ci(*): upgrade GitHub Actions for Node 24 compatibility (#1454)

Signed-off-by: Salman Muin Kayser Chishti <13schishti@gmail.com>

.github/workflows/build.yml

@@ -26,7 +26,7 @@ jobs:
       DEBIAN_FRONTEND: noninteractive
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -58,7 +58,7 @@ jobs:
           cmake --build /tmp/build --config Debug --target install
 
       - name: Upload artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: video2x-nightly-linux-amd64
           path: /tmp/install
@@ -67,14 +67,14 @@ jobs:
     runs-on: windows-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           submodules: recursive
 
       - name: Install Vulkan SDK
-        uses: humbletim/setup-vulkan-sdk@v1.2.0
+        uses: humbletim/setup-vulkan-sdk@v1.2.1
         with:
-          vulkan-query-version: 1.3.204.0
+          vulkan-query-version: 1.4.304.1
           vulkan-components: Vulkan-Headers, Vulkan-Loader, Glslang, SPIRV-Tools, SPIRV-Headers
           vulkan-use-cache: true
 
@@ -103,7 +103,7 @@ jobs:
           cmake --build build --config Debug --parallel --target install
 
       - name: Upload artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: video2x-nightly-windows-amd64
           path: build/video2x_install
@@ -112,9 +112,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
-      - uses: mr-smithers-excellent/docker-build-push@v5
+      - uses: mr-smithers-excellent/docker-build-push@v6
         name: Build the Docker image
         with:
           registry: ghcr.io
@@ -127,7 +127,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Install dependencies
         run: |
@@ -173,7 +173,7 @@ jobs:
             --output appimage
 
       - name: Upload artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: Video2X-x86_64.AppImage
           path: Video2X-x86_64.AppImage

.github/workflows/docs.yml

@@ -25,7 +25,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Install mdBook
         run: |
@@ -40,7 +40,7 @@ jobs:
         uses: actions/configure-pages@v5
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v3
+        uses: actions/upload-pages-artifact@v4
         with:
           path: "build/docs/book"
 

.github/workflows/release.yml

@@ -31,7 +31,7 @@ jobs:
       DEBIAN_FRONTEND: noninteractive
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           submodules: recursive
 
@@ -63,7 +63,7 @@ jobs:
           dpkg-deb --build build/video2x-linux-ubuntu-2404-amd64
 
       - name: Upload artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: video2x-linux-ubuntu-2404-amd64
           path: build/video2x-linux-ubuntu-2404-amd64.deb
@@ -77,14 +77,14 @@ jobs:
     runs-on: windows-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           submodules: recursive
 
       - name: Install Vulkan SDK
-        uses: humbletim/setup-vulkan-sdk@v1.2.0
+        uses: humbletim/setup-vulkan-sdk@v1.2.1
         with:
-          vulkan-query-version: 1.3.204.0
+          vulkan-query-version: 1.4.304.1
           vulkan-components: Vulkan-Headers, Vulkan-Loader, Glslang, SPIRV-Tools, SPIRV-Headers
           vulkan-use-cache: true
 
@@ -117,7 +117,7 @@ jobs:
           Compress-Archive -Path build/video2x_install/* -DestinationPath build/video2x-windows-amd64.zip
 
       - name: Upload artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: video2x-windows-amd64
           path: build/video2x-windows-amd64.zip
@@ -129,9 +129,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
-      - uses: mr-smithers-excellent/docker-build-push@v5
+      - uses: mr-smithers-excellent/docker-build-push@v6
         name: Build & push the Docker image
         with:
           registry: ghcr.io
@@ -153,7 +153,7 @@ jobs:
     #   upload_url: ${{ steps.create_release.outputs.upload_url }}
     steps:
       # - name: Download artifacts
-      #   uses: actions/download-artifact@v4
+      #   uses: actions/download-artifact@v7
 
       - name: Create release
         id: create_release

CHANGELOG.md

@@ -5,12 +5,24 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Added
+
+- Option to recalculate the PTS.
+- Real-ESRGAN models `realesr-general-x4v3` and `realesr-general-wdn-x4v3` (#1319).
+- (Video2X Qt6) Korean translation.
+
+### Changed
+
+- Separate audio and subtitle stream copying options.
+
 ## [6.4.0] - 2025-01-24
 
 ### Added
 
 - Multi-versioning to critical functions to enhance performance in generic architecture builds.
-- RIFE models v4.25 and v4.26 (#1304).
+- RIFE models `v4.25` and `v4.26` (#1304).
 - Support for processing videos without PTS information (#1278).
 - The feature to copy input streams' metadata to the output streams (#1282).
 - (Video2X Qt6) German translation (#1279).

README.md

@@ -27,31 +27,46 @@ Version 6.0.0 is a complete rewrite of this project in C/C++. It:
 - genuinely works this time, with much less hassle compared to the 5.0.0 beta;
 - is blazing fast, thanks to the new optimized pipeline and the efficiency of C/C++;
 - is cross-platform, available now for both Windows and Linux;
-- offers significantly better output quality with Anime4K v4, RealESRGAN, RealCUGAN, and RIFE;
+- offers significantly better output quality with Anime4K v4, Real-ESRGAN, Real-CUGAN, and RIFE;
 - supports two modes: filtering (upscaling) and frame interpolation;
 - supports Anime4K v4 and all custom MPV-compatible GLSL shaders;
-- supports RealESRGAN, RealCUGAN, and RIFE (all models) via ncnn and Vulkan;
+- supports Real-ESRGAN, Real-CUGAN, and RIFE (all models) via ncnn and Vulkan;
 - requires zero additional disk space during processing, just space for the final output.
 
 </details>
 
-![6.3.0-screenshot](https://github.com/user-attachments/assets/c5442f84-5ffc-4476-915f-a0fc188a2cb3)
+![6.4.0-screenshot](https://github.com/user-attachments/assets/9b1cc8a7-2903-4d2c-80a2-8d81f007e45b)
+
+## 🖥️ Hardware Requirements
+
+Your system must meet the minimum hardware requirements below to run Video2X.
+
+- **CPU**
+  - The precompiled binaries require CPUs with AVX2 support.
+  - **Intel**: Haswell (Q2 2013) or newer
+  - **AMD**: Excavator (Q2 2015) or newer
+- **GPU**
+  - The GPU must support Vulkan.
+  - **NVIDIA**: Kepler (GTX 600 series, Q2 2012) or newer
+  - **AMD**: GCN 1.0 (Radeon HD 7000 series, Q1 2012) or newer
+  - **Intel**: HD Graphics 4000 (Q2 2012) or newer
 
 ## [🪟 Install on Windows](https://docs.video2x.org/installing/windows-qt6.html)
 
-**[Download the Latest Windows Installer Executable (6.3.1)](https://github.com/k4yt3x/video2x/releases/download/6.3.1/video2x-qt6-windows-amd64-installer.exe)**
+**[Download the Latest Windows Installer Executable (6.4.0)](https://github.com/k4yt3x/video2x/releases/download/6.4.0/video2x-qt6-windows-amd64-installer.exe)**
 
