Upload 11 files

docs/CONTRIBUTING.md

@@ -0,0 +1,44 @@
+# Contributing to Real-ESRGAN
+
+:art: Real-ESRGAN needs your contributions. Any contributions are welcome, such as new features/models/typo fixes/suggestions/maintenance, *etc*. See [CONTRIBUTING.md](docs/CONTRIBUTING.md). All contributors are list [here](README.md#hugs-acknowledgement).
+
+We like open-source and want to develop practical algorithms for general image restoration. However, individual strength is limited. So, any kinds of contributions are welcome, such as:
+
+- New features
+- New models (your fine-tuned models)
+- Bug fixes
+- Typo fixes
+- Suggestions
+- Maintenance
+- Documents
+- *etc*
+
+## Workflow
+
+1. Fork and pull the latest Real-ESRGAN repository
+1. Checkout a new branch (do not use master branch for PRs)
+1. Commit your changes
+1. Create a PR
+
+**Note**:
+
+1. Please check the code style and linting
+    1. The style configuration is specified in [setup.cfg](setup.cfg)
+    1. If you use VSCode, the settings are configured in [.vscode/settings.json](.vscode/settings.json)
+1. Strongly recommend using `pre-commit hook`. It will check your code style and linting before your commit.
+    1. In the root path of project folder, run `pre-commit install`
+    1. The pre-commit configuration is listed in [.pre-commit-config.yaml](.pre-commit-config.yaml)
+1. Better to [open a discussion](https://github.com/xinntao/Real-ESRGAN/discussions) before large changes.
+    1. Welcome to discuss :sunglasses:. I will try my best to join the discussion.
+
+## TODO List
+
+:zero: The most straightforward way of improving model performance is to fine-tune on some specific datasets.
+
+Here are some TODOs:
+
+- [ ] optimize for human faces
+- [ ] optimize for texts
+- [ ] support controllable restoration strength
+
+:one: There are also [several issues](https://github.com/xinntao/Real-ESRGAN/issues) that require helpers to improve. If you can help, please let me know :smile:

docs/FAQ.md

@@ -0,0 +1,10 @@
+# FAQ
+
+1. **Q: How to select models?**<br>
+A: Please refer to [docs/model_zoo.md](docs/model_zoo.md)
+
+1. **Q: Can `face_enhance` be used for anime images/animation videos?**<br>
+A: No, it can only be used for real faces. It is recommended not to use this option for anime images/animation videos to save GPU memory.
+
+1. **Q: Error "slow_conv2d_cpu" not implemented for 'Half'**<br>
+A: In order to save GPU memory consumption and speed up inference, Real-ESRGAN uses half precision (fp16) during inference by default. However, some operators for half inference are not implemented in CPU mode. You need to add **`--fp32` option** for the commands. For example, `python inference_realesrgan.py -n RealESRGAN_x4plus.pth -i inputs --fp32`.

