shanginn/supir 🔢🖼️📝✓❓ → 🖼️

▶️ 132.2K runs 📅 Feb 2024 ⚙️ Cog 0.9.4 🔗 GitHub ⚖️ License

image-restoration image-upscaling

About

Example Output

Output

Performance Metrics

24.52s Prediction Time

218.31s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/KSWNkYxSDPsEOtuWtWrO2nihbpcgfvzeZbefsHCMjnGxl5jM/GLYUQSPobRY.jpg",
  "s_cfg": 7.5,
  "s_churn": 5,
  "s_noise": 1.003,
  "upscale": 2,
  "a_prompt": "hyper detailed, maximum detail, 32k, Color Grading, ultra HD, extreme meticulous detailing, skin pore detailing, hyper sharpness, perfect",
  "min_size": 1024,
  "n_prompt": "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: 2: Upsampling ratio of given inputs.
a_prompt Type: stringDefault: hyper detailed, maximum detail, 32k, Color Grading, ultra HD, extreme meticulous detailing, skin pore detailing, hyper sharpness, perfect: Additive positive prompt for the inputs.
captions Type: stringDefault: a professional, detailed, high-quality photo: Captions for the image
min_size Type: numberDefault: 1024: Minimum resolution of output images.
n_prompt Type: stringDefault: 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.
linear_cfg Type: booleanDefault: false: Linearly (with sigma) increase CFG from 'spt_linear_CFG' to s_cfg.
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: string • Format: uri

Example Execution Logs

Using seed: 42701
Captions from LLaVA: ['The image features a person wearing a blue jacket and a black hat, standing on a snow-covered surface. The person appears to be climbing or jumping on the snow, possibly enjoying a winter activity. The snowy surface is quite large, covering most of the scene, and the person is the main focus of the image. The overall style of the image is a black and white photograph, which adds a timeless and classic feel to the scene.']
Seed set to 42701

Version Details

Version ID: 7d613b6c116c06555c6c072edfa406365cd8539960f2c037022985049d4977f6
Version Created: March 11, 2024

Run on Replicate →