-You can download the latest Windows release on the [releases page](https://github.com/k4yt3x/video2x/releases/latest). For basic GUI usage, refer to the [documentation](https://docs.video2x.org/running/desktop.html). If you're unable to download directly from GitHub, try the [mirror site](https://files.k4yt3x.com/Projects/Video2X). The GUI currently supports the following languages:
+You can download the latest Windows release on the [releases page](https://github.com/k4yt3x/video2x/releases/latest). For basic GUI usage, refer to the [documentation](https://docs.video2x.org/running/desktop.html). If you're unable to download directly from GitHub, try the [mirror site](https://files.k4yt3x.com). The GUI currently supports the following languages:
 
 - English (United States)
 - 简体中文（中国）
 - 日本語（日本）
 - Português (Portugal)
 - Français (France)
+- Deutsch (Deutschland)
 
 ## [🐧 Install on Linux](https://docs.video2x.org/installing/linux.html)
 
-Video2X packages are available for the Linux distros listed below. If you'd like to build it from source code, refer to the [PKGBUILD](packaging/arch/PKGBUILD) file for a general overview of the required dependencies and commands. If a package is not available for your distro and you prefer not to compile the program from source code, consider using the container image outlined in the next section.
+Video2X packages are available for the Linux distros listed below. A universal AppImage is also available for other distros. If you'd like to build it from source code, refer to the [PKGBUILD](packaging/arch/PKGBUILD) file for a general overview of the required dependencies and commands.
 
 - Arch Linux: AUR packages, maintained by [@K4YT3X](https://github.com/k4yt3x).
   - [aur/video2x](https://aur.archlinux.org/packages/video2x)
@@ -61,8 +76,9 @@ Video2X packages are available for the Linux distros listed below. If you'd like
 - Arch Linux (Chinese Mainland): archlinuxcn packages, maintained by [@Integral-Tech](https://github.com/Integral-Tech).
   - [archlinuxcn/video2x](https://github.com/archlinuxcn/repo/tree/master/archlinuxcn/video2x)
   - [archlinuxcn/video2x-git](https://github.com/archlinuxcn/repo/tree/master/archlinuxcn/video2x-git)
+  - [archlinuxcn/video2x-qt6](https://github.com/archlinuxcn/repo/tree/master/archlinuxcn/video2x-qt6)
   - [archlinuxcn/video2x-qt6-git](https://github.com/archlinuxcn/repo/tree/master/archlinuxcn/video2x-qt6-git)
-- Ubuntu 24.04: `video2x-linux-ubuntu2404-amd64.deb` on the [releases page](https://github.com/k4yt3x/video2x/releases/latest).
+- Other distros: `Video2X-x86_64.AppImage` on the [releases page](https://github.com/k4yt3x/video2x/releases/latest).
 
 ## [📦 Container Image](https://docs.video2x.org/running/container.html)
 
@@ -99,11 +115,11 @@ _Upscale demo: Spirited Away's movie trailer_
 
 The following clip can be used to test if your setup works properly. This is also the standard clip used for running performance benchmarks.
 
-- [Standard Test Clip (240P)](https://files.k4yt3x.com/Resources/Videos/standard-test.mp4) 4.54 MiB
-- [Real-CUGAN Upscaled Sample (1704P)](https://files.k4yt3x.com/Resources/Videos/standard-realcugan.mp4) 3.5 MiB
-- [Real-ESRGAN Upscaled Sample (1704P)](https://files.k4yt3x.com/Resources/Videos/standard-realesrgan.mp4) 3.1 MiB
-- [waifu2x Upscaled Sample (1080P)](https://files.k4yt3x.com/Resources/Videos/standard-waifu2x.mp4) 4.54 MiB
-- [Ground Truth (1080P)](https://files.k4yt3x.com/Resources/Videos/standard-original.mp4) 22.2 MiB
+- [Standard Test Clip (240P)](https://files.k4yt3x.com/resources/videos/standard-test.mp4) 4.54 MiB
+- [Real-CUGAN Upscaled Sample (1704P)](https://files.k4yt3x.com/resources/videos/standard-realcugan.mp4) 3.5 MiB
+- [Real-ESRGAN Upscaled Sample (1704P)](https://files.k4yt3x.com/resources/videos/standard-realesrgan.mp4) 3.1 MiB
+- [waifu2x Upscaled Sample (1080P)](https://files.k4yt3x.com/resources/videos/standard-waifu2x.mp4) 4.54 MiB
+- [Ground Truth (1080P)](https://files.k4yt3x.com/resources/videos/standard-original.mp4) 22.2 MiB
 
 The original clip came from the anime "さくら荘のペットな彼女."\
 Copyright of this clip belongs to 株式会社アニプレックス.

docs/book/src/building/linux.md

@@ -40,14 +40,17 @@ The built binaries will be located in the `build` directory.
 Ubuntu users can use the `.justfile` to build the project automatically. The `ubuntu2404` and `ubuntu2204` targets are available for Ubuntu 24.04 and 22.04, respectively. `just` will automatically install the required dependencies, build the project, and package it into a `.deb` package file. It is recommended to perform the build in a container to ensure the environment's consistency and to avoid leaving extra build packages on your system.
 
 ```bash
-# just needs to be installed manually
-sudo apt-get update && sudo apt-get install just
+# The version of `just` in the Ubuntu repository is outdated
+# We need to compile and install `just` manually
+sudo apt-get update && sudo apt-get install cargo
+cargo install just
 
 # Clone the repository
 git clone --recurse-submodules https://github.com/k4yt3x/video2x.git
 cd video2x
 
 # Build the project
+# Before running the command, ensure ~/.cargo/bin is in your PATH
 just ubuntu2404
 ```
 

docs/book/src/installing/linux.md

@@ -12,12 +12,9 @@ Video2X packages are available for the Linux distros listed below. If you'd like
 - Chinese Mainland: archlinuxcn packages, maintained by [@Integral-Tech](https://github.com/Integral-Tech).
   - [archlinuxcn/video2x](https://github.com/archlinuxcn/repo/tree/master/archlinuxcn/video2x)
   - [archlinuxcn/video2x-git](https://github.com/archlinuxcn/repo/tree/master/archlinuxcn/video2x-git)
+  - [archlinuxcn/video2x-qt6](https://github.com/archlinuxcn/repo/tree/master/archlinuxcn/video2x-qt6)
   - [archlinuxcn/video2x-qt6-git](https://github.com/archlinuxcn/repo/tree/master/archlinuxcn/video2x-qt6-git)
 
-## Ubuntu
+## Other Distros
 
-Ubuntu users can download the `.deb` packages from the [releases page](https://github.com/k4yt3x/video2x/releases/latest). Install the package with the APT package manager:
-
-```bash
-sudo apt-get install ./video2x-linux-ubuntu2404-amd64.deb
-```
+Users of other distros can download and use the AppImage from the [releases page](https://github.com/k4yt3x/video2x/releases/latest).

docs/book/src/running/command-line.md

@@ -9,27 +9,27 @@ This page does not cover all the options available. For help with more options a
 Use the following command to upscale a video by 4x with RealESRGAN:
 
 ```bash
-video2x -i input.mp4 -o output.mp4 -f realesrgan -r 4 -m realesr-animevideov3
+video2x -i input.mp4 -o output.mp4 -p realesrgan -s 4 --realesrgan-model realesr-animevideov3
 ```
 