docs/Training.md

@@ -0,0 +1,271 @@
+# :computer: How to Train/Finetune Real-ESRGAN
+
+- [Train Real-ESRGAN](#train-real-esrgan)
+  - [Overview](#overview)
+  - [Dataset Preparation](#dataset-preparation)
+  - [Train Real-ESRNet](#Train-Real-ESRNet)
+  - [Train Real-ESRGAN](#Train-Real-ESRGAN)
+- [Finetune Real-ESRGAN on your own dataset](#Finetune-Real-ESRGAN-on-your-own-dataset)
+  - [Generate degraded images on the fly](#Generate-degraded-images-on-the-fly)
+  - [Use paired training data](#use-your-own-paired-data)
+
+[English](Training.md) **|** [简体中文](Training_CN.md)
+
+## Train Real-ESRGAN
+
+### Overview
+
+The training has been divided into two stages. These two stages have the same data synthesis process and training pipeline, except for the loss functions. Specifically,
+
+1. We first train Real-ESRNet with L1 loss from the pre-trained model ESRGAN.
+1. We then use the trained Real-ESRNet model as an initialization of the generator, and train the Real-ESRGAN with a combination of L1 loss, perceptual loss and GAN loss.
+
+### Dataset Preparation
+
+We use DF2K (DIV2K and Flickr2K) + OST datasets for our training. Only HR images are required. <br>
+You can download from :
+
+1. DIV2K: http://data.vision.ee.ethz.ch/cvl/DIV2K/DIV2K_train_HR.zip
+2. Flickr2K: https://cv.snu.ac.kr/research/EDSR/Flickr2K.tar
+3. OST: https://openmmlab.oss-cn-hangzhou.aliyuncs.com/datasets/OST_dataset.zip
+
+Here are steps for data preparation.
+
+#### Step 1: [Optional] Generate multi-scale images
+
+For the DF2K dataset, we use a multi-scale strategy, *i.e.*, we downsample HR images to obtain several Ground-Truth images with different scales. <br>
+You can use the [scripts/generate_multiscale_DF2K.py](scripts/generate_multiscale_DF2K.py) script to generate multi-scale images. <br>
+Note that this step can be omitted if you just want to have a fast try.
+
+```bash
+python scripts/generate_multiscale_DF2K.py --input datasets/DF2K/DF2K_HR --output datasets/DF2K/DF2K_multiscale
+```
+
+#### Step 2: [Optional] Crop to sub-images
+
+We then crop DF2K images into sub-images for faster IO and processing.<br>
+This step is optional if your IO is enough or your disk space is limited.
+
+You can use the [scripts/extract_subimages.py](scripts/extract_subimages.py) script. Here is the example:
+
+```bash
+ python scripts/extract_subimages.py --input datasets/DF2K/DF2K_multiscale --output datasets/DF2K/DF2K_multiscale_sub --crop_size 400 --step 200
+```
+
+#### Step 3: Prepare a txt for meta information
+
+You need to prepare a txt file containing the image paths. The following are some examples in `meta_info_DF2Kmultiscale+OST_sub.txt` (As different users may have different sub-images partitions, this file is not suitable for your purpose and you need to prepare your own txt file):
+
+```txt
+DF2K_HR_sub/000001_s001.png
+DF2K_HR_sub/000001_s002.png
+DF2K_HR_sub/000001_s003.png
+...
+```
+
+You can use the [scripts/generate_meta_info.py](scripts/generate_meta_info.py) script to generate the txt file. <br>
+You can merge several folders into one meta_info txt. Here is the example:
+
+```bash
+ python scripts/generate_meta_info.py --input datasets/DF2K/DF2K_HR datasets/DF2K/DF2K_multiscale --root datasets/DF2K datasets/DF2K --meta_info datasets/DF2K/meta_info/meta_info_DF2Kmultiscale.txt
+```
+
+### Train Real-ESRNet
+
+1. Download pre-trained model [ESRGAN](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth) into `experiments/pretrained_models`.
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth -P experiments/pretrained_models
+    ```
+1. Modify the content in the option file `options/train_realesrnet_x4plus.yml` accordingly:
+    ```yml
+    train:
+        name: DF2K+OST
+        type: RealESRGANDataset
+        dataroot_gt: datasets/DF2K  # modify to the root path of your folder
+        meta_info: realesrgan/meta_info/meta_info_DF2Kmultiscale+OST_sub.txt  # modify to your own generate meta info txt
+        io_backend:
+            type: disk
+    ```
+1. If you want to perform validation during training, uncomment those lines and modify accordingly:
+    ```yml
+      # Uncomment these for validation
+      # val:
+      #   name: validation
+      #   type: PairedImageDataset
+      #   dataroot_gt: path_to_gt
+      #   dataroot_lq: path_to_lq
+      #   io_backend:
+      #     type: disk
+
+    ...
+
+      # Uncomment these for validation
+      # validation settings
+      # val:
+      #   val_freq: !!float 5e3
+      #   save_img: True
+
+      #   metrics:
+      #     psnr: # metric name, can be arbitrary
+      #       type: calculate_psnr
+      #       crop_border: 4
+      #       test_y_channel: false
+    ```
+1. Before the formal training, you may run in the `--debug` mode to see whether everything is OK. We use four GPUs for training:
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --debug
+    ```
+
+    Train with **a single GPU** in the *debug* mode:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --debug
+    ```
+1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --auto_resume
+    ```
+
+    Train with **a single GPU**:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --auto_resume
+    ```
+
+### Train Real-ESRGAN
+
+1. After the training of Real-ESRNet, you now have the file `experiments/train_RealESRNetx4plus_1000k_B12G4_fromESRGAN/model/net_g_1000000.pth`. If you need to specify the pre-trained path to other files, modify the `pretrain_network_g` value in the option file `train_realesrgan_x4plus.yml`.
+1. Modify the option file `train_realesrgan_x4plus.yml` accordingly. Most modifications are similar to those listed above.
+1. Before the formal training, you may run in the `--debug` mode to see whether everything is OK. We use four GPUs for training:
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --debug
+    ```
+
+    Train with **a single GPU** in the *debug* mode:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --debug
+    ```
+1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --auto_resume
+    ```
+
+    Train with **a single GPU**:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --auto_resume
+    ```
+
+## Finetune Real-ESRGAN on your own dataset
+
+You can finetune Real-ESRGAN on your own dataset. Typically, the fine-tuning process can be divided into two cases:
+
+1. [Generate degraded images on the fly](#Generate-degraded-images-on-the-fly)
+1. [Use your own **paired** data](#Use-paired-training-data)
+
+### Generate degraded images on the fly
+
+Only high-resolution images are required. The low-quality images are generated with the degradation process described in Real-ESRGAN during training.
+
+**1. Prepare dataset**
+
+See [this section](#dataset-preparation) for more details.
+
+**2. Download pre-trained models**
+
+Download pre-trained models into `experiments/pretrained_models`.
+
+- *RealESRGAN_x4plus.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+    ```
+
+- *RealESRGAN_x4plus_netD.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth -P experiments/pretrained_models
+    ```
+
+**3. Finetune**
+
+Modify [options/finetune_realesrgan_x4plus.yml](options/finetune_realesrgan_x4plus.yml) accordingly, especially the `datasets` part:
+
+```yml
+train:
+    name: DF2K+OST
+    type: RealESRGANDataset
+    dataroot_gt: datasets/DF2K  # modify to the root path of your folder
+    meta_info: realesrgan/meta_info/meta_info_DF2Kmultiscale+OST_sub.txt  # modify to your own generate meta info txt
+    io_backend:
+        type: disk
+```
+
+We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --launcher pytorch --auto_resume
+```
+
+Finetune with **a single GPU**:
+```bash
+python realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --auto_resume
+```
+
+### Use your own paired data
+
+You can also finetune RealESRGAN with your own paired data. It is more similar to fine-tuning ESRGAN.
+
+**1. Prepare dataset**
+
+Assume that you already have two folders:
+
+- **gt folder** (Ground-truth, high-resolution images): *datasets/DF2K/DIV2K_train_HR_sub*
+- **lq folder** (Low quality, low-resolution images): *datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub*
+
+Then, you can prepare the meta_info txt file using the script [scripts/generate_meta_info_pairdata.py](scripts/generate_meta_info_pairdata.py):
+
+```bash
+python scripts/generate_meta_info_pairdata.py --input datasets/DF2K/DIV2K_train_HR_sub datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub --meta_info datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt
+```
+
+**2. Download pre-trained models**
+
+Download pre-trained models into `experiments/pretrained_models`.
+
+- *RealESRGAN_x4plus.pth*
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+    ```
+
+- *RealESRGAN_x4plus_netD.pth*
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth -P experiments/pretrained_models
+    ```
+
+**3. Finetune**
+
+Modify [options/finetune_realesrgan_x4plus_pairdata.yml](options/finetune_realesrgan_x4plus_pairdata.yml) accordingly, especially the `datasets` part:
+
+```yml
+train:
+    name: DIV2K
+    type: RealESRGANPairedDataset
+    dataroot_gt: datasets/DF2K  # modify to the root path of your folder
+    dataroot_lq: datasets/DF2K  # modify to the root path of your folder
+    meta_info: datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt  # modify to your own generate meta info txt
+    io_backend:
+        type: disk
+```
+
+We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --launcher pytorch --auto_resume
+```
+
+Finetune with **a single GPU**:
+```bash
+python realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --auto_resume
+```

docs/Training_CN.md

@@ -0,0 +1,271 @@
+# :computer: 如何训练/微调 Real-ESRGAN
+
+- [训练 Real-ESRGAN](#训练-real-esrgan)
+  - [概述](#概述)
+  - [准备数据集](#准备数据集)
+  - [训练 Real-ESRNet 模型](#训练-real-esrnet-模型)
+  - [训练 Real-ESRGAN 模型](#训练-real-esrgan-模型)
+- [用自己的数据集微调 Real-ESRGAN](#用自己的数据集微调-real-esrgan)
+  - [动态生成降级图像](#动态生成降级图像)
+  - [使用已配对的数据](#使用已配对的数据)
+
+[English](Training.md) **|** [简体中文](Training_CN.md)
+
+## 训练 Real-ESRGAN
+
+### 概述
+
+训练分为两个步骤。除了 loss 函数外，这两个步骤拥有相同数据合成以及训练的一条龙流程。具体点说：
+
+1. 首先使用 L1 loss 训练 Real-ESRNet 模型，其中 L1 loss 来自预先训练的 ESRGAN 模型。
+
+2. 然后我们将 Real-ESRNet 模型作为生成器初始化，结合L1 loss、感知 loss、GAN loss 三者的参数对 Real-ESRGAN 进行训练。
+
+### 准备数据集
+
+我们使用 DF2K ( DIV2K 和 Flickr2K ) + OST 数据集进行训练。只需要HR图像！<br>
+下面是网站链接:
+1. DIV2K: http://data.vision.ee.ethz.ch/cvl/DIV2K/DIV2K_train_HR.zip
+2. Flickr2K: https://cv.snu.ac.kr/research/EDSR/Flickr2K.tar
+3. OST: https://openmmlab.oss-cn-hangzhou.aliyuncs.com/datasets/OST_dataset.zip
+
+以下是数据的准备步骤。
+
+#### 第1步：【可选】生成多尺寸图片
+
+针对 DF2K 数据集，我们使用多尺寸缩放策略，*换言之*，我们对 HR 图像进行下采样，就能获得多尺寸的标准参考（Ground-Truth）图像。 <br>
+您可以使用这个 [scripts/generate_multiscale_DF2K.py](scripts/generate_multiscale_DF2K.py) 脚本快速生成多尺寸的图像。<br>
+注意：如果您只想简单试试，那么可以跳过此步骤。
+
+```bash
+python scripts/generate_multiscale_DF2K.py --input datasets/DF2K/DF2K_HR --output datasets/DF2K/DF2K_multiscale
+```
+
+#### 第2步：【可选】裁切为子图像
+
+我们可以将 DF2K 图像裁切为子图像，以加快 IO 和处理速度。<br>
+如果你的 IO 够好或储存空间有限，那么此步骤是可选的。<br>
+
+您可以使用脚本 [scripts/extract_subimages.py](scripts/extract_subimages.py)。这是使用示例:
+
+```bash
+ python scripts/extract_subimages.py --input datasets/DF2K/DF2K_multiscale --output datasets/DF2K/DF2K_multiscale_sub --crop_size 400 --step 200
+```
+
+#### 第3步：准备元信息 txt
+
+您需要准备一个包含图像路径的 txt 文件。下面是 `meta_info_DF2Kmultiscale+OST_sub.txt` 中的部分展示（由于各个用户可能有截然不同的子图像划分，这个文件不适合你的需求，你得准备自己的 txt 文件)：
+
+```txt
+DF2K_HR_sub/000001_s001.png
+DF2K_HR_sub/000001_s002.png
+DF2K_HR_sub/000001_s003.png
+...
+```
+
+你可以使用该脚本 [scripts/generate_meta_info.py](scripts/generate_meta_info.py) 生成包含图像路径的 txt 文件。<br>
+你还可以合并多个文件夹的图像路径到一个元信息（meta_info）txt。这是使用示例:
+
+```bash
+ python scripts/generate_meta_info.py --input datasets/DF2K/DF2K_HR, datasets/DF2K/DF2K_multiscale --root datasets/DF2K, datasets/DF2K --meta_info datasets/DF2K/meta_info/meta_info_DF2Kmultiscale.txt
+```
+
+### 训练 Real-ESRNet 模型
+
+1. 下载预先训练的模型 [ESRGAN](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth)，放到 `experiments/pretrained_models`目录下。
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth -P experiments/pretrained_models
+    ```
+2. 相应地修改选项文件 `options/train_realesrnet_x4plus.yml` 中的内容：
+    ```yml
+    train:
+        name: DF2K+OST
+        type: RealESRGANDataset
+        dataroot_gt: datasets/DF2K  # 修改为你的数据集文件夹根目录
+        meta_info: realesrgan/meta_info/meta_info_DF2Kmultiscale+OST_sub.txt  # 修改为你自己生成的元信息txt
+        io_backend:
+            type: disk
+    ```
+3. 如果你想在训练过程中执行验证，就取消注释这些内容并进行相应的修改：
+    ```yml
+      # 取消注释这些以进行验证
+      # val:
+      #   name: validation
+      #   type: PairedImageDataset
+      #   dataroot_gt: path_to_gt
+      #   dataroot_lq: path_to_lq
+      #   io_backend:
+      #     type: disk
+
+    ...
+
+      # 取消注释这些以进行验证
+      # 验证设置
+      # val:
+      #   val_freq: !!float 5e3
+      #   save_img: True
+
+      #   metrics:
+      #     psnr: # 指标名称，可以是任意的
+      #       type: calculate_psnr
+      #       crop_border: 4
+      #       test_y_channel: false
+    ```
+4. 正式训练之前，你可以用 `--debug` 模式检查是否正常运行。我们用了4个GPU进行训练：
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --debug
+    ```
+
+    用 **1个GPU** 训练的 debug 模式示例:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --debug
+    ```
+5. 正式训练开始。我们用了4个GPU进行训练。还可以使用参数 `--auto_resume` 在必要时自动恢复训练。
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --auto_resume
+    ```
+
+    用 **1个GPU** 训练：
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --auto_resume
+    ```
+
+### 训练 Real-ESRGAN 模型
+
+1. 训练 Real-ESRNet 模型后，您得到了这个 `experiments/train_RealESRNetx4plus_1000k_B12G4_fromESRGAN/model/net_g_1000000.pth` 文件。如果需要指定预训练路径到其他文件，请修改选项文件 `train_realesrgan_x4plus.yml` 中 `pretrain_network_g` 的值。
+1. 修改选项文件 `train_realesrgan_x4plus.yml` 的内容。大多数修改与上节提到的类似。
+1. 正式训练之前，你可以以 `--debug` 模式检查是否正常运行。我们使用了4个GPU进行训练：
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --debug
+    ```
+
+    用 **1个GPU** 训练的 debug 模式示例:
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --debug
+    ```
+1. 正式训练开始。我们使用4个GPU进行训练。还可以使用参数 `--auto_resume` 在必要时自动恢复训练。
+    ```bash
+    CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --auto_resume
+    ```
+
+    用 **1个GPU** 训练：
+    ```bash
+    python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --auto_resume
+    ```
+
+## 用自己的数据集微调 Real-ESRGAN
+
+你可以用自己的数据集微调 Real-ESRGAN。一般地，微调（Fine-Tune）程序可以分为两种类型:
+
+1. [动态生成降级图像](#动态生成降级图像)
+2. [使用**已配对**的数据](#使用已配对的数据)
+
+### 动态生成降级图像
+
+只需要高分辨率图像。在训练过程中，使用 Real-ESRGAN 描述的降级模型生成低质量图像。
+
+**1. 准备数据集**
+
+完整信息请参见[本节](#准备数据集)。
+
+**2. 下载预训练模型**
+
+下载预先训练的模型到 `experiments/pretrained_models` 目录下。
+
+- *RealESRGAN_x4plus.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+    ```
+
+- *RealESRGAN_x4plus_netD.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth -P experiments/pretrained_models
+    ```
+
+**3. 微调**
+
+修改选项文件 [options/finetune_realesrgan_x4plus.yml](options/finetune_realesrgan_x4plus.yml) ，特别是 `datasets` 部分：
+
+```yml
+train:
+    name: DF2K+OST
+    type: RealESRGANDataset
+    dataroot_gt: datasets/DF2K   # 修改为你的数据集文件夹根目录
+    meta_info: realesrgan/meta_info/meta_info_DF2Kmultiscale+OST_sub.txt  # 修改为你自己生成的元信息txt
+    io_backend:
+        type: disk
+```
+
+我们使用4个GPU进行训练。还可以使用参数 `--auto_resume` 在必要时自动恢复训练。
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --launcher pytorch --auto_resume
+```
+
+用 **1个GPU** 训练：
+```bash
+python realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --auto_resume
+```
+
+### 使用已配对的数据
+
+你还可以用自己已经配对的数据微调 RealESRGAN。这个过程更类似于微调 ESRGAN。
+
+**1. 准备数据集**
+
+假设你已经有两个文件夹（folder）:
+
+- **gt folder**（标准参考，高分辨率图像）：*datasets/DF2K/DIV2K_train_HR_sub*
+- **lq folder**（低质量，低分辨率图像）：*datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub*
+
+然后，您可以使用脚本 [scripts/generate_meta_info_pairdata.py](scripts/generate_meta_info_pairdata.py) 生成元信息（meta_info）txt 文件。
+
+```bash
+python scripts/generate_meta_info_pairdata.py --input datasets/DF2K/DIV2K_train_HR_sub datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub --meta_info datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt
+```
+
+**2. 下载预训练模型**
+
+下载预先训练的模型到 `experiments/pretrained_models` 目录下。
+
+- *RealESRGAN_x4plus.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P experiments/pretrained_models
+    ```
+
+- *RealESRGAN_x4plus_netD.pth*:
+    ```bash
+    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth -P experiments/pretrained_models
+    ```
+
+**3. 微调**
+
+修改选项文件 [options/finetune_realesrgan_x4plus_pairdata.yml](options/finetune_realesrgan_x4plus_pairdata.yml) ，特别是 `datasets` 部分：
+
+```yml
+train:
+    name: DIV2K
+    type: RealESRGANPairedDataset
+    dataroot_gt: datasets/DF2K  # 修改为你的 gt folder 文件夹根目录
+    dataroot_lq: datasets/DF2K  # 修改为你的 lq folder 文件夹根目录
+    meta_info: datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt  # 修改为你自己生成的元信息txt
+    io_backend:
+        type: disk
+```
+
+我们使用4个GPU进行训练。还可以使用参数 `--auto_resume` 在必要时自动恢复训练。
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --launcher pytorch --auto_resume
+```
+
+用 **1个GPU** 训练：
+```bash
+python realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --auto_resume
+```

docs/anime_comparisons.md

@@ -0,0 +1,66 @@
+# Comparisons among different anime models
+
+[English](anime_comparisons.md) **|** [简体中文](anime_comparisons_CN.md)
+
+## Update News
+
+- 2022/04/24: Release **AnimeVideo-v3**. We have made the following improvements:
+  - **better naturalness**
+  - **Fewer artifacts**
+  - **more faithful to the original colors**
+  - **better texture restoration**
+  - **better background restoration**
+
+## Comparisons
+
+We have compared our RealESRGAN-AnimeVideo-v3 with the following methods.
+Our RealESRGAN-AnimeVideo-v3 can achieve better results with faster inference speed.
+
+- [waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan) with the hyperparameters: `tile=0`, `noiselevel=2`
+- [Real-CUGAN](https://github.com/bilibili/ailab/tree/main/Real-CUGAN): we use the [20220227](https://github.com/bilibili/ailab/releases/tag/Real-CUGAN-add-faster-low-memory-mode) version, the hyperparameters are: `cache_mode=0`, `tile=0`, `alpha=1`.
+- our RealESRGAN-AnimeVideo-v3
+
+## Results
+
+You may need to **zoom in** for comparing details, or **click the image** to see in the full size. Please note that the images
+in the table below are the resized and cropped patches from the original images, you can download the original inputs and outputs from [Google Drive](https://drive.google.com/drive/folders/1bc_Hje1Nqop9NDkUvci2VACSjL7HZMRp?usp=sharing) .
+
+**More natural results, better background restoration**
+| Input | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![157083983-bec52c67-9a5e-4eed-afef-01fe6cd2af85_patch](https://user-images.githubusercontent.com/11482921/164452769-5d8cb4f8-1708-42d2-b941-f44a6f136feb.png) | ![](https://user-images.githubusercontent.com/11482921/164452767-c825cdec-f721-4ff1-aef1-fec41f146c4c.png) | ![](https://user-images.githubusercontent.com/11482921/164452755-3be50895-e3d4-432d-a7b9-9085c2a8e771.png) | ![](https://user-images.githubusercontent.com/11482921/164452771-be300656-379a-4323-a755-df8025a8c451.png) |
+|![a0010_patch](https://user-images.githubusercontent.com/11482921/164454047-22eeb493-3fa9-4142-9fc2-6f2a1c074cd5.png) | ![](https://user-images.githubusercontent.com/11482921/164454046-d5e79f8f-00a0-4b55-bc39-295d0d69747a.png) | ![](https://user-images.githubusercontent.com/11482921/164454040-87886b11-9d08-48bd-862f-0d4aed72eb19.png) | ![](https://user-images.githubusercontent.com/11482921/164454055-73dc9f02-286e-4d5c-8f70-c13742e08f42.png) |
+|![00000044_patch](https://user-images.githubusercontent.com/11482921/164451232-bacf64fc-e55a-44db-afbb-6b31ab0f8973.png) | ![](https://user-images.githubusercontent.com/11482921/164451318-f309b61a-75b8-4b74-b5f3-595725f1cf0b.png) | ![](https://user-images.githubusercontent.com/11482921/164451348-994f8a35-adbe-4a4b-9c61-feaa294af06a.png) | ![](https://user-images.githubusercontent.com/11482921/164451361-9b7d376e-6f75-4648-b752-542b44845d1c.png) |
+
+**Fewer artifacts, better detailed textures**
+| Input | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![00000053_patch](https://user-images.githubusercontent.com/11482921/164448411-148a7e5c-cfcd-4504-8bc7-e318eb883bb6.png) | ![](https://user-images.githubusercontent.com/11482921/164448633-dfc15224-b6d2-4403-a3c9-4bb819979364.png) | ![](https://user-images.githubusercontent.com/11482921/164448771-0d359509-5293-4d4c-8e3c-86a2a314ea88.png) | ![](https://user-images.githubusercontent.com/11482921/164448848-1a4ff99e-075b-4458-9db7-2c89e8160aa0.png) |
+|![Disney_v4_22_018514_s2_patch](https://user-images.githubusercontent.com/11482921/164451898-83311cdf-bd3e-450f-b9f6-34d7fea3ab79.png) | ![](https://user-images.githubusercontent.com/11482921/164451894-6c56521c-6561-40d6-a3a5-8dde2c167b8a.png) | ![](https://user-images.githubusercontent.com/11482921/164451888-af9b47e3-39dc-4f3e-b0d7-d372d8191e2a.png) | ![](https://user-images.githubusercontent.com/11482921/164451901-31ca4dd4-9847-4baa-8cde-ad50f4053dcf.png) |
+|![Japan_v2_0_007261_s2_patch](https://user-images.githubusercontent.com/11482921/164454578-73c77392-77de-49c5-b03c-c36631723192.png) | ![](https://user-images.githubusercontent.com/11482921/164454574-b1ede5f0-4520-4eaa-8f59-086751a34e62.png) | ![](https://user-images.githubusercontent.com/11482921/164454567-4cb3fdd8-6a2d-4016-85b2-a305a8ff80e4.png) | ![](https://user-images.githubusercontent.com/11482921/164454583-7f243f20-eca3-4500-ac43-eb058a4a101a.png) |
+|![huluxiongdi_2_patch](https://user-images.githubusercontent.com/11482921/164453482-0726c842-337e-40ec-bf6c-f902ee956a8b.png) | ![](https://user-images.githubusercontent.com/11482921/164453480-71d5e091-5bfa-4c77-9c57-4e37f66ca0a3.png) | ![](https://user-images.githubusercontent.com/11482921/164453468-c295d3c9-3661-45f0-9ecd-406a1877f76e.png) | ![](https://user-images.githubusercontent.com/11482921/164453486-3091887c-587c-450e-b6fe-905cb518d57e.png) |
+
+**Other better results**
+| Input | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![Japan_v2_1_128525_s1_patch](https://user-images.githubusercontent.com/11482921/164454933-67697f7c-b6ef-47dc-bfca-822a78af8acf.png) | ![](https://user-images.githubusercontent.com/11482921/164454931-9450de7c-f0b3-4638-9c1e-0668e0c41ef0.png) | ![](https://user-images.githubusercontent.com/11482921/164454926-ed746976-786d-41c5-8a83-7693cd774c3a.png) | ![](https://user-images.githubusercontent.com/11482921/164454936-8abdf0f0-fb30-40eb-8281-3b46c0bcb9ae.png) |
+|![tianshuqitan_2_patch](https://user-images.githubusercontent.com/11482921/164456948-807c1476-90b6-4507-81da-cb986d01600c.png) | ![](https://user-images.githubusercontent.com/11482921/164456943-25e89de9-d7e5-4f61-a2e1-96786af6ae9e.png) | ![](https://user-images.githubusercontent.com/11482921/164456954-b468c447-59f5-4594-9693-3683e44ba3e6.png) | ![](https://user-images.githubusercontent.com/11482921/164456957-640f910c-3b04-407c-ac20-044d72e19735.png) |
+|![00000051_patch](https://user-images.githubusercontent.com/11482921/164456044-e9a6b3fa-b24e-4eb7-acf9-1f7746551b1e.png) ![00000051_patch](https://user-images.githubusercontent.com/11482921/164456421-b67245b0-767d-4250-9105-80bbe507ecfc.png) | ![](https://user-images.githubusercontent.com/11482921/164456040-85763cf2-cb28-4ba3-abb6-1dbb48c55713.png) ![](https://user-images.githubusercontent.com/11482921/164456419-59cf342e-bc1e-4044-868c-e1090abad313.png) | ![](https://user-images.githubusercontent.com/11482921/164456031-4244bb7b-8649-4e01-86f4-40c2099c5afd.png) ![](https://user-images.githubusercontent.com/11482921/164456411-b6afcbe9-c054-448d-a6df-96d3ba3047f8.png) | ![](https://user-images.githubusercontent.com/11482921/164456035-12e270be-fd52-46d4-b18a-3d3b680731fe.png) ![](https://user-images.githubusercontent.com/11482921/164456417-dcaa8b62-f497-427d-b2d2-f390f1200fb9.png) |
+|![00000099_patch](https://user-images.githubusercontent.com/11482921/164455312-6411b6e1-5823-4131-a4b0-a6be8a9ae89f.png) | ![](https://user-images.githubusercontent.com/11482921/164455310-f2b99646-3a22-47a4-805b-dc451ac86ddb.png) | ![](https://user-images.githubusercontent.com/11482921/164455294-35471b42-2826-4451-b7ec-6de01344954c.png) | ![](https://user-images.githubusercontent.com/11482921/164455305-fa4c9758-564a-4081-8b4e-f11057a0404d.png) |
+|![00000016_patch](https://user-images.githubusercontent.com/11482921/164455672-447353c9-2da2-4fcb-ba4a-7dd6b94c19c1.png) | ![](https://user-images.githubusercontent.com/11482921/164455669-df384631-baaa-42f8-9150-40f658471558.png) | ![](https://user-images.githubusercontent.com/11482921/164455657-68006bf0-138d-4981-aaca-8aa927d2f78a.png) | ![](https://user-images.githubusercontent.com/11482921/164455664-0342b93e-a62a-4b36-a90e-7118f3f1e45d.png) |
+
+## Inference Speed
+
+### PyTorch
+
+Note that we only report the **model** time, and ignore the IO time.
+
+| GPU | Input Resolution | waifu2x | Real-CUGAN | RealESRGAN-AnimeVideo-v3
+| :---: | :---:         |  :---:        |     :---:      |  :---:      |
+| V100 | 1921 x 1080 | - | 3.4 fps | **10.0** fps |
+| V100 | 1280 x 720 | - | 7.2 fps | **22.6** fps |
+| V100 | 640 x 480 | - | 24.4 fps | **65.9** fps |
+
+### ncnn
+
+- [ ] TODO

