zust-ai/supir 🔢🖼️📝✓❓ → 🖼️

▶️ 355.6K runs 📅 Feb 2024 ⚙️ Cog 0.8.6

image-restoration image-upscaling

About

Example Output

Output

Performance Metrics

37.64s Prediction Time

283.27s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/KTLVJXCM9ezJK0VXD1hfRvsOgFQ94ZrsNc6Lw7F4hoMzhCJ4/1703062309551-1024.png",
  "s_cfg": 7.5,
  "s_churn": 5,
  "s_noise": 1.003,
  "upscale": 2,
  "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-v0F",
  "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: string • Format: uri

Example Execution Logs

Using seed: 4823
Captions from LLaVA: ['The image features three men sitting around a dining table, each wearing blue shirts. They are focused on a laptop computer placed on the table, likely discussing or working on a project together.   The table is set with various items, including a keyboard and a mouse, which are placed in front of the laptop. There are also several cups scattered around the table, possibly containing drinks for the men. A chair can be seen on the right side of the table, and a book is placed nearby. The scene appears to be a casual and collaborative work environment.']
Seed set to 4823

Version Details

Version ID: 9daf6d19556db0fd6e347a7a5cae7d4a68cf25486266ca3e6dc82618f0a2e0b9
Version Created: February 26, 2024

Run on Replicate →