 Use the following command to upscale a video to with libplacebo + Anime4Kv4 Mode A+A:
 
 ```bash
-video2x -i input.mp4 -o output.mp4 -f libplacebo -s anime4k-v4-a+a -w 3840 -h 2160
+video2x -i input.mp4 -o output.mp4 -w 3840 -h 2160 -p libplacebo --libplacebo-shader anime4k-v4-a+a
 ```
 
 ## Advanced
 
-It is possible to specify custom MPV-compatible GLSL shader files with the `--shader, -s` argument:
+It is possible to specify custom MPV-compatible GLSL shader files with the `--libplacebo-shader` argument:
 
 ```bash
-video2x -i input.mp4 -o output.mp4 -f libplacebo -s path/to/custom/shader.glsl -w 3840 -h 2160
+video2x -i input.mp4 -o output.mp4 -p libplacebo -w 3840 -h 2160 --libplacebo-shader path/to/custom/shader.glsl
 ```
 
 List the available GPUs with `--list-gpus, -l`:
 
 ```bash
-$video2x --list-gpus
+$ video2x --list-gpus
 0. NVIDIA RTX A6000
         Type: Discrete GPU
         Vulkan API Version: 1.3.289
@@ -39,11 +39,66 @@ $video2x --list-gpus
 Select which GPU to use with the `--gpu, -g` argument:
 
 ```bash
-video2x -i input.mp4 -o output.mp4 -f realesrgan -r 4 -m realesr-animevideov3 -g 1
+video2x -i input.mp4 -o output.mp4 -p realesrgan -s 4 --realesrgan-model realesr-animevideov3 -g 1
 ```
 
-Specify arbitrary extra FFmepg encoder options with the `--extra-encoder-options, -e` argument:
+Specify arbitrary extra FFmpeg encoder options with the `--extra-encoder-options, -e` argument:
 
 ```bash
-video2x -i input.mkv -o output.mkv -f realesrgan -m realesrgan-plus -r 4 -c libx264rgb -e crf=17 -e preset=veryslow -e tune=film
+video2x -i input.mkv -o output.mkv -p realesrgan --realesrgan-model realesrgan-plus -s 4 -c libx264rgb -e crf=17 -e preset=veryslow -e tune=film
+```
+
+## Encoder Options
+
+Video2X uses FFmpeg's C libraries to encode videos. Encoder options are specified in two ways:
+
+- **Common options** shared by all encoders are stored in a [`AVCodecContext`](https://ffmpeg.org/doxygen/trunk/structAVCodecContext.html) struct. Below are some options set through `AVCodecContext`:
+  - Codec
+  - Pixel format
+  - Bitrate
+  - Keyframe interval
+  - Minimum and maximum quantizer
+  - GOP size
+- **Encoder-specific** options are stored in [`AVOption`](https://ffmpeg.org/doxygen/trunk/structAVOption.html) structs and set with the [`av_opt_set`](https://ffmpeg.org/doxygen/trunk/group__opt__set__funcs.html#ga5fd4b92bdf4f392a2847f711676a7537) function. Below are some encoder-specific options for `libx264`:
+  - CRF
+  - Preset
+  - Tune
+  - Profile
+
+Common options can only be set through Video2X's command line arguments. You can run `video2x --help` and see the `Encoder options` section to see the supported options.
+
+You can specify encoder-specific options in Video2X using the `--extra-encoder-option` (`-e`) argument. To view the available options for a particular codec, run:
+
+```bash
+ffmpeg -h encoder=$ENCODER
+```
+
+For example, to view the available options for `libx264`, run:
+
+```console
+$ ffmpeg -h encoder=libx264
+Encoder libx264 [libx264 H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10]:
+    General capabilities: dr1 delay threads
+    Threading capabilities: other
+    Supported pixel formats: yuv420p yuvj420p yuv422p yuvj422p yuv444p yuvj444p nv12 nv16 nv21 yuv420p10le yuv422p10le yuv444p10le nv20le gray gray10le
+libx264 AVOptions:
+  -preset            <string>     E..V....... Set the encoding preset (cf. x264 --fullhelp) (default "medium")
+  -tune              <string>     E..V....... Tune the encoding params (cf. x264 --fullhelp)
+  -profile           <string>     E..V....... Set profile restrictions (cf. x264 --fullhelp)
+  -fastfirstpass     <boolean>    E..V....... Use fast settings when encoding first pass (default true)
+  -level             <string>     E..V....... Specify level (as defined by Annex A)
+  -passlogfile       <string>     E..V....... Filename for 2 pass stats
+  -wpredp            <string>     E..V....... Weighted prediction for P-frames
+  -a53cc             <boolean>    E..V....... Use A53 Closed Captions (if available) (default true)
+  -x264opts          <string>     E..V....... x264 options
+  -crf               <float>      E..V....... Select the quality for constant quality mode (from -1 to FLT_MAX) (default -1)
+  -crf_max           <float>      E..V....... In CRF mode, prevents VBV from lowering quality beyond this point. (from -1 to FLT_MAX) (default -1)
+  -qp                <int>        E..V....... Constant quantization parameter rate control method (from -1 to INT_MAX) (default -1)
+...
+```
+
+You can then set the encoder-specific options with the `-e` argument. The `-e` argument can be used multiple times to set multiple options. For example, the following arguments set the CRF to 17, the preset to `veryslow`, and the tune to `film` for `libx264`:
+
+```console
+-e crf=17 -e preset=veryslow -e tune=film
 ```

docs/book/src/running/container.md

@@ -17,7 +17,7 @@ This section documents how to upscale a video. Replace `$TAG` with an appropriat
 Make sure your host has the proper GPU and Vulkan libraries and drivers, then use the following command to launch the container:
 
 ```shell
-docker run --gpus all -it --rm -v $PWD/data:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -f realesrgan -r 4 -m realesr-animevideov3
+docker run --gpus all -it --rm -v $PWD/data:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -p realesrgan -s 4 --realesrgan-model realesr-animevideov3
 ```
 
 ### NVIDIA GPUs
@@ -33,19 +33,19 @@ In addition to installing the proper drivers on your host, `nvidia-docker2` (NVI
 Once all the prerequisites are installed, you can launch the container:
 
 ```shell
-docker run --gpus all -it --rm -v $PWD:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -f realesrgan -r 4 -m realesr-animevideov3
+docker run --gpus all -it --rm -v $PWD:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -p realesrgan -s 4 --realesrgan-model realesr-animevideov3
 ```
 
 Depending on the version of your nvidia-docker and some other mysterious factors, you can also try setting `no-cgroups = true` in `/etc/nvidia-container-runtime/config.toml` and adding the NVIDIA devices into the container if the command above doesn't work:
 
 ```shell
-docker run --gpus all --device=/dev/nvidia0 --device=/dev/nvidiactl --runtime nvidia -it --rm -v $PWD:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -f realesrgan -r 4 -m realesr-animevideov3
+docker run --gpus all --device=/dev/nvidia0 --device=/dev/nvidiactl --runtime nvidia -it --rm -v $PWD:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -p realesrgan -s 4 --realesrgan-model realesr-animevideov3
 ```
 
 If you are still getting a `vkEnumeratePhysicalDevices failed -3` error at this point, try adding the `--privileged` flag to give the container the same level of permissions as the host:
 
 ```shell
-docker run --gpus all --privileged -it --rm -v $PWD:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -f realesrgan -r 4 -m realesr-animevideov3
+docker run --gpus all --privileged -it --rm -v $PWD:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -p realesrgan -s 4 --realesrgan-model realesr-animevideov3
 ```
 
 ### Intel GPUs
@@ -53,5 +53,5 @@ docker run --gpus all --privileged -it --rm -v $PWD:/host ghcr.io/k4yt3x/video2x
 Similar to NVIDIA GPUs, you can add `--gpus all` or `--device /dev/dri` to pass the GPU into the container. Adding `--privileged` might help with the performance (thanks @NukeninDark).
 
 ```shell
-docker run --gpus all --privileged -it --rm -v $PWD:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -f realesrgan -r 4 -m realesr-animevideov3
+docker run --gpus all --privileged -it --rm -v $PWD:/host ghcr.io/k4yt3x/video2x:$TAG -i standard-test.mp4 -o output.mp4 -p realesrgan -s 4 --realesrgan-model realesr-animevideov3
 ```

include/libvideo2x/encoder.h

@@ -17,7 +17,9 @@ namespace encoder {
 struct EncoderConfig {
     // Non-AVCodecContext options
     std::string codec = "libx264";
-    bool copy_streams = true;
+    bool recalculate_pts = true;
+    bool copy_audio_streams = true;
+    bool copy_subtitle_streams = true;
 
     // Basic video options
     AVPixelFormat pix_fmt = AV_PIX_FMT_NONE;
@@ -72,6 +74,7 @@ class Encoder {
     int get_output_video_stream_index() const;
 
    private:
+    EncoderConfig enc_cfg_;
     AVFormatContext* ofmt_ctx_;
     AVCodecContext* enc_ctx_;
     int out_vstream_idx_;

include/libvideo2x/filter_realesrgan.h

@@ -18,6 +18,7 @@ class FilterRealesrgan : public Filter {
         int gpuid = 0,
         bool tta_mode = false,
         int scaling_factor = 4,
+        int noise_level = 0,
         const fsutils::StringType model_name = STR("realesr-animevideov3")
     );
 
@@ -47,6 +48,7 @@ class FilterRealesrgan : public Filter {
     int gpuid_;
     bool tta_mode_;
     int scaling_factor_;
+    int noise_level_;
     const fsutils::StringType model_name_;
     AVRational in_time_base_;
     AVRational out_time_base_;

models/realesrgan/realesr-generalv3-wdn-x4.param

@@ -0,0 +1,75 @@
+7767517
+73 74
+Input            data                     0 1 data
+Split            splitncnn_input0         1 2 data data_splitncnn_0 data_splitncnn_1
+Convolution      /Conv                    1 1 data_splitncnn_1 /Conv_output_0 0=64 1=3 4=1 5=1 6=1728
+PReLU            /PRelu                   1 1 /Conv_output_0 /PRelu_output_0 0=64
+Convolution      /Conv_1                  1 1 /PRelu_output_0 /Conv_1_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_1                 1 1 /Conv_1_output_0 /PRelu_1_output_0 0=64
+Convolution      /Conv_2                  1 1 /PRelu_1_output_0 /Conv_2_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_2                 1 1 /Conv_2_output_0 /PRelu_2_output_0 0=64
+Convolution      /Conv_3                  1 1 /PRelu_2_output_0 /Conv_3_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_3                 1 1 /Conv_3_output_0 /PRelu_3_output_0 0=64
+Convolution      /Conv_4                  1 1 /PRelu_3_output_0 /Conv_4_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_4                 1 1 /Conv_4_output_0 /PRelu_4_output_0 0=64
+Convolution      /Conv_5                  1 1 /PRelu_4_output_0 /Conv_5_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_5                 1 1 /Conv_5_output_0 /PRelu_5_output_0 0=64
+Convolution      /Conv_6                  1 1 /PRelu_5_output_0 /Conv_6_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_6                 1 1 /Conv_6_output_0 /PRelu_6_output_0 0=64
+Convolution      /Conv_7                  1 1 /PRelu_6_output_0 /Conv_7_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_7                 1 1 /Conv_7_output_0 /PRelu_7_output_0 0=64
+Convolution      /Conv_8                  1 1 /PRelu_7_output_0 /Conv_8_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_8                 1 1 /Conv_8_output_0 /PRelu_8_output_0 0=64
+Convolution      /Conv_9                  1 1 /PRelu_8_output_0 /Conv_9_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_9                 1 1 /Conv_9_output_0 /PRelu_9_output_0 0=64
+Convolution      /Conv_10                 1 1 /PRelu_9_output_0 /Conv_10_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_10                1 1 /Conv_10_output_0 /PRelu_10_output_0 0=64
+Convolution      /Conv_11                 1 1 /PRelu_10_output_0 /Conv_11_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_11                1 1 /Conv_11_output_0 /PRelu_11_output_0 0=64
+Convolution      /Conv_12                 1 1 /PRelu_11_output_0 /Conv_12_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_12                1 1 /Conv_12_output_0 /PRelu_12_output_0 0=64
+Convolution      /Conv_13                 1 1 /PRelu_12_output_0 /Conv_13_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_13                1 1 /Conv_13_output_0 /PRelu_13_output_0 0=64
+Convolution      /Conv_14                 1 1 /PRelu_13_output_0 /Conv_14_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_14                1 1 /Conv_14_output_0 /PRelu_14_output_0 0=64
+Convolution      /Conv_15                 1 1 /PRelu_14_output_0 /Conv_15_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_15                1 1 /Conv_15_output_0 /PRelu_15_output_0 0=64
+Convolution      /Conv_16                 1 1 /PRelu_15_output_0 /Conv_16_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_16                1 1 /Conv_16_output_0 /PRelu_16_output_0 0=64
+Convolution      /Conv_17                 1 1 /PRelu_16_output_0 /Conv_17_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_17                1 1 /Conv_17_output_0 /PRelu_17_output_0 0=64
+Convolution      /Conv_18                 1 1 /PRelu_17_output_0 /Conv_18_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_18                1 1 /Conv_18_output_0 /PRelu_18_output_0 0=64
+Convolution      /Conv_19                 1 1 /PRelu_18_output_0 /Conv_19_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_19                1 1 /Conv_19_output_0 /PRelu_19_output_0 0=64
+Convolution      /Conv_20                 1 1 /PRelu_19_output_0 /Conv_20_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_20                1 1 /Conv_20_output_0 /PRelu_20_output_0 0=64
+Convolution      /Conv_21                 1 1 /PRelu_20_output_0 /Conv_21_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_21                1 1 /Conv_21_output_0 /PRelu_21_output_0 0=64
+Convolution      /Conv_22                 1 1 /PRelu_21_output_0 /Conv_22_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_22                1 1 /Conv_22_output_0 /PRelu_22_output_0 0=64
+Convolution      /Conv_23                 1 1 /PRelu_22_output_0 /Conv_23_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_23                1 1 /Conv_23_output_0 /PRelu_23_output_0 0=64
+Convolution      /Conv_24                 1 1 /PRelu_23_output_0 /Conv_24_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_24                1 1 /Conv_24_output_0 /PRelu_24_output_0 0=64
+Convolution      /Conv_25                 1 1 /PRelu_24_output_0 /Conv_25_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_25                1 1 /Conv_25_output_0 /PRelu_25_output_0 0=64
+Convolution      /Conv_26                 1 1 /PRelu_25_output_0 /Conv_26_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_26                1 1 /Conv_26_output_0 /PRelu_26_output_0 0=64
+Convolution      /Conv_27                 1 1 /PRelu_26_output_0 /Conv_27_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_27                1 1 /Conv_27_output_0 /PRelu_27_output_0 0=64
+Convolution      /Conv_28                 1 1 /PRelu_27_output_0 /Conv_28_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_28                1 1 /Conv_28_output_0 /PRelu_28_output_0 0=64
+Convolution      /Conv_29                 1 1 /PRelu_28_output_0 /Conv_29_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_29                1 1 /Conv_29_output_0 /PRelu_29_output_0 0=64
+Convolution      /Conv_30                 1 1 /PRelu_29_output_0 /Conv_30_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_30                1 1 /Conv_30_output_0 /PRelu_30_output_0 0=64
+Convolution      /Conv_31                 1 1 /PRelu_30_output_0 /Conv_31_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_31                1 1 /Conv_31_output_0 /PRelu_31_output_0 0=64
+Convolution      /Conv_32                 1 1 /PRelu_31_output_0 /Conv_32_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_32                1 1 /Conv_32_output_0 /PRelu_32_output_0 0=64
+Convolution      /Conv_33                 1 1 /PRelu_32_output_0 /Conv_33_output_0 0=48 1=3 4=1 5=1 6=27648
+PixelShuffle     /DepthToSpace            1 1 /Conv_33_output_0 /DepthToSpace_output_0 0=4
+Interp           /Resize                  1 1 data_splitncnn_0 /Resize_output_0 0=1 1=4.000000e+00 2=4.000000e+00
+BinaryOp         /Add                     2 1 /DepthToSpace_output_0 /Resize_output_0 /Add_output_0
+Clip             /Clip                    1 1 /Add_output_0 output 0=0.000000e+00 1=1.000000e+00

models/realesrgan/realesr-generalv3-x4.param

@@ -0,0 +1,75 @@
+7767517
+73 74
+Input            data                     0 1 data
+Split            splitncnn_input0         1 2 data data_splitncnn_0 data_splitncnn_1
+Convolution      /Conv                    1 1 data_splitncnn_1 /Conv_output_0 0=64 1=3 4=1 5=1 6=1728
+PReLU            /PRelu                   1 1 /Conv_output_0 /PRelu_output_0 0=64
+Convolution      /Conv_1                  1 1 /PRelu_output_0 /Conv_1_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_1                 1 1 /Conv_1_output_0 /PRelu_1_output_0 0=64
+Convolution      /Conv_2                  1 1 /PRelu_1_output_0 /Conv_2_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_2                 1 1 /Conv_2_output_0 /PRelu_2_output_0 0=64
+Convolution      /Conv_3                  1 1 /PRelu_2_output_0 /Conv_3_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_3                 1 1 /Conv_3_output_0 /PRelu_3_output_0 0=64
+Convolution      /Conv_4                  1 1 /PRelu_3_output_0 /Conv_4_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_4                 1 1 /Conv_4_output_0 /PRelu_4_output_0 0=64
+Convolution      /Conv_5                  1 1 /PRelu_4_output_0 /Conv_5_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_5                 1 1 /Conv_5_output_0 /PRelu_5_output_0 0=64
+Convolution      /Conv_6                  1 1 /PRelu_5_output_0 /Conv_6_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_6                 1 1 /Conv_6_output_0 /PRelu_6_output_0 0=64
+Convolution      /Conv_7                  1 1 /PRelu_6_output_0 /Conv_7_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_7                 1 1 /Conv_7_output_0 /PRelu_7_output_0 0=64
+Convolution      /Conv_8                  1 1 /PRelu_7_output_0 /Conv_8_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_8                 1 1 /Conv_8_output_0 /PRelu_8_output_0 0=64
+Convolution      /Conv_9                  1 1 /PRelu_8_output_0 /Conv_9_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_9                 1 1 /Conv_9_output_0 /PRelu_9_output_0 0=64
+Convolution      /Conv_10                 1 1 /PRelu_9_output_0 /Conv_10_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_10                1 1 /Conv_10_output_0 /PRelu_10_output_0 0=64
+Convolution      /Conv_11                 1 1 /PRelu_10_output_0 /Conv_11_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_11                1 1 /Conv_11_output_0 /PRelu_11_output_0 0=64
+Convolution      /Conv_12                 1 1 /PRelu_11_output_0 /Conv_12_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_12                1 1 /Conv_12_output_0 /PRelu_12_output_0 0=64
+Convolution      /Conv_13                 1 1 /PRelu_12_output_0 /Conv_13_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_13                1 1 /Conv_13_output_0 /PRelu_13_output_0 0=64
+Convolution      /Conv_14                 1 1 /PRelu_13_output_0 /Conv_14_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_14                1 1 /Conv_14_output_0 /PRelu_14_output_0 0=64
+Convolution      /Conv_15                 1 1 /PRelu_14_output_0 /Conv_15_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_15                1 1 /Conv_15_output_0 /PRelu_15_output_0 0=64
+Convolution      /Conv_16                 1 1 /PRelu_15_output_0 /Conv_16_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_16                1 1 /Conv_16_output_0 /PRelu_16_output_0 0=64
+Convolution      /Conv_17                 1 1 /PRelu_16_output_0 /Conv_17_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_17                1 1 /Conv_17_output_0 /PRelu_17_output_0 0=64
+Convolution      /Conv_18                 1 1 /PRelu_17_output_0 /Conv_18_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_18                1 1 /Conv_18_output_0 /PRelu_18_output_0 0=64
+Convolution      /Conv_19                 1 1 /PRelu_18_output_0 /Conv_19_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_19                1 1 /Conv_19_output_0 /PRelu_19_output_0 0=64
+Convolution      /Conv_20                 1 1 /PRelu_19_output_0 /Conv_20_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_20                1 1 /Conv_20_output_0 /PRelu_20_output_0 0=64
+Convolution      /Conv_21                 1 1 /PRelu_20_output_0 /Conv_21_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_21                1 1 /Conv_21_output_0 /PRelu_21_output_0 0=64
+Convolution      /Conv_22                 1 1 /PRelu_21_output_0 /Conv_22_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_22                1 1 /Conv_22_output_0 /PRelu_22_output_0 0=64
+Convolution      /Conv_23                 1 1 /PRelu_22_output_0 /Conv_23_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_23                1 1 /Conv_23_output_0 /PRelu_23_output_0 0=64
+Convolution      /Conv_24                 1 1 /PRelu_23_output_0 /Conv_24_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_24                1 1 /Conv_24_output_0 /PRelu_24_output_0 0=64
+Convolution      /Conv_25                 1 1 /PRelu_24_output_0 /Conv_25_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_25                1 1 /Conv_25_output_0 /PRelu_25_output_0 0=64
