Fanghua-Yu /SUPIR

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

★ 5,703⑂ 480👁 64⑃ 12● 157▤ 0
PythonNOASSERTIONCreated 2023-12-21supir.xpixel.group/
+2
日增长
5,703
stars
480
forks
64
watchers
12
prs
157
issues
0
releases

README

(CVPR2024) Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild

 [Paper]   [Project Page]   [[Online App]](https://supir.suppixel.ai/home) 
 Fanghua, Yu, Jinjin Gu, Zheyuan Li, Jinfan Hu, Xiangtao Kong, Xintao Wang, Jingwen He, Yu Qiao, Chao Dong 
 Shenzhen Institute of Advanced Technology; Shanghai AI Laboratory; University of Sydney; The Hong Kong Polytechnic University; ARC Lab, Tencent PCG; The Chinese University of Hong Kong 



  


---
 🚀 We're thrilled to announce the official launch of SupPixel AI! Experience the next level of image processing and upscaling with our cutting-edge AI technology based on SUPIR. Explore now at suppixel.ai.

---
 🔧 Dependencies and Installation

1. Clone repo
    bash
    git clone https://github.com/Fanghua-Yu/SUPIR.git
    cd SUPIR
    

2. Install dependent packages
    bash
    conda create -n SUPIR python=3.8 -y
    conda activate SUPIR
    pip install --upgrade pip
    pip install -r requirements.txt
    

3. Download Checkpoints

For users who can connect to huggingface, please setting LLAVA_CLIP_PATH, SDXL_CLIP1_PATH, SDXL_CLIP2_CKPT_PTH in CKPT_PTH.py as None. These CLIPs will be downloaded automatically. 

 Dependent Models
 SDXL CLIP Encoder-1
 SDXL CLIP Encoder-2
 SDXL base 1.0_0.9vae
 LLaVA CLIP
 LLaVA v1.5 13B
 (optional) Juggernaut-XL_v9_RunDiffusionPhoto_v2
   Replacement of SDXL base 1.0_0.9vae for Photo Realistic
 (optional) Juggernaut_RunDiffusionPhoto2_Lightning_4Steps
   Distilling model used in SUPIR_v0_Juggernautv9_lightning.yaml


 Models we provided:
 SUPIR-v0Q: Baidu Netdisk, Google Drive
    
    Default training settings with paper. High generalization and high image quality in most cases.

 SUPIR-v0F: Baidu Netdisk, Google Drive

    Training with light degradation settings. Stage1 encoder of SUPIR-v0F remains more details when facing light degradations.

4. Edit Custom Path for Checkpoints
    
     [CKPT_PTH.py] -- LLAVA_CLIP_PATH, LLAVA_MODEL_PATH, SDXL_CLIP1_PATH, SDXL_CLIP2_CACHE_DIR 
     [options/SUPIR_v0.yaml] -- SDXL_CKPT, SUPIR_CKPT_Q, SUPIR_CKPT_F
    
---

 ⚡ Quick Inference
 Val Dataset
RealPhoto60: Baidu Netdisk, Google Drive

 Usage of SUPIR
Shell
Usage: 
-- python test.py [options] 
-- python gradio_demo.py [interactive options]

--img_dir                Input folder.
--save_dir               Output folder.
--upscale                Upsampling ratio of given inputs. Default: 1
--SUPIR_sign             Model selection. Default: 'Q'; Options: ['F', 'Q']
--seed                   Random seed. Default: 1234
--min_size               Minimum resolution of output images. Default: 1024
--edm_steps              Numb of steps for EDM Sampling Scheduler. Default: 50
--s_stage1               Control Strength of Stage1. Default: -1 (negative means invalid)
--s_churn                Original hy-param of EDM. Default: 5
--s_noise                Original hy-param of EDM. Default: 1.01
--s_cfg                  Classifier-free 

Top issues

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON