diff --git a/README.md b/README.md
index 2aa1e63..9678432 100644
--- a/README.md
+++ b/README.md
@@ -5,8 +5,15 @@ Note that this version is not compatible with previous versions. If you want to
 
 # :rocket: [BasicSR](https://github.com/xinntao/BasicSR)
 
-[GitHub](https://github.com/xinntao/BasicSR) | [Gitee码云](https://gitee.com/xinntao/BasicSR) <br>
-[English](README.md) | [简体中文](README_CN.md)
+[English](README.md) **|** [简体中文](README_CN.md) &emsp; [GitHub](https://github.com/xinntao/BasicSR) **|** [Gitee码云](https://gitee.com/xinntao/BasicSR)
+
+:arrow_double_down: Google Drive: [Pretrained Models](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) **|** [Reproduced Experiments](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing)
+:arrow_double_down: 百度网盘: [预训练模型](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g) **|** [复现实验](https://pan.baidu.com/s/1UElD6q8sVAgn_cxeBDOlvQ) <br>
+:chart_with_upwards_trend: [Training curves in wandb](https://app.wandb.ai/xintao/basicsr) <br>
+:computer: [Commands for training and testing](docs/TrainTest.md) <br>
+:zap: [HOWTOs](#zap-howtos)
+
+---
 
 BasicSR is an **open source** image and video super-resolution toolbox based on PyTorch (will extend to more restoration tasks in the future).<br>
 <sub>([ESRGAN](https://github.com/xinntao/ESRGAN), [EDVR](https://github.com/xinntao/EDVR), [DNI](https://github.com/xinntao/DNI), [SFTGAN](https://github.com/xinntao/SFTGAN))</sub>
@@ -34,11 +41,11 @@ BasicSR is an **open source** image and video super-resolution toolbox based on
 We provides simple pipelines to train/test/inference models for quick start.
 These pipelines/commands cannot cover all the cases and more details are in the following sections.
 
-- :zap: [How to train StyleGAN2](docs/HOWTOs.md#How-to-train-StyleGAN2)
-- :zap: [How to test StyleGAN2](docs/HOWTOs.md#How-to-test-StyleGAN2)
-- :zap: [How to test DFDNet](docs/HOWTOs.md#How-to-test-DFDNet)
+- [How to train StyleGAN2](docs/HOWTOs.md#How-to-train-StyleGAN2)
+- [How to test StyleGAN2](docs/HOWTOs.md#How-to-test-StyleGAN2)
+- [How to test DFDNet](docs/HOWTOs.md#How-to-test-DFDNet)
 
-## Dependencies and Installation
+## :wrench: Dependencies and Installation
 
 - Python >= 3.7 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))
 - [PyTorch >= 1.3](https://pytorch.org/)
@@ -54,25 +61,22 @@ python setup.py develop
 
 Note that BasicSR is only tested in Ubuntu, and may be not suitable for Windows. You may try [Windows WSL with CUDA supports](https://docs.microsoft.com/en-us/windows/win32/direct3d12/gpu-cuda-in-wsl) :-) (It is now only available for insider build with Fast ring).
 
-## TODO List
+## :hourglass_flowing_sand: TODO List
 
 Please see [project boards](https://github.com/xinntao/BasicSR/projects).
 
-## Dataset Preparation
+## :turtle: Dataset Preparation
 
 - Please refer to **[DatasetPreparation.md](docs/DatasetPreparation.md)** for more details.
 - The descriptions of currently supported datasets (`torch.utils.data.Dataset` classes) are in [Datasets.md](docs/Datasets.md).
 
-## Train and Test
+## :computer: Train and Test
 
 - **Training and testing commands**: Please see **[TrainTest.md](docs/TrainTest.md)** for the basic usage.
 - **Options/Configs**: Please refer to [Config.md](docs/Config.md).
 - **Logging**: Please refer to [Logging.md](docs/Logging.md).
 
-## Model Zoo and Baselines
-
-**[Download official pre-trained models](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing)**<br>
-**[Download reproduced models and logs](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing)**
+## :card_file_box: Model Zoo and Baselines
 
 - The descriptions of currently supported models are in [Models.md](docs/Models.md).
 - **Pre-trained models and log examples** are available in **[ModelZoo.md](docs/ModelZoo.md)**.
@@ -83,7 +87,7 @@ Please see [project boards](https://github.com/xinntao/BasicSR/projects).
    <img src="./assets/wandb.jpg" height="280">
 </a></p>
 
-## Codebase Designs and Conventions
+## :memo: Codebase Designs and Conventions
 
 Please see [DesignConvention.md](docs/DesignConvention.md) for the designs and conventions of the BasicSR codebase.<br>
 The figure below shows the overall framework. More descriptions for each component: <br>
@@ -91,11 +95,11 @@ The figure below shows the overall framework. More descriptions for each compone
 
 ![overall_structure](./assets/overall_structure.png)
 
-## License and Acknowledgement
+## :scroll: License and Acknowledgement
 
 This project is released under the Apache 2.0 license.
 More details about license and acknowledgement are in [LICENSE](LICENSE/README.md).
 
-## Contact
+## :e-mail: Contact
 
 If you have any question, please email `xintao.wang@outlook.com`.
diff --git a/README_CN.md b/README_CN.md
index 9dcd378..c963f68 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -6,8 +6,15 @@
 
 # :rocket: [BasicSR](https://github.com/xinntao/BasicSR)
 
-[GitHub](https://github.com/xinntao/BasicSR) | [Gitee码云](https://gitee.com/xinntao/BasicSR) <br>
-[English](README.md) | [简体中文](README_CN.md)
+[English](README.md) **|** [简体中文](README_CN.md) &emsp; [GitHub](https://github.com/xinntao/BasicSR) **|** [Gitee码云](https://gitee.com/xinntao/BasicSR)
+
+:arrow_double_down: 百度网盘: [预训练模型](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g) **|** [复现实验](https://pan.baidu.com/s/1UElD6q8sVAgn_cxeBDOlvQ)
+:arrow_double_down: Google Drive: [Pretrained Models](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) **|** [Reproduced Experiments](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing) <br>
+:chart_with_upwards_trend: [wandb的训练曲线](https://app.wandb.ai/xintao/basicsr) <br>
+:computer: [训练和测试的命令](docs/TrainTest_CN.md) <br>
+:zap: [HOWTOs](#zap-howtos)
+
+---
 
 BasicSR 是一个基于 PyTorch 的**开源**图像视频超分辨率 (Super-Resolution) 工具箱 (之后会支持更多的 Restoration 任务).<br>
 <sub>([ESRGAN](https://github.com/xinntao/ESRGAN), [EDVR](https://github.com/xinntao/EDVR), [DNI](https://github.com/xinntao/DNI), [SFTGAN](https://github.com/xinntao/SFTGAN))</sub>
@@ -30,15 +37,15 @@ BasicSR 是一个基于 PyTorch 的**开源**图像视频超分辨率 (Super-Res
 </ul>
 </details>
 
-## :zap:HOWTOs
+## :zap: HOWTOs
 
 我们提供了简单的流程来快速上手 训练/测试/推理 模型. 这些命令并不能涵盖所有用法, 更多的细节参见下面的部分.
 
-- :zap: [如何训练 StyleGAN2](docs/HOWTOs_CN.md#如何训练-StyleGAN2)
-- :zap: [如何测试 StyleGAN2](docs/HOWTOs_CN.md#如何测试-StyleGAN2)
-- :zap: [如何测试 DFDNet](docs/HOWTOs_CN.md#如何测试-DFDNet)
+- [如何训练 StyleGAN2](docs/HOWTOs_CN.md#如何训练-StyleGAN2)
+- [如何测试 StyleGAN2](docs/HOWTOs_CN.md#如何测试-StyleGAN2)
+- [如何测试 DFDNet](docs/HOWTOs_CN.md#如何测试-DFDNet)
 
-## 依赖和安装
+## :wrench: 依赖和安装
 
 - Python >= 3.7 (推荐使用 [Anaconda](https://www.anaconda.com/download/#linux) 或 [Miniconda](https://docs.conda.io/en/latest/miniconda.html))
 - [PyTorch >= 1.3](https://pytorch.org/)
@@ -54,25 +61,22 @@ python setup.py develop
 
 注意: BasicSR 仅在 Ubuntu 下进行测试，或许不支持Windows. 可以在Windows下尝试[支持CUDA的Windows WSL](https://docs.microsoft.com/en-us/windows/win32/direct3d12/gpu-cuda-in-wsl) :-) (目前只有Fast ring的预览版系统可以安装).
 
-## TODO 清单
+## :hourglass_flowing_sand: TODO 清单
 
 参见 [project boards](https://github.com/xinntao/BasicSR/projects).
 
-## 数据准备
+## :turtle: 数据准备
 
 - 数据准备步骤, 参见 **[DatasetPreparation_CN.md](docs/DatasetPreparation_CN.md)**.
 - 目前支持的数据集 (`torch.utils.data.Dataset`类), 参见 [Datasets_CN.md](docs/Datasets_CN.md).
 
-## 训练和测试
+## :computer: 训练和测试
 
 - **训练和测试的命令**, 参见 **[TrainTest_CN.md](docs/TrainTest_CN.md)**.
 - **Options/Configs**配置文件的说明, 参见 [Config_CN.md](docs/Config_CN.md).
 - **Logging**日志系统的说明, 参见 [Logging_CN.md](docs/Logging_CN.md).
 
-## 模型库和基准
-
-**[下载官方提供的预训练模型](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing)** <br>
-**[下载复现的模型和log](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing)**
+## :card_file_box: 模型库和基准
 
 - 目前支持的模型描述, 参见 [Models_CN.md](docs/Models_CN.md).
 - **预训练模型和log样例**, 参见 **[ModelZoo_CN.md](docs/ModelZoo_CN.md)**.
@@ -83,7 +87,7 @@ python setup.py develop
    <img src="./assets/wandb.jpg" height="280">
 </a></p>
 
-## 代码库的设计和约定
+## :memo: 代码库的设计和约定
 
 参见 [DesignConvention_CN.md](docs/DesignConvention_CN.md).<br>
 下图概括了整体的框架. 每个模块更多的描述参见: <br>
@@ -91,11 +95,11 @@ python setup.py develop
 
 ![overall_structure](./assets/overall_structure.png)
 
-## 许可
+## :scroll: 许可
 
 本项目使用 Apache 2.0 license.
 更多细节参见 [LICENSE](LICENSE/README.md).
 
-#### 联系
+## :e-mail: 联系
 
 若有任何问题, 请电邮 `xintao.wang@outlook.com`.
diff --git a/VERSION b/VERSION
index 9084fa2..524cb55 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.1.0
+1.1.1
diff --git a/basicsr/data/util.py b/basicsr/data/util.py
index 798d368..50245ac 100644
--- a/basicsr/data/util.py
+++ b/basicsr/data/util.py
@@ -246,6 +246,21 @@ def paired_paths_from_folder(folders, keys, filename_tmpl):
     return paths
 
 
+def paths_from_folder(folder):
+    """Generate paths from folder.
+
+    Args:
+        folder (str): Folder path.
+
+    Returns:
+        list[str]: Returned path list.
+    """
+
+    paths = list(mmcv.scandir(folder))
+    paths = [osp.join(folder, path) for path in paths]
+    return paths
+
+
 def generate_gaussian_kernel(kernel_size=13, sigma=1.6):
     """Generate Gaussian kernel used in `duf_downsample`.
 
diff --git a/basicsr/models/archs/__init__.py b/basicsr/models/archs/__init__.py
index 8f17af5..a00982a 100644
--- a/basicsr/models/archs/__init__.py
+++ b/basicsr/models/archs/__init__.py
@@ -15,3 +15,31 @@
     importlib.import_module(f'basicsr.models.archs.{file_name}')
     for file_name in arch_filenames
 ]
+
+
+def dynamic_instantiation(modules, cls_type, opt):
+    """Dynamically instantiate class.
+
+    Args:
+        modules (list[importlib modules]): List of modules from importlib
+            files.
+        cls_type (str): Class type.
+        opt (dict): Class initialization kwargs.
+
+    Returns:
+        class: Instantiated class.
+    """
+
+    for module in modules:
+        cls_ = getattr(module, cls_type, None)
+        if cls_ is not None:
+            break
+    if cls_ is None:
+        raise ValueError(f'{cls_type} is not found.')
+    return cls_(**opt)
+
+
+def define_network(opt):
+    network_type = opt.pop('type')
+    net = dynamic_instantiation(_arch_modules, network_type, opt)
+    return net
diff --git a/basicsr/models/networks.py b/basicsr/models/networks.py
deleted file mode 100644
index ecc97f1..0000000
--- a/basicsr/models/networks.py
+++ /dev/null
@@ -1,39 +0,0 @@
-from basicsr.models.archs import _arch_modules
-
-
-def dynamic_instantiation(modules, cls_type, opt):
-    """Dynamically instantiate class.
-
-    Args:
-        modules (list[importlib modules]): List of modules from importlib
-            files.
-        cls_type (str): Class type.
-        opt (dict): Class initialization kwargs.
-
-    Returns:
-        class： Instantiated class.
-    """
-
-    for module in modules:
-        cls_ = getattr(module, cls_type, None)
-        if cls_ is not None:
-            break
-    if cls_ is None:
-        raise ValueError(f'{cls_type} is not found.')
-    return cls_(**opt)
-
-
-# Generator
-def define_net_g(opt):
-    network_type = opt.pop('type')
-    net_g = dynamic_instantiation(_arch_modules, network_type, opt)
-
-    return net_g
-
-
-# Discriminator
-def define_net_d(opt):
-    network_type = opt.pop('type')
-
-    net_d = dynamic_instantiation(_arch_modules, network_type, opt)
-    return net_d
diff --git a/basicsr/models/sr_model.py b/basicsr/models/sr_model.py
index 56b6193..66a98b6 100644
--- a/basicsr/models/sr_model.py
+++ b/basicsr/models/sr_model.py
@@ -5,7 +5,7 @@
 from copy import deepcopy
 from os import path as osp
 
-from basicsr.models import networks as networks
+from basicsr.models.archs import define_network
 from basicsr.models.base_model import BaseModel
 from basicsr.utils import ProgressBar, get_root_logger, tensor2img
 
@@ -20,7 +20,7 @@ def __init__(self, opt):
         super(SRModel, self).__init__(opt)
 
         # define network
-        self.net_g = networks.define_net_g(deepcopy(opt['network_g']))
+        self.net_g = define_network(deepcopy(opt['network_g']))
         self.net_g = self.model_to_device(self.net_g)
         self.print_network(self.net_g)
 
diff --git a/basicsr/models/srgan_model.py b/basicsr/models/srgan_model.py
index a9e7c27..d927773 100644
--- a/basicsr/models/srgan_model.py
+++ b/basicsr/models/srgan_model.py
@@ -3,7 +3,7 @@
 from collections import OrderedDict
 from copy import deepcopy
 
-from basicsr.models import networks as networks
+from basicsr.models.archs import define_network
 from basicsr.models.sr_model import SRModel
 
 loss_module = importlib.import_module('basicsr.models.losses')
@@ -16,7 +16,7 @@ def init_training_settings(self):
         train_opt = self.opt['train']
 
         # define network net_d
-        self.net_d = networks.define_net_d(deepcopy(self.opt['network_d']))
+        self.net_d = define_network(deepcopy(self.opt['network_d']))
         self.net_d = self.model_to_device(self.net_d)
         self.print_network(self.net_d)
 
diff --git a/basicsr/models/stylegan2_model.py b/basicsr/models/stylegan2_model.py
index d3ab279..7cf7aec 100644
--- a/basicsr/models/stylegan2_model.py
+++ b/basicsr/models/stylegan2_model.py
@@ -1,13 +1,14 @@
 import importlib
 import math
 import mmcv
+import numpy as np
 import random
 import torch
 from collections import OrderedDict
 from copy import deepcopy
 from os import path as osp
 
-from basicsr.models import networks as networks
+from basicsr.models.archs import define_network
 from basicsr.models.base_model import BaseModel
 from basicsr.models.losses.losses import g_path_regularize, r1_penalty
 from basicsr.utils import tensor2img
@@ -22,7 +23,7 @@ def __init__(self, opt):
         super(StyleGAN2Model, self).__init__(opt)
 
         # define network net_g
-        self.net_g = networks.define_net_g(deepcopy(opt['network_g']))
+        self.net_g = define_network(deepcopy(opt['network_g']))
         self.net_g = self.model_to_device(self.net_g)
         self.print_network(self.net_g)
         # load pretrained model
@@ -34,8 +35,9 @@ def __init__(self, opt):
 
         # latent dimension: self.num_style_feat
         self.num_style_feat = opt['network_g']['num_style_feat']
+        num_val_samples = self.opt['val'].get('num_val_samples', 16)
         self.fixed_sample = torch.randn(
-            16, self.num_style_feat, device=self.device)
+            num_val_samples, self.num_style_feat, device=self.device)
 
         if self.is_train:
             self.init_training_settings()
@@ -44,7 +46,7 @@ def init_training_settings(self):
         train_opt = self.opt['train']
 
         # define network net_d
-        self.net_d = networks.define_net_d(deepcopy(self.opt['network_d']))
+        self.net_d = define_network(deepcopy(self.opt['network_d']))
         self.net_d = self.model_to_device(self.net_d)
         self.print_network(self.net_d)
 
@@ -57,8 +59,8 @@ def init_training_settings(self):
         # define network net_g with Exponential Moving Average (EMA)
         # net_g_ema only used for testing on one GPU and saving, do not need to
         # wrap with DistributedDataParallel
-        self.net_g_ema = networks.define_net_g(
-            deepcopy(self.opt['network_g'])).to(self.device)
+        self.net_g_ema = define_network(deepcopy(self.opt['network_g'])).to(
+            self.device)
         # load pretrained model
         load_path = self.opt['path'].get('pretrain_model_g', None)
         if load_path is not None:
@@ -311,7 +313,8 @@ def nondist_validation(self, dataloader, current_iter, tb_logger,
                                      f'test_{self.opt["name"]}.png')
         mmcv.imwrite(result, save_img_path)
         # add sample images to tb_logger
-        result = mmcv.bgr2rgb(result / 255.)
+        result = (result / 255.).astype(np.float32)
+        result = mmcv.bgr2rgb(result)
         if tb_logger is not None:
             tb_logger.add_image(
                 'samples', result, global_step=current_iter, dataformats='HWC')
diff --git a/basicsr/models/video_gan_model.py b/basicsr/models/video_gan_model.py
index 836954b..94ccf4b 100644
--- a/basicsr/models/video_gan_model.py
+++ b/basicsr/models/video_gan_model.py
@@ -3,7 +3,7 @@
 from collections import OrderedDict
 from copy import deepcopy
 
-from basicsr.models import networks as networks
+from basicsr.models.archs import define_network
 from basicsr.models.video_base_model import VideoBaseModel
 
 loss_module = importlib.import_module('basicsr.models.losses')
@@ -16,7 +16,7 @@ def init_training_settings(self):
         train_opt = self.opt['train']
 
         # define network net_d
-        self.net_d = networks.define_net_d(deepcopy(self.opt['network_d']))
+        self.net_d = define_network(deepcopy(self.opt['network_d']))
         self.net_d = self.model_to_device(self.net_d)
         self.print_network(self.net_d)
 
diff --git a/basicsr/train.py b/basicsr/train.py
index 07c0736..0d769c8 100644
--- a/basicsr/train.py
+++ b/basicsr/train.py
@@ -205,8 +205,8 @@ def main():
                 model.save(epoch, current_iter)
 
             # validation
-            if opt['val']['val_freq'] is not None and current_iter % opt[
-                    'val']['val_freq'] == 0:
+            if opt.get('val') is not None and (current_iter %
+                                               opt['val']['val_freq'] == 0):
                 model.validation(val_loader, current_iter, tb_logger,
                                  opt['val']['save_img'])
 
@@ -222,7 +222,7 @@ def main():
     logger.info(f'End of training. Time consumed: {consumed_time}')
     logger.info('Save the latest model.')
     model.save(epoch=-1, current_iter=-1)  # -1 stands for the latest
-    if opt['val']['val_freq'] is not None:
+    if opt.get('val') is not None:
         model.validation(val_loader, current_iter, tb_logger,
                          opt['val']['save_img'])
     if tb_logger:
diff --git a/basicsr/utils/options.py b/basicsr/utils/options.py
index cddf25e..f7717f0 100644
--- a/basicsr/utils/options.py
+++ b/basicsr/utils/options.py
@@ -75,7 +75,8 @@ def parse(opt_path, is_train=True):
 
         # change some options for debug mode
         if 'debug' in opt['name']:
-            opt['val']['val_freq'] = 8
+            if 'val' in opt:
+                opt['val']['val_freq'] = 8
             opt['logger']['print_freq'] = 1
             opt['logger']['save_checkpoint_freq'] = 8
     else:  # test
diff --git a/docs/Config.md b/docs/Config.md
index 3c0163b..f2a0775 100644
--- a/docs/Config.md
+++ b/docs/Config.md
@@ -1,6 +1,6 @@
 # Configuration
 
-[English](Config.md) | [简体中文](Config_CN.md)
+[English](Config.md) **|** [简体中文](Config_CN.md)
 
 #### Contents
 
diff --git a/docs/Config_CN.md b/docs/Config_CN.md
index db77fc6..6fa159d 100644
--- a/docs/Config_CN.md
+++ b/docs/Config_CN.md
@@ -1,6 +1,6 @@
 # 配置文件
 
-[English](Config.md) | [简体中文](Config_CN.md)
+[English](Config.md) **|** [简体中文](Config_CN.md)
 
 #### 目录
 
diff --git a/docs/DatasetPreparation.md b/docs/DatasetPreparation.md
index a18159d..b579f58 100644
--- a/docs/DatasetPreparation.md
+++ b/docs/DatasetPreparation.md
@@ -1,6 +1,6 @@
 # Dataset Preparation
 
-[English](DatasetPreparation.md) | [简体中文](DatasetPreparation_CN.md)
+[English](DatasetPreparation.md) **|** [简体中文](DatasetPreparation_CN.md)
 