+Convolution      /Conv_26                 1 1 /PRelu_25_output_0 /Conv_26_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_26                1 1 /Conv_26_output_0 /PRelu_26_output_0 0=64
+Convolution      /Conv_27                 1 1 /PRelu_26_output_0 /Conv_27_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_27                1 1 /Conv_27_output_0 /PRelu_27_output_0 0=64
+Convolution      /Conv_28                 1 1 /PRelu_27_output_0 /Conv_28_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_28                1 1 /Conv_28_output_0 /PRelu_28_output_0 0=64
+Convolution      /Conv_29                 1 1 /PRelu_28_output_0 /Conv_29_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_29                1 1 /Conv_29_output_0 /PRelu_29_output_0 0=64
+Convolution      /Conv_30                 1 1 /PRelu_29_output_0 /Conv_30_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_30                1 1 /Conv_30_output_0 /PRelu_30_output_0 0=64
+Convolution      /Conv_31                 1 1 /PRelu_30_output_0 /Conv_31_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_31                1 1 /Conv_31_output_0 /PRelu_31_output_0 0=64
+Convolution      /Conv_32                 1 1 /PRelu_31_output_0 /Conv_32_output_0 0=64 1=3 4=1 5=1 6=36864
+PReLU            /PRelu_32                1 1 /Conv_32_output_0 /PRelu_32_output_0 0=64
+Convolution      /Conv_33                 1 1 /PRelu_32_output_0 /Conv_33_output_0 0=48 1=3 4=1 5=1 6=27648
+PixelShuffle     /DepthToSpace            1 1 /Conv_33_output_0 /DepthToSpace_output_0 0=4
+Interp           /Resize                  1 1 data_splitncnn_0 /Resize_output_0 0=1 1=4.000000e+00 2=4.000000e+00
+BinaryOp         /Add                     2 1 /DepthToSpace_output_0 /Resize_output_0 /Add_output_0
+Clip             /Clip                    1 1 /Add_output_0 output 0=0.000000e+00 1=1.000000e+00

packaging/arch/PKGBUILD

@@ -5,8 +5,8 @@ pkgdesc="A machine learning-based video super resolution and frame interpolation
 arch=('x86_64')
 url="https://github.com/k4yt3x/video2x"
 license=('AGPL-3.0-only')
-depends=('ffmpeg' 'ncnn' 'vulkan-driver' 'spdlog' 'boost-libs')
-makedepends=('git' 'cmake' 'clang' 'vulkan-headers' 'openmp' 'boost')
+depends=('ffmpeg' 'ncnn' 'openmp' 'vulkan-driver' 'spdlog' 'boost-libs')
+makedepends=('git' 'cmake' 'clang' 'vulkan-headers' 'boost')
 
 pkgver() {
     printf "r%s.%s" "$(git rev-list --count HEAD)" "$(git rev-parse --short=7 HEAD)"

packaging/docker/Dockerfile

@@ -38,7 +38,7 @@ ENV VK_ICD_FILENAMES=/usr/share/vulkan/icd.d/nvidia_icd.json\
 
 COPY --from=builder /tmp/video2x.pkg.tar.zst /video2x.pkg.tar.zst
 RUN pacman -Sy --noconfirm nvidia-utils vulkan-radeon vulkan-intel vulkan-swrast \
-        ffmpeg ncnn spdlog boost-libs \
+        ffmpeg ncnn openmp spdlog boost-libs \
     && pacman -U --noconfirm /video2x.pkg.tar.zst \
     && rm -rf /video2x.pkg.tar.zst /var/cache/pacman/pkg/*
 

src/encoder.cpp

@@ -6,10 +6,9 @@ extern "C" {
 #include <libavutil/opt.h>
 }
 
-#include "logger_manager.h"
-
 #include "avutils.h"
 #include "conversions.h"
+#include "logger_manager.h"
 
 namespace video2x {
 namespace encoder {
@@ -45,6 +44,9 @@ int Encoder::init(
 ) {
     int ret;
 
+    // Copy the encoder configuration
+    enc_cfg_ = enc_cfg;
+
     // Allocate the output format context
     avformat_alloc_output_context2(&ofmt_ctx_, nullptr, nullptr, out_fpath.u8string().c_str());
     if (!ofmt_ctx_) {
@@ -188,8 +190,8 @@ int Encoder::init(
     out_vstream->r_frame_rate = enc_ctx_->framerate;
 
     // Copy other streams if necessary
-    if (enc_cfg.copy_streams) {
-        // Allocate the stream mape frame o
+    if (enc_cfg.copy_audio_streams || enc_cfg.copy_subtitle_streams) {
+        // Allocate the stream map
         stream_map_ =
             reinterpret_cast<int*>(av_malloc_array(ifmt_ctx->nb_streams, sizeof(*stream_map_)));
         if (!stream_map_) {
@@ -198,22 +200,37 @@ int Encoder::init(
         }
 
         // Map each input stream to an output stream
-        for (int i = 0; i < static_cast<int>(ifmt_ctx->nb_streams); i++) {
-            AVStream* in_stream = ifmt_ctx->streams[i];
+        for (int stream_index = 0; stream_index < static_cast<int>(ifmt_ctx->nb_streams);
+             stream_index++) {
+            AVStream* in_stream = ifmt_ctx->streams[stream_index];
             AVCodecParameters* in_codecpar = in_stream->codecpar;
 
             // Skip the input video stream as it's already processed
-            if (i == in_vstream_idx) {
-                stream_map_[i] = out_vstream_idx_;
+            if (stream_index == in_vstream_idx) {
+                stream_map_[stream_index] = out_vstream_idx_;
                 continue;
             }
 
-            // Map only audio and subtitle streams (skip other types)
-            if (in_codecpar->codec_type != AVMEDIA_TYPE_AUDIO &&
-                in_codecpar->codec_type != AVMEDIA_TYPE_SUBTITLE) {
-                stream_map_[i] = -1;
-                logger()->warn("Skipping unsupported stream type at index: {}", i);
-                continue;
+            // Determine if the current stream should be skipped
+            switch (in_codecpar->codec_type) {
+                case AVMEDIA_TYPE_AUDIO:
+                    if (!enc_cfg.copy_audio_streams) {
+                        stream_map_[stream_index] = -1;
+                        continue;
+                    }
+                    logger()->debug("Copying audio stream at index: {}", stream_index);
+                    break;
+                case AVMEDIA_TYPE_SUBTITLE:
+                    if (!enc_cfg.copy_subtitle_streams) {
+                        stream_map_[stream_index] = -1;
+                        continue;
+                    }
+                    logger()->debug("Copying subtitle stream at index: {}", stream_index);
+                    break;
+                default:
+                    stream_map_[stream_index] = -1;
+                    logger()->warn("Skipping unsupported stream type at index: {}", stream_index);
+                    continue;
             }
 
             // Create corresponding output stream for audio and subtitle streams
@@ -242,8 +259,8 @@ int Encoder::init(
             out_stream->time_base = in_stream->time_base;
 
             // Map input stream index to output stream index
-            logger()->debug("Stream mapping: {} (in) -> {} (out)", i, out_stream->index);
-            stream_map_[i] = out_stream->index;
+            logger()->debug("Stream mapping: {} (in) -> {} (out)", stream_index, out_stream->index);
+            stream_map_[stream_index] = out_stream->index;
         }
     }
 
@@ -275,7 +292,9 @@ int Encoder::write_frame(AVFrame* frame, int64_t frame_idx) {
     frame->pict_type = AV_PICTURE_TYPE_NONE;
 
     // Calculate this frame's presentation timestamp (PTS)
-    frame->pts = av_rescale_q(frame_idx, av_inv_q(enc_ctx_->framerate), enc_ctx_->time_base);
