SUPIR下載 - SUPIR源代碼下載

SUPIR

Python

1.0.0

下載

（CVPR2024）擴展到卓越：練習模型縮放野外照片真實的圖像修復

[PAPER] [項目頁面] [在線應用程序]
Fanghua，Yu，Jinjin Gu，Zheyuan Li，Jinfan Hu，Xiangtao Kong，Xintao Wang，Jingwen He，Yu Qiao，Chao Dong
深圳先進技術研究所；上海AI實驗室；悉尼大學；香港理工大學；弧實驗室，騰訊PCG；香港中國大學

我們很高興宣布Suppixel AI的正式發布！通過基於Supir的尖端AI技術，體驗下一個圖像處理和升級。現在在Suppixel.ai探索。

？依賴項和安裝

克隆回購

git clone https://github.com/Fanghua-Yu/SUPIR.git
cd SUPIR

安裝因軟件包

conda create -n SUPIR python=3.8 -y
conda activate SUPIR
pip install --upgrade pip
pip install -r requirements.txt

下載檢查點

對於可以連接到HuggingFace的用戶，請設置LLAVA_CLIP_PATH, SDXL_CLIP1_PATH, SDXL_CLIP2_CKPT_PTH in CKPT_PTH.py in None 。這些剪輯將自動下載。

依賴模型

SDXL剪輯Encoder-1
SDXL剪輯編碼2
SDXL基礎1.0_0.9VAE
llava剪輯
llava v1.5 13b
（可選）juggernaut-xl_v9_rundiffusionphoto_v2
- 替換SDXL base 1.0_0.9vae的照片現實
（可選）juggernaut_rundiffusionphoto2_lightning_4steps
- SUPIR_v0_Juggernautv9_lightning.yaml中使用的蒸餾模型

我們提供的模型：

SUPIR-v0Q ：Baidu NetDisk，Google Drive
默認培訓設置用紙張。在大多數情況下，高概括和高圖像質量。
SUPIR-v0F ：Baidu NetDisk，Google Drive
通過輕度降解設置進行培訓。 SUPIR-v0F的階段1編碼器在面對光降解時仍然有更多細節。

編輯檢查點的自定義路徑

 * [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

⚡快速推斷

Val數據集

REALPHOTO60：Baidu NetDisk，Google Drive

使用Supir

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: 1.003
--s_cfg                  Classifier-free guidance scale for prompts. Default: 7.5
--s_stage2               Control Strength of Stage2. Default: 1.0
--num_samples            Number of samples for each input. Default: 1
--a_prompt               Additive positive prompt for all inputs. 
    Default: ' 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. '
--n_prompt               Fixed negative prompt for all inputs. 
    Default: ' 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 '
--color_fix_type         Color Fixing Type. Default: ' Wavelet ' ; Options: [ ' None ' , ' AdaIn ' , ' Wavelet ' ]
--linear_CFG             Linearly (with sigma) increase CFG from ' spt_linear_CFG ' to s_cfg. Default: False
--linear_s_stage2        Linearly (with sigma) increase s_stage2 from ' spt_linear_s_stage2 ' to s_stage2. Default: False
--spt_linear_CFG         Start point of linearly increasing CFG. Default: 1.0
--spt_linear_s_stage2    Start point of linearly increasing s_stage2. Default: 0.0
--ae_dtype               Inference data type of AutoEncoder. Default: ' bf16 ' ; Options: [ ' fp32 ' , ' bf16 ' ]
--diff_dtype             Inference data type of Diffusion. Default: ' fp16 ' ; Options: [ ' fp32 ' , ' fp16 ' , ' bf16 ' ]

Python腳本

 # Seek for best quality for most cases
CUDA_VISIBLE_DEVICES=0,1 python test.py --img_dir ' /opt/data/private/LV_Dataset/DiffGLV-Test-All/RealPhoto60/LQ ' --save_dir ./results-Q --SUPIR_sign Q --upscale 2
# for light degradation and high fidelity
CUDA_VISIBLE_DEVICES=0,1 python test.py --img_dir ' /opt/data/private/LV_Dataset/DiffGLV-Test-All/RealPhoto60/LQ ' --save_dir ./results-F --SUPIR_sign F --upscale 2 --s_cfg 4.0 --linear_CFG

Gradio演示

CUDA_VISIBLE_DEVICES=0,1 python gradio_demo.py --ip 0.0.0.0 --port 6688 --use_image_slider --log_history

# Juggernaut_RunDiffusionPhoto2_Lightning_4Steps and DPM++ M2 SDE Karras for fast sampling
CUDA_VISIBLE_DEVICES=0,1 python gradio_demo.py --ip 0.0.0.0 --port 6688 --use_image_slider --log_history --opt options/SUPIR_v0_Juggernautv9_lightning.yaml

# less VRAM & slower (12G for Diffusion, 16G for LLaVA)
CUDA_VISIBLE_DEVICES=0,1 python gradio_demo.py --ip 0.0.0.0 --port 6688 --use_image_slider --log_history --loading_half_params --use_tile_vae --load_8bit_llava

在線應用

我們剛剛啟動了Suppixel AI，這是一種易於使用的工具，旨在幫助進行高質量的圖像處理和放大。它建立在Supir。無論您是喜歡攝影，數字藝術，還是喜歡使用圖像增強效果，我們都希望您檢查一下。

Bibtex

 @misc{yu2024scaling,
  title={Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild}, 
  author={Fanghua Yu and Jinjin Gu and Zheyuan Li and Jinfan Hu and Xiangtao Kong and Xintao Wang and Jingwen He and Yu Qiao and Chao Dong},
  year={2024},
  eprint={2401.13627},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}