docs/anime_comparisons_CN.md

@@ -0,0 +1,68 @@
+# 动漫视频模型比较
+
+[English](anime_comparisons.md) **|** [简体中文](anime_comparisons_CN.md)
+
+## 更新
+
+- 2022/04/24: 发布 **AnimeVideo-v3**. 主要做了以下更新：
+  - **更自然**
+  - **更少瑕疵**
+  - **颜色保持得更好**
+  - **更好的纹理恢复**
+  - **虚化背景处理**
+
+## 比较
+
+我们将 RealESRGAN-AnimeVideo-v3 与以下方法进行了比较。我们的 RealESRGAN-AnimeVideo-v3 可以以更快的推理速度获得更好的结果。
+
+- [waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan). 超参数: `tile=0`, `noiselevel=2`
+- [Real-CUGAN](https://github.com/bilibili/ailab/tree/main/Real-CUGAN): 我们使用了[20220227](https://github.com/bilibili/ailab/releases/tag/Real-CUGAN-add-faster-low-memory-mode)版本, 超参: `cache_mode=0`, `tile=0`, `alpha=1`.
+- 我们的 RealESRGAN-AnimeVideo-v3
+
+## 结果
+
+您可能需要**放大**以比较详细信息, 或者**单击图像**以查看完整尺寸。 请注意下面表格的图片是从原图里裁剪patch并且resize后的结果，您可以从
+[Google Drive](https://drive.google.com/drive/folders/1bc_Hje1Nqop9NDkUvci2VACSjL7HZMRp?usp=sharing) 里下载原始的输入和输出。
+
+**更自然的结果，更好的虚化背景恢复**
+
+| 输入 | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![157083983-bec52c67-9a5e-4eed-afef-01fe6cd2af85_patch](https://user-images.githubusercontent.com/11482921/164452769-5d8cb4f8-1708-42d2-b941-f44a6f136feb.png) | ![](https://user-images.githubusercontent.com/11482921/164452767-c825cdec-f721-4ff1-aef1-fec41f146c4c.png) | ![](https://user-images.githubusercontent.com/11482921/164452755-3be50895-e3d4-432d-a7b9-9085c2a8e771.png) | ![](https://user-images.githubusercontent.com/11482921/164452771-be300656-379a-4323-a755-df8025a8c451.png) |
+|![a0010_patch](https://user-images.githubusercontent.com/11482921/164454047-22eeb493-3fa9-4142-9fc2-6f2a1c074cd5.png) | ![](https://user-images.githubusercontent.com/11482921/164454046-d5e79f8f-00a0-4b55-bc39-295d0d69747a.png) | ![](https://user-images.githubusercontent.com/11482921/164454040-87886b11-9d08-48bd-862f-0d4aed72eb19.png) | ![](https://user-images.githubusercontent.com/11482921/164454055-73dc9f02-286e-4d5c-8f70-c13742e08f42.png) |
+|![00000044_patch](https://user-images.githubusercontent.com/11482921/164451232-bacf64fc-e55a-44db-afbb-6b31ab0f8973.png) | ![](https://user-images.githubusercontent.com/11482921/164451318-f309b61a-75b8-4b74-b5f3-595725f1cf0b.png) | ![](https://user-images.githubusercontent.com/11482921/164451348-994f8a35-adbe-4a4b-9c61-feaa294af06a.png) | ![](https://user-images.githubusercontent.com/11482921/164451361-9b7d376e-6f75-4648-b752-542b44845d1c.png) |
+
+**更少瑕疵，更好的细节纹理**
+
+| 输入 | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![00000053_patch](https://user-images.githubusercontent.com/11482921/164448411-148a7e5c-cfcd-4504-8bc7-e318eb883bb6.png) | ![](https://user-images.githubusercontent.com/11482921/164448633-dfc15224-b6d2-4403-a3c9-4bb819979364.png) | ![](https://user-images.githubusercontent.com/11482921/164448771-0d359509-5293-4d4c-8e3c-86a2a314ea88.png) | ![](https://user-images.githubusercontent.com/11482921/164448848-1a4ff99e-075b-4458-9db7-2c89e8160aa0.png) |
+|![Disney_v4_22_018514_s2_patch](https://user-images.githubusercontent.com/11482921/164451898-83311cdf-bd3e-450f-b9f6-34d7fea3ab79.png) | ![](https://user-images.githubusercontent.com/11482921/164451894-6c56521c-6561-40d6-a3a5-8dde2c167b8a.png) | ![](https://user-images.githubusercontent.com/11482921/164451888-af9b47e3-39dc-4f3e-b0d7-d372d8191e2a.png) | ![](https://user-images.githubusercontent.com/11482921/164451901-31ca4dd4-9847-4baa-8cde-ad50f4053dcf.png) |
+|![Japan_v2_0_007261_s2_patch](https://user-images.githubusercontent.com/11482921/164454578-73c77392-77de-49c5-b03c-c36631723192.png) | ![](https://user-images.githubusercontent.com/11482921/164454574-b1ede5f0-4520-4eaa-8f59-086751a34e62.png) | ![](https://user-images.githubusercontent.com/11482921/164454567-4cb3fdd8-6a2d-4016-85b2-a305a8ff80e4.png) | ![](https://user-images.githubusercontent.com/11482921/164454583-7f243f20-eca3-4500-ac43-eb058a4a101a.png) |
+|![huluxiongdi_2_patch](https://user-images.githubusercontent.com/11482921/164453482-0726c842-337e-40ec-bf6c-f902ee956a8b.png) | ![](https://user-images.githubusercontent.com/11482921/164453480-71d5e091-5bfa-4c77-9c57-4e37f66ca0a3.png) | ![](https://user-images.githubusercontent.com/11482921/164453468-c295d3c9-3661-45f0-9ecd-406a1877f76e.png) | ![](https://user-images.githubusercontent.com/11482921/164453486-3091887c-587c-450e-b6fe-905cb518d57e.png) |
+
+**其他更好的结果**
+
+| 输入 | waifu2x | Real-CUGAN | RealESRGAN<br>AnimeVideo-v3 |
+| :---: | :---:        |     :---:      |  :---:      |
+|![Japan_v2_1_128525_s1_patch](https://user-images.githubusercontent.com/11482921/164454933-67697f7c-b6ef-47dc-bfca-822a78af8acf.png) | ![](https://user-images.githubusercontent.com/11482921/164454931-9450de7c-f0b3-4638-9c1e-0668e0c41ef0.png) | ![](https://user-images.githubusercontent.com/11482921/164454926-ed746976-786d-41c5-8a83-7693cd774c3a.png) | ![](https://user-images.githubusercontent.com/11482921/164454936-8abdf0f0-fb30-40eb-8281-3b46c0bcb9ae.png) |
+|![tianshuqitan_2_patch](https://user-images.githubusercontent.com/11482921/164456948-807c1476-90b6-4507-81da-cb986d01600c.png) | ![](https://user-images.githubusercontent.com/11482921/164456943-25e89de9-d7e5-4f61-a2e1-96786af6ae9e.png) | ![](https://user-images.githubusercontent.com/11482921/164456954-b468c447-59f5-4594-9693-3683e44ba3e6.png) | ![](https://user-images.githubusercontent.com/11482921/164456957-640f910c-3b04-407c-ac20-044d72e19735.png) |
+|![00000051_patch](https://user-images.githubusercontent.com/11482921/164456044-e9a6b3fa-b24e-4eb7-acf9-1f7746551b1e.png) ![00000051_patch](https://user-images.githubusercontent.com/11482921/164456421-b67245b0-767d-4250-9105-80bbe507ecfc.png) | ![](https://user-images.githubusercontent.com/11482921/164456040-85763cf2-cb28-4ba3-abb6-1dbb48c55713.png) ![](https://user-images.githubusercontent.com/11482921/164456419-59cf342e-bc1e-4044-868c-e1090abad313.png) | ![](https://user-images.githubusercontent.com/11482921/164456031-4244bb7b-8649-4e01-86f4-40c2099c5afd.png) ![](https://user-images.githubusercontent.com/11482921/164456411-b6afcbe9-c054-448d-a6df-96d3ba3047f8.png) | ![](https://user-images.githubusercontent.com/11482921/164456035-12e270be-fd52-46d4-b18a-3d3b680731fe.png) ![](https://user-images.githubusercontent.com/11482921/164456417-dcaa8b62-f497-427d-b2d2-f390f1200fb9.png) |
+|![00000099_patch](https://user-images.githubusercontent.com/11482921/164455312-6411b6e1-5823-4131-a4b0-a6be8a9ae89f.png) | ![](https://user-images.githubusercontent.com/11482921/164455310-f2b99646-3a22-47a4-805b-dc451ac86ddb.png) | ![](https://user-images.githubusercontent.com/11482921/164455294-35471b42-2826-4451-b7ec-6de01344954c.png) | ![](https://user-images.githubusercontent.com/11482921/164455305-fa4c9758-564a-4081-8b4e-f11057a0404d.png) |
+|![00000016_patch](https://user-images.githubusercontent.com/11482921/164455672-447353c9-2da2-4fcb-ba4a-7dd6b94c19c1.png) | ![](https://user-images.githubusercontent.com/11482921/164455669-df384631-baaa-42f8-9150-40f658471558.png) | ![](https://user-images.githubusercontent.com/11482921/164455657-68006bf0-138d-4981-aaca-8aa927d2f78a.png) | ![](https://user-images.githubusercontent.com/11482921/164455664-0342b93e-a62a-4b36-a90e-7118f3f1e45d.png) |
+
+## 推理速度比较
+
+### PyTorch
+
+请注意，我们只报告了**模型推理**的时间, 而忽略了读写硬盘的时间.
+
+| GPU | 输入尺寸 | waifu2x | Real-CUGAN | RealESRGAN-AnimeVideo-v3
+| :---: | :---:         |  :---:        |     :---:      |  :---:      |
+| V100 | 1921 x 1080 | - | 3.4 fps | **10.0** fps |
+| V100 | 1280 x 720 | - | 7.2 fps | **22.6** fps |
+| V100 | 640 x 480 | - | 24.4 fps | **65.9** fps |
+
+### ncnn
+
+- [ ] TODO