+    if (enc_cfg_.recalculate_pts) {
+        frame->pts = av_rescale_q(frame_idx, av_inv_q(enc_ctx_->framerate), enc_ctx_->time_base);
+    }
 
     // Convert the frame to the encoder's pixel format if needed
     if (frame->format != enc_ctx_->pix_fmt) {

src/filter_libplacebo.cpp

@@ -1,7 +1,5 @@
 #include "filter_libplacebo.h"
 
-#include <cstdio>
-
 #include <spdlog/spdlog.h>
 
 #include "fsutils.h"

src/filter_realesrgan.cpp

@@ -17,12 +17,14 @@ FilterRealesrgan::FilterRealesrgan(
     int gpuid,
     bool tta_mode,
     int scaling_factor,
+    int noise_level,
     const fsutils::StringType model_name
 )
     : realesrgan_(nullptr),
       gpuid_(gpuid),
       tta_mode_(tta_mode),
       scaling_factor_(scaling_factor),
+      noise_level_(noise_level),
       model_name_(std::move(model_name)) {}
 
 FilterRealesrgan::~FilterRealesrgan() {
@@ -35,10 +37,16 @@ int FilterRealesrgan::init(AVCodecContext* dec_ctx, AVCodecContext* enc_ctx, AVB
     std::filesystem::path model_param_path;
     std::filesystem::path model_bin_path;
 
-    fsutils::StringType param_file_name =
-        model_name_ + STR("-x") + fsutils::to_string_type(scaling_factor_) + STR(".param");
-    fsutils::StringType bin_file_name =
-        model_name_ + STR("-x") + fsutils::to_string_type(scaling_factor_) + STR(".bin");
+    fsutils::StringType param_file_name = model_name_;
+    fsutils::StringType bin_file_name = model_name_;
+
+    if (model_name_ == STR("realesr-generalv3") && noise_level_ > 0) {
+        param_file_name += STR("-wdn");
+        bin_file_name += STR("-wdn");
+    }
+
+    param_file_name += STR("-x") + fsutils::to_string_type(scaling_factor_) + STR(".param");
+    bin_file_name += STR("-x") + fsutils::to_string_type(scaling_factor_) + STR(".bin");
 
     // Find the model paths by model name if provided
     model_param_path = std::filesystem::path(STR("models")) / STR("realesrgan") / param_file_name;

src/libvideo2x.cpp

@@ -1,5 +1,4 @@
 #include "libvideo2x.h"
-#include <libavcodec/avcodec.h>
 
 extern "C" {
 #include <libavutil/avutil.h>
@@ -238,8 +237,10 @@ int VideoProcessor::process_frames(
                 }
 
                 // Calculate this frame's presentation timestamp (PTS)
-                frame->pts =
-                    av_rescale_q(frame_idx_, av_inv_q(enc_ctx->framerate), enc_ctx->time_base);
+                if (enc_cfg_.recalculate_pts) {
+                    frame->pts =
+                        av_rescale_q(frame_idx_, av_inv_q(enc_ctx->framerate), enc_ctx->time_base);
+                }
 
                 // Process the frame based on the selected processing mode
                 AVFrame* proc_frame = nullptr;
@@ -262,10 +263,11 @@ int VideoProcessor::process_frames(
                     return ret;
                 }
                 av_frame_unref(frame.get());
-                frame_idx_++;
+                frame_idx_.fetch_add(1);
                 logger()->debug("Processed frame {}/{}", frame_idx_.load(), total_frames_.load());
             }
-        } else if (enc_cfg_.copy_streams && stream_map[packet->stream_index] >= 0) {
+        } else if ((enc_cfg_.copy_audio_streams || enc_cfg_.copy_subtitle_streams) &&
+                   stream_map[packet->stream_index] >= 0) {
             ret = write_raw_packet(packet.get(), ifmt_ctx, ofmt_ctx, stream_map);
             if (ret < 0) {
                 return ret;
@@ -274,12 +276,12 @@ int VideoProcessor::process_frames(
         av_packet_unref(packet.get());
     }
 
-    // Flush the filter
+    // Flush the processor
     std::vector<AVFrame*> raw_flushed_frames;
     ret = processor->flush(raw_flushed_frames);
     if (ret < 0) {
         av_strerror(ret, errbuf, sizeof(errbuf));
-        logger()->critical("Error flushing filter: {}", errbuf);
+        logger()->critical("Error flushing processor: {}", errbuf);
         return ret;
     }
 
@@ -295,7 +297,7 @@ int VideoProcessor::process_frames(
         if (ret < 0) {
             return ret;
         }
-        frame_idx_++;
+        frame_idx_.fetch_add(1);
     }
 
     // Flush the encoder
@@ -314,7 +316,7 @@ int VideoProcessor::write_frame(AVFrame* frame, encoder::Encoder& encoder) {
     int ret = 0;
 
     if (!benchmark_) {
-        ret = encoder.write_frame(frame, frame_idx_);
+        ret = encoder.write_frame(frame, frame_idx_.load());
         if (ret < 0) {
             av_strerror(ret, errbuf, sizeof(errbuf));
             logger()->critical("Error encoding/writing frame: {}", errbuf);
@@ -437,7 +439,7 @@ int VideoProcessor::process_interpolation(
             }
         }
 
-        frame_idx_++;
+        frame_idx_.fetch_add(1);
         current_time_step += time_step;
     }
 

src/processor_factory.cpp

@@ -91,6 +91,7 @@ void ProcessorFactory::init_default_processors(ProcessorFactory& factory) {
                 static_cast<int>(vk_device_index),
                 config.tta_mode,
                 proc_cfg.scaling_factor,
+                proc_cfg.noise_level,
                 config.model_name
             );
         }

tools/video2x/src/argparse.cpp

@@ -95,7 +95,9 @@ int parse_args(
         encoder_opts.add_options()
             ("codec,c", PO_STR_VALUE<video2x::fsutils::StringType>()
                 ->default_value(STR("libx264"), "libx264"), "Output codec")
-            ("no-copy-streams", "Do not copy audio and subtitle streams")
+            ("no-recalculate-pts", "Do not recalculate presentation timestamps")
+            ("no-copy-audio-streams", "Do not copy audio streams")
+            ("no-copy-subtitle-streams", "Do not copy subtitle streams")
             ("pix-fmt", PO_STR_VALUE<video2x::fsutils::StringType>(), "Output pixel format")
             ("bit-rate", po::value<int64_t>(&enc_cfg.bit_rate)->default_value(0),
                 "Bitrate in bits per second")
@@ -134,7 +136,7 @@ int parse_args(
             ("scaling-factor,s", po::value<int>(&proc_cfg.scaling_factor)
                 ->notifier([](int v) { validate_min(v, "scaling-factor", 2); }), "Scaling factor")
             ("noise-level,n", po::value<int>(&proc_cfg.noise_level)
-                ->notifier([](int v) { validate_min(v, "noise-level", 0); }), "Noise level")
+                ->notifier([](int v) { validate_min(v, "noise-level", -1); }), "Noise level")
         ;
 
         po::options_description interp_opts("Frame interpolation options");
@@ -156,23 +158,23 @@ int parse_args(
                 "anime4k-v4-b, anime4k-v4-b+b, anime4k-v4-c, anime4k-v4-c+a, anime4k-v4.1-gan)")
         ;
 
-        po::options_description realesrgan_opts("RealESRGAN options");
+        po::options_description realesrgan_opts("Real-ESRGAN options");
         realesrgan_opts.add_options()
             ("realesrgan-model", PO_STR_VALUE<video2x::fsutils::StringType>()
                 ->default_value(STR("realesr-animevideov3"), "realesr-animevideov3")