 #### Contents
 
diff --git a/docs/DatasetPreparation_CN.md b/docs/DatasetPreparation_CN.md
index b8dc492..7600256 100644
--- a/docs/DatasetPreparation_CN.md
+++ b/docs/DatasetPreparation_CN.md
@@ -1,6 +1,6 @@
 # 数据准备
 
-[English](DatasetPreparation.md) | [简体中文](DatasetPreparation_CN.md)
+[English](DatasetPreparation.md) **|** [简体中文](DatasetPreparation_CN.md)
 
 #### 目录
 
diff --git a/docs/Datasets.md b/docs/Datasets.md
index 2264823..c7653af 100644
--- a/docs/Datasets.md
+++ b/docs/Datasets.md
@@ -1,6 +1,6 @@
 # Datasets
 
-[English](Datasets.md) | [简体中文](Datasets_CN.md)
+[English](Datasets.md) **|** [简体中文](Datasets_CN.md)
 
 ## Supported Datasets
 
diff --git a/docs/Datasets_CN.md b/docs/Datasets_CN.md
index e785f2c..0a6324a 100644
--- a/docs/Datasets_CN.md
+++ b/docs/Datasets_CN.md
@@ -1,6 +1,6 @@
 # 数据处理
 
-[English](Datasets.md) | [简体中文](Datasets_CN.md)
+[English](Datasets.md) **|** [简体中文](Datasets_CN.md)
 
 ## 支持的数据处理
 
diff --git a/docs/DesignConvention.md b/docs/DesignConvention.md
index 4828147..35ee55f 100644
--- a/docs/DesignConvention.md
+++ b/docs/DesignConvention.md
@@ -1,6 +1,6 @@
 # Codebase Designs and Conventions
 
-[English](DesignConvention.md) | [简体中文](DesignConvention_CN.md)
+[English](DesignConvention.md) **|** [简体中文](DesignConvention_CN.md)
 
 #### Contents
 
diff --git a/docs/DesignConvention_CN.md b/docs/DesignConvention_CN.md
index 8b20111..d3c16d3 100644
--- a/docs/DesignConvention_CN.md
+++ b/docs/DesignConvention_CN.md
@@ -1,6 +1,6 @@
 # 代码库的设计和约定
 
-[English](DesignConvention.md) | [简体中文](DesignConvention_CN.md)
+[English](DesignConvention.md) **|** [简体中文](DesignConvention_CN.md)
 
 #### 目录
 
diff --git a/docs/HOWTOs.md b/docs/HOWTOs.md
index 1b2632c..a2d6433 100644
--- a/docs/HOWTOs.md
+++ b/docs/HOWTOs.md
@@ -1,6 +1,6 @@
 # HOWTOs
 
-[English](HOWTOs.md) | [简体中文](HOWTOs_CN.md)
+[English](HOWTOs.md) **|** [简体中文](HOWTOs_CN.md)
 
 ## How to train StyleGAN2
 
@@ -17,7 +17,7 @@
 
 ## How to test StyleGAN2
 
-1. Download pre-trained models from [ModelZoo](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) to the `experiments/pretrained_models` folder.
+1. Download pre-trained models from **ModelZoo** ([Google Drive](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing), [百度网盘](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g)) to the `experiments/pretrained_models` folder.
 1. Test.
 
     > python tests/test_stylegan2.py
@@ -30,15 +30,15 @@
     1. Clone dlib repo: `git clone git@github.com:davisking/dlib.git`
     1. `cd dlib`
     1. Install: `python setup.py install`
-2. Download the dlib pretrained models from [ModelZoo](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) to the `experiments/pretrained_models/dlib` folder.<br>
+2. Download the dlib pretrained models from **ModelZoo** ([Google Drive](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing), [百度网盘](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g)) to the `experiments/pretrained_models/dlib` folder.<br>
     You can download by run the following command OR manually download the pretrained models.
 
-    > python scripts/download_pretrained_models.py --method dlib
+    > python scripts/download_pretrained_models.py dlib
 
-3. Download pretrained DFDNet models, dictionary and face template from [ModelZoo](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) to the `experiments/pretrained_models/DFDNet` folder.<br>
+3. Download pretrained DFDNet models, dictionary and face template from **ModelZoo** ([Google Drive](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing), [百度网盘](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g)) to the `experiments/pretrained_models/DFDNet` folder.<br>
     You can download by run the the following command OR manually download the pretrained models.
 