docs/anime_model.md

@@ -0,0 +1,68 @@
+# Anime Model
+
+:white_check_mark: We add [*RealESRGAN_x4plus_anime_6B.pth*](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth), which is optimized for **anime** images with much smaller model size.
+
+- [How to Use](#how-to-use)
+  - [PyTorch Inference](#pytorch-inference)
+  - [ncnn Executable File](#ncnn-executable-file)
+- [Comparisons with waifu2x](#comparisons-with-waifu2x)
+- [Comparisons with Sliding Bars](#comparisons-with-sliding-bars)
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_1.png">
+</p>
+
+The following is a video comparison with sliding bar. You may need to use the full-screen mode for better visual quality, as the original image is large; otherwise, you may encounter aliasing issue.
+
+<https://user-images.githubusercontent.com/17445847/131535127-613250d4-f754-4e20-9720-2f9608ad0675.mp4>
+
+## How to Use
+
+### PyTorch Inference
+
+Pre-trained models: [RealESRGAN_x4plus_anime_6B](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth)
+
+```bash
+# download model
+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
+```
+
+### ncnn Executable File
+
+Download the latest 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**.
+
+Taking the Windows as example, run:
+
+```bash
+./realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrgan-x4plus-anime
+```
+
+## Comparisons with waifu2x
+
+We compare Real-ESRGAN-anime with [waifu2x](https://github.com/nihui/waifu2x-ncnn-vulkan). We use the `-n 2 -s 4` for waifu2x.
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_1.png">
+</p>
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_2.png">
+</p>
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_3.png">
+</p>
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_4.png">
+</p>
+<p align="center">
+  <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_5.png">
+</p>
+
+## Comparisons with Sliding Bars
+
+The following are video comparisons with sliding bar. You may need to use the full-screen mode for better visual quality, as the original image is large; otherwise, you may encounter aliasing issue.
+
+<https://user-images.githubusercontent.com/17445847/131536647-a2fbf896-b495-4a9f-b1dd-ca7bbc90101a.mp4>
+
+<https://user-images.githubusercontent.com/17445847/131536742-6d9d82b6-9765-4296-a15f-18f9aeaa5465.mp4>

docs/anime_video_model.md

@@ -0,0 +1,136 @@
+# Anime Video Models
+
+:white_check_mark: We add small models that are optimized for anime videos :-)<br>
+More comparisons can be found in [anime_comparisons.md](anime_comparisons.md)
+
+- [How to Use](#how-to-use)
+- [PyTorch Inference](#pytorch-inference)
+- [ncnn Executable File](#ncnn-executable-file)
+  - [Step 1: Use ffmpeg to extract frames from video](#step-1-use-ffmpeg-to-extract-frames-from-video)
+  - [Step 2: Inference with Real-ESRGAN executable file](#step-2-inference-with-real-esrgan-executable-file)
+  - [Step 3: Merge the enhanced frames back into a video](#step-3-merge-the-enhanced-frames-back-into-a-video)
+- [More Demos](#more-demos)
+
+| Models                                                                                                                             | Scale | Description                    |
+| ---------------------------------------------------------------------------------------------------------------------------------- | :---- | :----------------------------- |
+| [realesr-animevideov3](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth) | X4 <sup>1</sup>   | Anime video model with XS size |
+
+Note: <br>
+<sup>1</sup> This model can also be used for X1, X2, X3.
+
+---
+
+The following are some demos (best view in the full screen mode).
+
+<https://user-images.githubusercontent.com/17445847/145706977-98bc64a4-af27-481c-8abe-c475e15db7ff.MP4>
+
+<https://user-images.githubusercontent.com/17445847/145707055-6a4b79cb-3d9d-477f-8610-c6be43797133.MP4>
+
+<https://user-images.githubusercontent.com/17445847/145783523-f4553729-9f03-44a8-a7cc-782aadf67b50.MP4>
+
+## How to Use
+
+### PyTorch Inference
+
+```bash
+# download model
+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)
+CUDA_VISIBLE_DEVICES=0 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2 --num_process_per_gpu 2
+# multi gpu and multi process inference
+CUDA_VISIBLE_DEVICES=0,1,2,3 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2 --num_process_per_gpu 2
+```
+
+```console
+Usage:
+--num_process_per_gpu    The total number of process is num_gpu * num_process_per_gpu. The bottleneck of
+                         the program lies on the IO, so the GPUs are usually not fully utilized. To alleviate
+                         this issue, you can use multi-processing by setting this parameter. As long as it
+                         does not exceed the CUDA memory
+--extract_frame_first    If you encounter ffmpeg error when using multi-processing, you can turn this option on.
+```
+
+### NCNN Executable File
+
+#### Step 1: Use ffmpeg to extract frames from video
+
+```bash
+ffmpeg -i onepiece_demo.mp4 -qscale:v 1 -qmin 1 -qmax 1 -vsync 0 tmp_frames/frame%08d.png
+```
+
+- Remember to create the folder `tmp_frames` ahead
+
+#### Step 2: Inference with Real-ESRGAN executable file
+
+1. Download the latest 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**
+
+1. Taking the Windows as example, run:
+
+    ```bash
+    ./realesrgan-ncnn-vulkan.exe -i tmp_frames -o out_frames -n realesr-animevideov3 -s 2 -f jpg
+    ```
+
+    - Remember to create the folder `out_frames` ahead
+
+#### Step 3: Merge the enhanced frames back into a video
+
+1. First obtain fps from input videos by
+
+    ```bash
+    ffmpeg -i onepiece_demo.mp4
+    ```
+
+    ```console
+    Usage:
+    -i                   input video path
+    ```
+
+    You will get the output similar to the following screenshot.
+
+    <p align="center">
+        <img src="https://user-images.githubusercontent.com/17445847/145710145-c4f3accf-b82f-4307-9f20-3803a2c73f57.png">
+    </p>
+
+2. Merge frames
+
+    ```bash
+    ffmpeg -r 23.98 -i out_frames/frame%08d.jpg -c:v libx264 -r 23.98 -pix_fmt yuv420p output.mp4
+    ```
+
+    ```console
+    Usage:
+    -i                   input video path
+    -c:v                 video encoder (usually we use libx264)
+    -r                   fps, remember to modify it to meet your needs
+    -pix_fmt             pixel format in video
+    ```
+
+    If you also want to copy audio from the input videos, run:
+
+     ```bash
+    ffmpeg -r 23.98 -i out_frames/frame%08d.jpg -i onepiece_demo.mp4 -map 0:v:0 -map 1:a:0 -c:a copy -c:v libx264 -r 23.98 -pix_fmt yuv420p output_w_audio.mp4
+    ```
+
+    ```console
+    Usage:
+    -i                   input video path, here we use two input streams
+    -c:v                 video encoder (usually we use libx264)
+    -r                   fps, remember to modify it to meet your needs
+    -pix_fmt             pixel format in video
+    ```
+
+## More Demos
+
+- Input video for One Piece:
+
+    <https://user-images.githubusercontent.com/17445847/145706822-0e83d9c4-78ef-40ee-b2a4-d8b8c3692d17.mp4>
+
+- Out video for One Piece
+
+    <https://user-images.githubusercontent.com/17445847/164960481-759658cf-fcb8-480c-b888-cecb606e8744.mp4>
+
+**More comparisons**
+
+<https://user-images.githubusercontent.com/17445847/145707458-04a5e9b9-2edd-4d1f-b400-380a72e5f5e6.MP4>

