add github release workflow, v0.3.0

.github/workflows/release.yml

@@ -0,0 +1,41 @@
+name: release
+on:
+  push:
+    tags:
+      - '*'
+
+jobs:
+  build:
+    permissions: write-all
+    name: Create Release
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+      - name: Create Release
+        id: create_release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: ${{ github.ref }}
+          release_name: Real-ESRGAN ${{ github.ref }} Release Note
+          body: |
+            🚀 See you again 😸
+            🚀Have a nice day 😸 and happy everyday 😃
+            🚀 Long time no see ☄️
+
+            ✨ **Highlights**
+            ✅ [Features] Support ...
+
+            🐛 **Bug Fixes**
+
+            🌴 **Improvements**
+
+            📢📢📢
+
+            <p align="center">
+               <img src="https://raw.githubusercontent.com/xinntao/Real-ESRGAN/master/assets/realesrgan_logo.png" height=150>
+            </p>
+          draft: true
+          prerelease: false

.gitignore

@@ -5,7 +5,7 @@ results/*
 tb_logger/*
 wandb/*
 tmp/*
-realesrgan/weights/*
+weights/*
 
 version.py
 

MANIFEST.in

@@ -5,4 +5,4 @@ include inference_realesrgan.py
 include VERSION
 include LICENSE
 include requirements.txt
-include realesrgan/weights/README.md
+include weights/README.md

README.md

@@ -22,10 +22,10 @@
 🔥 **RealESRGAN_x4plus_anime_6B** for anime images **(动漫插图模型)**. Please see [[*anime_model*](docs/anime_model.md)]
 
 <!-- 1. You can try in our website: [ARC Demo](https://arc.tencent.com/en/ai-demos/imgRestore) (now only support RealESRGAN_x4plus_anime_6B) -->
-1. :boom: **Add** online demo: [![Replicate](https://img.shields.io/static/v1?label=Demo&message=Replicate&color=blue)](https://replicate.com/xinntao/realesrgan).
+1. :boom: **Update** online Replicate demo: [![Replicate](https://img.shields.io/static/v1?label=Demo&message=Replicate&color=blue)](https://replicate.com/xinntao/realesrgan)
-1. [Colab Demo](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) for Real-ESRGAN **|** [Colab Demo](https://colab.research.google.com/drive/1yNl9ORUxxlL4N0keJa2SEPB61imPQd1B?usp=sharing) for Real-ESRGAN (**anime videos**)
+1. Online Colab demo for Real-ESRGAN: [![Colab](https://img.shields.io/static/v1?label=Demo&message=Colab&color=orange)](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) **|** Online Colab demo for for Real-ESRGAN (**anime videos**): [![Colab](https://img.shields.io/static/v1?label=Demo&message=Colab&color=orange)](https://colab.research.google.com/drive/1yNl9ORUxxlL4N0keJa2SEPB61imPQd1B?usp=sharing)
 1. Portable [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip) **executable files for Intel/AMD/Nvidia GPU**. You can find more information [here](#portable-executable-files-ncnn). The ncnn implementation is in [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan)
-1. You can watch enhanced animations in [Tencent Video](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html). 欢迎观看[腾讯视频动漫修复](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html)
+<!-- 1. You can watch enhanced animations in [Tencent Video](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html). 欢迎观看[腾讯视频动漫修复](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html) -->
 
 Real-ESRGAN aims at developing **Practical Algorithms for General Image/Video Restoration**.<br>
 We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.
@@ -59,6 +59,7 @@ Other recommended projects:<br>
 <!---------------------------------- Updates --------------------------->
 ## 🚩 Updates
 
+- ✅ Add the **realesr-general-x4v3** model - a tiny small model for general scenes. It also supports the **--dn** option to balance the noise (avoiding over-smooth results). **--dn** is short for denoising strength.
 - ✅ Update the **RealESRGAN AnimeVideo-v3** model. Please see [anime video models](docs/anime_video_model.md) and [comparisons](docs/anime_comparisons.md) for more details.
 - ✅ Add small models for anime videos. More details are in [anime video models](docs/anime_video_model.md).
 - ✅ Add the ncnn implementation [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan).
@@ -198,7 +199,7 @@ A common command: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile
 Download pre-trained models: [RealESRGAN_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)
 
 ```bash
-wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P weights
 ```
 