-    > python scripts/download_pretrained_models.py --method DFDNet
+    > python scripts/download_pretrained_models.py DFDNet
 
 4. Prepare the testing dataset in the `datasets`, for example, we put images in the `datasets/TestWhole` folder.
 5. Test.
diff --git a/docs/HOWTOs_CN.md b/docs/HOWTOs_CN.md
index e728e53..aad7f25 100644
--- a/docs/HOWTOs_CN.md
+++ b/docs/HOWTOs_CN.md
@@ -1,6 +1,6 @@
 # HOWTOs
 
-[English](HOWTOs.md) | [简体中文](HOWTOs_CN.md)
+[English](HOWTOs.md) **|** [简体中文](HOWTOs_CN.md)
 
 ## 如何训练 StyleGAN2
 
@@ -17,7 +17,7 @@
 
 ## 如何测试 StyleGAN2
 
-1. 从 [ModelZoo](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) 下载预训练模型到 `experiments/pretrained_models` 文件夹.
+1. 从 **ModelZoo** ([Google Drive](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing), [百度网盘](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g)) 下载预训练模型到 `experiments/pretrained_models` 文件夹.
 1. 测试.
 
     > python tests/test_stylegan2.py
@@ -30,15 +30,15 @@
     1. 克隆 dlib repo: `git clone git@github.com:davisking/dlib.git`
     1. `cd dlib`
     1. 安装: `python setup.py install`
-2. 从 [ModelZoo](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) 下载预训练的 dlib 模型到 `experiments/pretrained_models/dlib` 文件夹.<br>
+2. 从 **ModelZoo** ([Google Drive](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing), [百度网盘](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g)) 下载预训练的 dlib 模型到 `experiments/pretrained_models/dlib` 文件夹.<br>
     你可以通过运行下面的命令下载 或 手动下载.
 
-    > python scripts/download_pretrained_models.py --method dlib
+    > python scripts/download_pretrained_models.py dlib
 
-3. 从 [ModelZoo](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) 下载 DFDNet 模型, 字典和人脸关键点模板到 `experiments/pretrained_models/DFDNet` 文件夹.<br>
+3. 从 **ModelZoo** ([Google Drive](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing), [百度网盘](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g)) 下载 DFDNet 模型, 字典和人脸关键点模板到 `experiments/pretrained_models/DFDNet` 文件夹.<br>
      你可以通过运行下面的命令下载 或 手动下载.
 
-    > python scripts/download_pretrained_models.py --method DFDNet
+    > python scripts/download_pretrained_models.py DFDNet
 
 4. 准备测试图片到 `datasets`, 比如说我们把测试图片放在 `datasets/TestWhole` 文件夹.
 5. 测试.
diff --git a/docs/Logging.md b/docs/Logging.md
index 68e486b..ac2e45c 100644
--- a/docs/Logging.md
+++ b/docs/Logging.md
@@ -1,6 +1,6 @@
 # Logging
 
-[English](Logging.md) | [简体中文](Logging_CN.md)
+[English](Logging.md) **|** [简体中文](Logging_CN.md)
 
 #### Contents
 
diff --git a/docs/Logging_CN.md b/docs/Logging_CN.md
index 01d489e..cb1889f 100644
--- a/docs/Logging_CN.md
+++ b/docs/Logging_CN.md
@@ -1,6 +1,6 @@
 # Logging日志
 
-[English](Logging.md) | [简体中文](Logging_CN.md)
+[English](Logging.md) **|** [简体中文](Logging_CN.md)
 
 #### 目录
 
diff --git a/docs/ModelZoo.md b/docs/ModelZoo.md
index 4431ec5..af6579c 100644
--- a/docs/ModelZoo.md
+++ b/docs/ModelZoo.md
@@ -1,6 +1,6 @@
 # Model Zoo and Baselines
 
-[English](ModelZoo.md) | [简体中文](ModelZoo_CN.md)
+[English](ModelZoo.md) **|** [简体中文](ModelZoo_CN.md)
 
 We provide:
 
@@ -9,16 +9,16 @@ We provide:
 
 You can put the downloaded models in the `experiments/pretrained_models` folder.
 
-**[Download official pre-trained models](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing)**
+**[Download official pre-trained models]** ([Google Drive](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing), [百度网盘](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g))(https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing))
 
 You can use the scrip to download pre-trained models from Google Drive.
 
 ```python
-python scripts/download_pretrained_models.py --method ESRGAN
+python scripts/download_pretrained_models.py ESRGAN
 # method can be ESRGAN, EDVR, StyleGAN, EDSR, DUF, DFDNet, dlib
 ```
 
-**[Download reproduced models and logs](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing)**
+**[Download reproduced models and logs]** ([Google Drive](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing), [百度网盘](https://pan.baidu.com/s/1UElD6q8sVAgn_cxeBDOlvQ))
 