docs/feedback.md

@@ -0,0 +1,11 @@
+# Feedback 反馈
+
+## 动漫插画模型
+
+1. 视频处理不了: 目前的模型，不是针对视频的，所以视频效果很很不好。我们在探究针对视频的模型了
+1. 景深虚化有问题: 现在的模型把一些景深 和 特意的虚化 都复原了，感觉不好。这个后面我们会考虑把这个信息结合进入。一个简单的做法是识别景深和虚化，然后作为条件告诉神经网络，哪些地方复原强一些，哪些地方复原要弱一些
+1. 不可以调节: 像 Waifu2X 可以调节。可以根据自己的喜好，做调整，但是 Real-ESRGAN-anime 并不可以。导致有些恢复效果过了
+1. 把原来的风格改变了: 不同的动漫插画都有自己的风格，现在的 Real-ESRGAN-anime 倾向于恢复成一种风格（这是受到训练数据集影响的）。风格是动漫很重要的一个要素，所以要尽可能保持
+1. 模型太大: 目前的模型处理太慢，能够更快。这个我们有相关的工作在探究，希望能够尽快有结果，并应用到 Real-ESRGAN 这一系列的模型上
+
+Thanks for the [detailed and valuable feedbacks/suggestions](https://github.com/xinntao/Real-ESRGAN/issues/131) by [2ji3150](https://github.com/2ji3150).

docs/model_zoo.md

@@ -0,0 +1,49 @@
+# :european_castle: Model Zoo
+
+- [For General Images](#for-general-images)
+- [For Anime Images](#for-anime-images)
+- [For Anime Videos](#for-anime-videos)
+
+---
+
+## For General Images
+
+| Models                                                                                                                          | Scale | Description                                  |
+| ------------------------------------------------------------------------------------------------------------------------------- | :---- | :------------------------------------------- |
+| [RealESRGAN_x4plus](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)                      | X4    | X4 model for general images                  |
+| [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.
+
+| Models                                                                                                                 | Corresponding model |
+| ---------------------------------------------------------------------------------------------------------------------- | :------------------ |
+| [RealESRGAN_x4plus_netD](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth) | RealESRGAN_x4plus   |
+| [RealESRGAN_x2plus_netD](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x2plus_netD.pth) | RealESRGAN_x2plus   |
+
+## For Anime Images / Illustrations
+
+| Models                                                                                                                         | Scale | Description                                                 |
+| ------------------------------------------------------------------------------------------------------------------------------ | :---- | :---------------------------------------------------------- |
+| [RealESRGAN_x4plus_anime_6B](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth) | X4    | Optimized for anime images; 6 RRDB blocks (smaller network) |
+
+The following models are **discriminators**, which are usually used for fine-tuning.
+
+| Models                                                                                                                                   | Corresponding model        |
+| ---------------------------------------------------------------------------------------------------------------------------------------- | :------------------------- |
+| [RealESRGAN_x4plus_anime_6B_netD](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B_netD.pth) | RealESRGAN_x4plus_anime_6B |
+
+## For Animation Videos
+
+| Models                                                                                                                             | Scale | Description                    |
+| ---------------------------------------------------------------------------------------------------------------------------------- | :---- | :----------------------------- |
+| [realesr-animevideov3](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth) | X4<sup>1</sup>    | Anime video model with XS size |
+
+Note: <br>
+<sup>1</sup> This model can also be used for X1, X2, X3.
+
+The following models are **discriminators**, which are usually used for fine-tuning.
+
+TODO

docs/ncnn_conversion.md

@@ -0,0 +1,11 @@
+# Instructions on converting to NCNN models
+
+1. Convert to onnx model with `scripts/pytorch2onnx.py`. Remember to modify codes accordingly
+1. Convert onnx model to ncnn model
+    1. `cd ncnn-master\ncnn\build\tools\onnx`
+    1. `onnx2ncnn.exe realesrgan-x4.onnx realesrgan-x4-raw.param realesrgan-x4-raw.bin`
+1. Optimize ncnn model
+    1. fp16 mode
+        1. `cd ncnn-master\ncnn\build\tools`
+        1. `ncnnoptimize.exe realesrgan-x4-raw.param realesrgan-x4-raw.bin realesrgan-x4.param realesrgan-x4.bin 1`
+1. Modify the blob name in `realesrgan-x4.param`: `data` and `output`