 Inference!
@@ -220,7 +221,7 @@ Pre-trained models: [RealESRGAN_x4plus_anime_6B](https://github.com/xinntao/Real
 
 ```bash
 # download model
-wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P experiments/pretrained_models
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P weights
 # inference
 python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i inputs
 ```
@@ -259,6 +260,7 @@ If you develop/use Real-ESRGAN in your projects, welcome to let me know.
 - [Real-ESRGAN_GUI](https://github.com/net2cn/Real-ESRGAN_GUI) by [net2cn](https://github.com/net2cn)
 - [Real-ESRGAN-EGUI](https://github.com/WGzeyu/Real-ESRGAN-EGUI) by [WGzeyu](https://github.com/WGzeyu)
 - [anime_upscaler](https://github.com/shangar21/anime_upscaler) by [shangar21](https://github.com/shangar21)
+- [Upscayl](https://github.com/upscayl/upscayl) by [Nayam Amarshe](https://github.com/NayamAmarshe) and [TGS963](https://github.com/TGS963)
 
 ## 🤗 Acknowledgement
 

README_CN.md

@@ -195,7 +195,7 @@ Usage: realesrgan-ncnn-vulkan.exe -i infile -o outfile [options]...
 下载我们训练好的模型: [RealESRGAN_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)
 
 ```bash
-wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P weights
 ```
 
 推断!
@@ -217,7 +217,7 @@ python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs --face_enhance
 
 ```bash
 # 下载模型
-wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P experiments/pretrained_models
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P weights
 # 推断
 python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i inputs
 ```

VERSION

@@ -1 +1 @@
-0.2.7
+0.3.0

cog_predict.py

@@ -29,52 +29,50 @@ class Predictor(BasePredictor):
     def setup(self):
         os.makedirs('output', exist_ok=True)
         # download weights
-        if not os.path.exists('realesrgan/weights/realesr-general-x4v3.pth'):
+        if not os.path.exists('weights/realesr-general-x4v3.pth'):
             os.system(
-                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P ./realesrgan/weights'
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P ./weights'
             )
-        if not os.path.exists('realesrgan/weights/GFPGANv1.4.pth'):
+        if not os.path.exists('weights/GFPGANv1.4.pth'):
+            os.system('wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -P ./weights')
+        if not os.path.exists('weights/RealESRGAN_x4plus.pth'):
             os.system(
-                'wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -P ./realesrgan/weights'
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P ./weights'
             )
-        if not os.path.exists('realesrgan/weights/RealESRGAN_x4plus.pth'):
+        if not os.path.exists('weights/RealESRGAN_x4plus_anime_6B.pth'):
             os.system(
-                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P ./realesrgan/weights'
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P ./weights'
             )
-        if not os.path.exists('realesrgan/weights/RealESRGAN_x4plus_anime_6B.pth'):
+        if not os.path.exists('weights/realesr-animevideov3.pth'):
             os.system(
-                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P ./realesrgan/weights'
+                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth -P ./weights'
-            )
-        if not os.path.exists('realesrgan/weights/realesr-animevideov3.pth'):
-            os.system(
-                'wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth -P ./realesrgan/weights'
             )
 
     def choose_model(self, scale, version, tile=0):
         half = True if torch.cuda.is_available() else False
         if version == 'General - RealESRGANplus':
             model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
-            model_path = 'realesrgan/weights/RealESRGAN_x4plus.pth'
+            model_path = 'weights/RealESRGAN_x4plus.pth'
             self.upsampler = RealESRGANer(
                 scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
         elif version == 'General - v3':
             model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
-            model_path = 'realesrgan/weights/realesr-general-x4v3.pth'
+            model_path = 'weights/realesr-general-x4v3.pth'
             self.upsampler = RealESRGANer(
                 scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
         elif version == 'Anime - anime6B':
             model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
-            model_path = 'realesrgan/weights/RealESRGAN_x4plus_anime_6B.pth'
+            model_path = 'weights/RealESRGAN_x4plus_anime_6B.pth'
             self.upsampler = RealESRGANer(
                 scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
         elif version == 'AnimeVideo - v3':
             model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu')
-            model_path = 'realesrgan/weights/realesr-animevideov3.pth'
+            model_path = 'weights/realesr-animevideov3.pth'
             self.upsampler = RealESRGANer(
                 scale=4, model_path=model_path, model=model, tile=tile, tile_pad=10, pre_pad=0, half=half)
 
