimum resolution of output images.
1024n_promptstringNegative prompt for the inputs.
"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"s_cfgnumberClassifier-free guidance scale for prompts.
7.5min: 1, max: 20s_churnnumberOriginal churn hy-param of EDM.
5s_noisenumberOriginal noise hy-param of EDM.
1.003s_stage1integerControl Strength of Stage1 (negative means invalid).
-1s_stage2numberControl Strength of Stage2.
1seedintegerRandom seed. Leave blank to randomize the seed
spt_linear_CFGnumberStart point of linearly increasing CFG.
1spt_linear_s_stage2numberStart point of linearly increasing s_stage2.
0upscaleintegerUpsampling ratio of given inputs.
1b9c26267b41fUpdated: 7/25/202620.5K runs
cinemasetfree.com