cjwbw/supir 🔢🖼️📝✓❓ → 🖼️

▶️ 189.5K runs 📅 Feb 2024 ⚙️ Cog 0.9.4 🔗 GitHub 📄 Paper ⚖️ License
image-restoration image-upscaling

About

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This version uses LLaVA-13b for captioning.

Example Output

Output

Example output

Performance Metrics

18.57s Prediction Time
859.90s Total Time
All Input Parameters
{
  "image": "https://replicate.delivery/pbxt/KSFJ6sJWyEiPWysywNsAr2enzigJA3NZpG4YMrxrSFEIEShi/05.png",
  "s_cfg": 7.5,
  "s_churn": 5,
  "s_noise": 1.003,
  "upscale": 1,
  "a_prompt": "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.",
  "min_size": 1024,
  "n_prompt": "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_stage1": -1,
  "s_stage2": 1,
  "edm_steps": 50,
  "use_llava": true,
  "linear_CFG": false,
  "model_name": "SUPIR-v0Q",
  "color_fix_type": "Wavelet",
  "spt_linear_CFG": 1,
  "linear_s_stage2": false,
  "spt_linear_s_stage2": 0
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
image (required) Type: string
Low quality input image.
s_cfg Type: numberDefault: 7.5Range: 1 - 20
Classifier-free guidance scale for prompts.
s_churn Type: numberDefault: 5
Original churn hy-param of EDM.
s_noise Type: numberDefault: 1.003
Original noise hy-param of EDM.
upscale Type: integerDefault: 1
Upsampling ratio of given inputs.
a_prompt Type: stringDefault: 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.
min_size Type: numberDefault: 1024
Minimum resolution of output images.
n_prompt Type: stringDefault: 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.
s_stage1 Type: integerDefault: -1
Control Strength of Stage1 (negative means invalid).
s_stage2 Type: numberDefault: 1
Control Strength of Stage2.
edm_steps Type: integerDefault: 50Range: 1 - 500
Number of steps for EDM Sampling Schedule.
use_llava Type: booleanDefault: true
Use LLaVA model to get captions.
linear_CFG Type: booleanDefault: false
Linearly (with sigma) increase CFG from 'spt_linear_CFG' to s_cfg.
model_name Default: SUPIR-v0Q
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.
color_fix_type Default: Wavelet
Color Fixing Type..
spt_linear_CFG Type: numberDefault: 1
Start point of linearly increasing CFG.
linear_s_stage2 Type: booleanDefault: false
Linearly (with sigma) increase s_stage2 from 'spt_linear_s_stage2' to s_stage2.
spt_linear_s_stage2 Type: numberDefault: 0
Start point of linearly increasing s_stage2.
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Using seed: 12774
Captions from LLaVA: ['The image features a beautiful bird perched on a thin, dry branch in a field. The bird is colorful and stands out against the brown background of the field. The branch is located in the middle of the scene, with the bird sitting on it, drawing attention to itself. The field is filled with a variety of flowers, adding a vibrant touch to the scene. The overall style of the image is artistic, with a focus on the bird and its natural surroundings.']
Seed set to 12774
Version Details
Version ID
1302b550b4f7681da87ed0e405016d443fe1fafd64dabce6673401855a5039b5
Version Created
February 23, 2024
Run on Replicate →