         self.face_enhancer = GFPGANer(
-            model_path='realesrgan/weights/GFPGANv1.4.pth',
+            model_path='weights/GFPGANv1.4.pth',
             upscale=scale,
             arch='clean',
             channel_multiplier=2,

docs/anime_model.md

@@ -24,7 +24,7 @@ Pre-trained models: [RealESRGAN_x4plus_anime_6B](https://github.com/xinntao/Real
 
 ```bash
 # download model
-wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P experiments/pretrained_models
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P weights
 # inference
 python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i inputs
 ```

docs/anime_video_model.md

@@ -34,7 +34,7 @@ The following are some demos (best view in the full screen mode).
 
 ```bash
 # download model
-wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth -P realesrgan/weights
+wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth -P weights
 # single gpu and single process inference
 CUDA_VISIBLE_DEVICES=0 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2
 # single gpu and multi process inference (you can use multi-processing to improve GPU utilization)

docs/model_zoo.md

@@ -14,6 +14,7 @@
 | [RealESRGAN_x2plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth)                      | X2    | X2 model for general images                  |
 | [RealESRNet_x4plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth)                      | X4    | X4 model with MSE loss (over-smooth effects) |
 | [official ESRGAN_x4](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth) | X4    | official ESRGAN model                        |
+| [realesr-general-x4v3](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth) | X4 (can also be used for X1, X2, X3) | A tiny small model (consume much fewer GPU memory and time); not too strong deblur and denoise capacity |
 
 The following models are **discriminators**, which are usually used for fine-tuning.
 

inference_realesrgan.py

@@ -88,13 +88,13 @@ def main():
     if args.model_path is not None:
         model_path = args.model_path
     else:
-        model_path = os.path.join('realesrgan/weights', args.model_name + '.pth')
+        model_path = os.path.join('weights', args.model_name + '.pth')
         if not os.path.isfile(model_path):
-            ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+            ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
             for url in file_url:
                 # model_path will be updated
                 model_path = load_file_from_url(
-                    url=url, model_dir=os.path.join(ROOT_DIR, 'realesrgan/weights'), progress=True, file_name=None)
+                    url=url, model_dir=os.path.join(ROOT_DIR, 'weights'), progress=True, file_name=None)
 
     # use dni to control the denoise strength
     dni_weight = None

inference_realesrgan_video.py

@@ -8,6 +8,7 @@ import shutil
 import subprocess
 import torch
 from basicsr.archs.rrdbnet_arch import RRDBNet
+from basicsr.utils.download_util import load_file_from_url
 from os import path as osp
 from tqdm import tqdm
 
@@ -172,32 +173,55 @@ class Writer:
 def inference_video(args, video_save_path, device=None, total_workers=1, worker_idx=0):
     # ---------------------- determine models according to model names ---------------------- #
     args.model_name = args.model_name.split('.pth')[0]
-    if args.model_name in ['RealESRGAN_x4plus', 'RealESRNet_x4plus']:  # x4 RRDBNet model
+    if args.model_name == 'RealESRGAN_x4plus':  # x4 RRDBNet model
         model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
         netscale = 4
-    elif args.model_name in ['RealESRGAN_x4plus_anime_6B']:  # x4 RRDBNet model with 6 blocks
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth']
+    elif args.model_name == 'RealESRNet_x4plus':  # x4 RRDBNet model
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+        netscale = 4
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth']
+    elif args.model_name == 'RealESRGAN_x4plus_anime_6B':  # x4 RRDBNet model with 6 blocks
         model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
         netscale = 4
-    elif args.model_name in ['RealESRGAN_x2plus']:  # x2 RRDBNet model
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth']
+    elif args.model_name == 'RealESRGAN_x2plus':  # x2 RRDBNet model