                 ->notifier(validate_realesrgan_model_name),
-                "Name of the RealESRGAN model to use (realesr-animevideov3, realesrgan-plus-anime, "
-                "realesrgan-plus)")
+                "Name of the Real-ESRGAN model to use (realesr-animevideov3, "
+                "realesrgan-plus-anime, realesrgan-plus, realesr-generalv3)")
         ;
 
-        po::options_description realcugan_opts("RealCUGAN options");
+        po::options_description realcugan_opts("Real-CUGAN options");
         realcugan_opts.add_options()
             ("realcugan-model", PO_STR_VALUE<video2x::fsutils::StringType>()
                 ->default_value(STR("models-se"), "models-se")
                 ->notifier(validate_realcugan_model_name),
-                "Name of the RealCUGAN model to use (models-nose, models-pro, models-se)")
+                "Name of the Real-CUGAN model to use (models-nose, models-pro, models-se)")
             ("realcugan-threads", po::value<int>()->default_value(1),
-                "Number of threads to use for RealCUGAN")
+                "Number of threads to use for Real-CUGAN")
             ("realcugan-syncgap", po::value<int>()->default_value(3),
                 "Sync gap mode; 0:no sync, 1: accurate sync: 2 = rough sync, 3: very rough sync")
         ;
@@ -212,7 +214,7 @@ int parse_args(
                 << "    video2x -i input.mp4 -o output.mp4 -w 3840 -h 2160 \\" << std::endl
                 << "      -p libplacebo --libplacebo-shader anime4k-v4-a+a" << std::endl
                 << std::endl
-                << "  Upscale a film by 4x using RealESRGAN with custom encoder options:"
+                << "  Upscale a film by 4x using Real-ESRGAN with custom encoder options:"
                 << std::endl
                 << "    video2x -i input.mkv -o output.mkv -s 4 \\" << std::endl
                 << "      -p realesrgan --realesrgan-model realesrgan-plus \\" << std::endl
@@ -323,8 +325,10 @@ int parse_args(
             enc_cfg.codec = codec_str;
         }
 
-        // Parse copy streams flag
-        enc_cfg.copy_streams = vm.count("no-copy-streams") == 0;
+        // Parse copy streams options
+        enc_cfg.recalculate_pts = vm.count("no-recalculate-pts") == 0;
+        enc_cfg.copy_audio_streams = vm.count("no-copy-audio-streams") == 0;
+        enc_cfg.copy_subtitle_streams = vm.count("no-copy-subtitle-streams") == 0;
 
         // Parse pixel format to AVPixelFormat
         enc_cfg.pix_fmt = AV_PIX_FMT_NONE;
@@ -385,16 +389,19 @@ int parse_args(
             }
             case video2x::processors::ProcessorType::RealESRGAN: {
                 if (!vm.count("realesrgan-model")) {
-                    video2x::logger()->critical("RealESRGAN model name must be set for RealESRGAN."
-                    );
+                    video2x::logger()->critical("The model name must be set for Real-ESRGAN.");
                     return -1;
                 }
                 if (proc_cfg.scaling_factor < 2 || proc_cfg.scaling_factor > 4) {
                     video2x::logger()->critical(
-                        "Scaling factor must be set to 2, 3, or 4 for RealESRGAN."
+                        "Scaling factor must be set to 2, 3, or 4 for Real-ESRGAN."
                     );
                     return -1;
                 }
+                if (proc_cfg.noise_level < -1 || proc_cfg.noise_level > 1) {
+                    video2x::logger()->critical("Noise level must be 0 or 1 for Real-ESRGAN.");
+                    return -1;
+                }
 
                 proc_cfg.processor_type = video2x::processors::ProcessorType::RealESRGAN;
                 video2x::processors::RealESRGANConfig realesrgan_config;
@@ -406,31 +413,31 @@ int parse_args(
             }
             case video2x::processors::ProcessorType::RealCUGAN: {
                 if (!vm.count("realcugan-model")) {
-                    video2x::logger()->critical("RealCUGAN model name must be set for RealCUGAN.");
+                    video2x::logger()->critical("The model name must be set for Real-CUGAN.");
                     return -1;
                 }
                 if (vm.count("realcugan-threads") && vm["realcugan-threads"].as<int>() < 1) {
                     video2x::logger()->critical(
-                        "Number of threads must be at least 1 for RealCUGAN."
+                        "Number of threads must be at least 1 for Real-CUGAN."
                     );
                     return -1;
                 }
                 if (vm.count("realcugan-syncgap") && (vm["realcugan-syncgap"].as<int>() < 0 ||
                                                       vm["realcugan-syncgap"].as<int>() > 3)) {
                     video2x::logger()->critical(
-                        "Sync gap mode must be set to 0, 1, 2, or 3 for RealCUGAN."
+                        "Sync gap mode must be set to 0, 1, 2, or 3 for Real-CUGAN."
                     );
                     return -1;
                 }
                 if (proc_cfg.scaling_factor < 2 || proc_cfg.scaling_factor > 4) {
                     video2x::logger()->critical(
-                        "Scaling factor must be set to 2, 3, or 4 for RealCUGAN."
+                        "Scaling factor must be set to 2, 3, or 4 for Real-CUGAN."
                     );
                     return -1;
                 }
                 if (proc_cfg.noise_level < -1 || proc_cfg.noise_level > 3) {
                     video2x::logger()->critical(
-                        "Noise level must be set to -1, 0, 1, 2, or 3 for RealCUGAN."
+                        "Noise level must be set to -1, 0, 1, 2, or 3 for Real-CUGAN."
                     );
                     return -1;
                 }
@@ -447,7 +454,7 @@ int parse_args(
             }
             case video2x::processors::ProcessorType::RIFE: {
                 if (!vm.count("rife-model")) {
-                    video2x::logger()->critical("RIFE model name must be set for RIFE.");
+                    video2x::logger()->critical("The model name must be set for RIFE.");
                     return -1;
                 }
                 if (proc_cfg.frm_rate_mul < 2) {

tools/video2x/src/validators.cpp

@@ -24,7 +24,10 @@ void validate_anime4k_shader_name(const video2x::fsutils::StringType& shader_nam
 
 void validate_realesrgan_model_name(const video2x::fsutils::StringType& model_name) {
     static const std::unordered_set<video2x::fsutils::StringType> valid_realesrgan_models = {
-        STR("realesrgan-plus"), STR("realesrgan-plus-anime"), STR("realesr-animevideov3")
+        STR("realesrgan-plus"),
+        STR("realesrgan-plus-anime"),
+        STR("realesr-animevideov3"),
+        STR("realesr-generalv3"),
     };
     if (valid_realesrgan_models.count(model_name) == 0) {
         throw po::validation_error(