 In addition, we upload the training process and curves in [wandb](https://www.wandb.com/).
 
diff --git a/docs/ModelZoo_CN.md b/docs/ModelZoo_CN.md
index 8299231..9290a91 100644
--- a/docs/ModelZoo_CN.md
+++ b/docs/ModelZoo_CN.md
@@ -1,6 +1,6 @@
 # 模型库和基准
 
-[English](ModelZoo.md) | [简体中文](ModelZoo_CN.md)
+[English](ModelZoo.md) **|** [简体中文](ModelZoo_CN.md)
 
 我们提供了:
 
@@ -9,16 +9,15 @@
 
 下载的模型可以放在 `experiments/pretrained_models` 文件夹.
 
-**[下载官方提供的预训练模型](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing)**
-
+**[下载官方提供的预训练模型]** ([Google Drive](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing), [百度网盘](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g))
 你可以使用以下脚本从Google Drive下载预训练模型.
 
 ```python
-python scripts/download_pretrained_models.py --method ESRGAN
+python scripts/download_pretrained_models.py ESRGAN
 # method can be ESRGAN, EDVR, StyleGAN, EDSR, DUF, DFDNet, dlib
 ```
 
-**[下载复现的模型和log](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing)**
+**[下载复现的模型和log]** ([Google Drive](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing), [百度网盘](https://pan.baidu.com/s/1UElD6q8sVAgn_cxeBDOlvQ))
 
 此外, 我们在 [wandb](https://www.wandb.com/) 上更新了模型训练的过程和曲线. 大家可以方便的比较:
 
diff --git a/docs/Models.md b/docs/Models.md
index bf6e96d..35e156a 100644
--- a/docs/Models.md
+++ b/docs/Models.md
@@ -1,6 +1,6 @@
 # Models
 
-[English](Models.md) | [简体中文](Models_CN.md)
+[English](Models.md) **|** [简体中文](Models_CN.md)
 
 #### Contents
 
diff --git a/docs/Models_CN.md b/docs/Models_CN.md
index 7f95376..35eee42 100644
--- a/docs/Models_CN.md
+++ b/docs/Models_CN.md
@@ -1,6 +1,6 @@
 # 模型
 
-[English](Models.md) | [简体中文](Models_CN.md)
+[English](Models.md) **|** [简体中文](Models_CN.md)
 
 #### 目录
 
diff --git a/docs/TrainTest.md b/docs/TrainTest.md
index 4a6cab2..b3d7cd7 100644
--- a/docs/TrainTest.md
+++ b/docs/TrainTest.md
@@ -1,6 +1,6 @@
 # Training and Testing
 
-[English](TrainTest.md) | [简体中文](TrainTest_CN.md)
+[English](TrainTest.md) **|** [简体中文](TrainTest_CN.md)
 
 Please run the commands in the root path of `BasicSR`. <br>
 In general, both the training and testing include the following steps:
diff --git a/docs/TrainTest_CN.md b/docs/TrainTest_CN.md
index 2bb66e0..21c4cbd 100644
--- a/docs/TrainTest_CN.md
+++ b/docs/TrainTest_CN.md
@@ -1,6 +1,6 @@
 # 训练和测试
 
-[English](TrainTest.md) | [简体中文](TrainTest_CN.md)
+[English](TrainTest.md) **|** [简体中文](TrainTest_CN.md)
 
 所有的命令都在 `BasicSR` 的根目录下运行. <br>
 一般来说, 训练和测试都有以下的步骤:
diff --git a/scripts/download_pretrained_models.py b/scripts/download_pretrained_models.py
index a2fec5d..cc26218 100644
--- a/scripts/download_pretrained_models.py
+++ b/scripts/download_pretrained_models.py
@@ -29,7 +29,12 @@ def download_pretrained_models(method, file_ids):
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
 
-    parser.add_argument('--method', type=str, default='ESRGAN')
+    parser.add_argument(
+        'method',
+        type=str,
+        help=(
+            "Options: 'ESRGAN', 'EDVR', 'StyleGAN', 'EDSR', 'DUF', 'DFDNet', "
+            "'dlib'. Set to 'all' if you want to download all the models."))
     args = parser.parse_args()
 
     file_ids = {
@@ -121,4 +126,8 @@ def download_pretrained_models(method, file_ids):
         }
     }
 
-    download_pretrained_models(args.method, file_ids[args.method])
+    if args.method == 'all':
+        for method in file_ids.keys():
+            download_pretrained_models(method, file_ids[method])
+    else:
+        download_pretrained_models(args.method, file_ids[args.method])