         model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=2)
         netscale = 2
-    elif args.model_name in ['realesr-animevideov3']:  # x4 VGG-style model (XS size)
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth']
+    elif args.model_name == 'realesr-animevideov3':  # x4 VGG-style model (XS size)
         model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu')
         netscale = 4
-    else:
+        file_url = ['https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth']
-        raise NotImplementedError
+    elif args.model_name == 'realesr-general-x4v3':  # x4 VGG-style model (S size)
+        model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
+        netscale = 4
+        file_url = [
+            'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth',
+            'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth'
+        ]
 
     # ---------------------- determine model paths ---------------------- #
-    model_path = os.path.join('experiments/pretrained_models', args.model_name + '.pth')
+    model_path = os.path.join('weights', args.model_name + '.pth')
     if not os.path.isfile(model_path):
-        model_path = os.path.join('realesrgan/weights', args.model_name + '.pth')
+        ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
-    if not os.path.isfile(model_path):
+        for url in file_url:
-        raise ValueError(f'Model {args.model_name} does not exist.')
+            # model_path will be updated
+            model_path = load_file_from_url(
+                url=url, model_dir=os.path.join(ROOT_DIR, 'weights'), progress=True, file_name=None)
+
+    # use dni to control the denoise strength
+    dni_weight = None
+    if args.model_name == 'realesr-general-x4v3' and args.denoise_strength != 1:
+        wdn_model_path = model_path.replace('realesr-general-x4v3', 'realesr-general-wdn-x4v3')
+        model_path = [model_path, wdn_model_path]
+        dni_weight = [args.denoise_strength, 1 - args.denoise_strength]
 
     # restorer
     upsampler = RealESRGANer(
         scale=netscale,
         model_path=model_path,
+        dni_weight=dni_weight,
         model=model,
         tile=args.tile,
         tile_pad=args.tile_pad,
@@ -312,9 +336,16 @@ def main():
         type=str,
         default='realesr-animevideov3',
         help=('Model names: realesr-animevideov3 | RealESRGAN_x4plus_anime_6B | RealESRGAN_x4plus | RealESRNet_x4plus |'
-              ' RealESRGAN_x2plus | '
+              ' RealESRGAN_x2plus | realesr-general-x4v3'
               'Default:realesr-animevideov3'))
     parser.add_argument('-o', '--output', type=str, default='results', help='Output folder')
+    parser.add_argument(
+        '-dn',
+        '--denoise_strength',
+        type=float,
+        default=0.5,
+        help=('Denoise strength. 0 for weak denoise (keep noise), 1 for strong denoise ability. '
+              'Only used for the realesr-general-x4v3 model'))
     parser.add_argument('-s', '--outscale', type=float, default=4, help='The final upsampling scale of the image')
     parser.add_argument('--suffix', type=str, default='out', help='Suffix of the restored video')
     parser.add_argument('-t', '--tile', type=int, default=0, help='Tile size, 0 for no tile during testing')

realesrgan/utils.py

@@ -56,13 +56,10 @@ class RealESRGANer():
             assert len(model_path) == len(dni_weight), 'model_path and dni_weight should have the save length.'
             loadnet = self.dni(model_path[0], model_path[1], dni_weight)
         else:
-            # if the model_path starts with https, it will first download models to the folder: realesrgan/weights
+            # if the model_path starts with https, it will first download models to the folder: weights
             if model_path.startswith('https://'):
                 model_path = load_file_from_url(
-                    url=model_path,
+                    url=model_path, model_dir=os.path.join(ROOT_DIR, 'weights'), progress=True, file_name=None)
-                    model_dir=os.path.join(ROOT_DIR, 'realesrgan/weights'),
-                    progress=True,
-                    file_name=None)
             loadnet = torch.load(model_path, map_location=torch.device('cpu'))
 
         # prefer to use params_ema