chore(librealesrgan): updated librealesrgan submodule path

Signed-off-by: k4yt3x <i@k4yt3x.com>

.gitattributes

@@ -1 +1 @@
-models/* linguist-vendored
+models/** linguist-vendored

.github/FUNDING.yml

@@ -1,12 +1,2 @@
-# These are supported funding model platforms
-
 github: k4yt3x
 patreon: k4yt3x
-open_collective: # Replace with a single Open Collective username
-ko_fi: # Replace with a single Ko-fi username
-tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
-community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
-liberapay: # Replace with a single Liberapay username
-issuehunt: # Replace with a single IssueHunt username
-otechie: # Replace with a single Otechie username
-custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/workflows/build.yml

@@ -6,6 +6,7 @@ on:
       - dev
   pull_request: {}
   workflow_dispatch: {}
+
 jobs:
   ubuntu:
     runs-on: ubuntu-latest
@@ -29,11 +30,12 @@ jobs:
             libswscale-dev \
             libvulkan-dev \
             glslang-tools \
-            libomp-dev
+            libomp-dev \
+            libopencv-dev
       - name: Build Video2X
         run: |
           mkdir -p /tmp/build /tmp/install
-          cmake -B /tmp/build -S . -DUSE_SYSTEM_NCNN=OFF \
+          cmake -B /tmp/build -S . -DUSE_SYSTEM_NCNN=OFF -DUSE_SYSTEM_SPDLOG=OFF \
             -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ \
             -DCMAKE_BUILD_TYPE=Debug -DCMAKE_INSTALL_PREFIX=/tmp/install \
             -DINSTALL_BIN_DESTINATION=. -DINSTALL_INCLUDE_DESTINATION=include \
@@ -44,6 +46,7 @@ jobs:
         with:
           name: video2x-nightly-linux-amd64
           path: /tmp/install
+
   windows:
     runs-on: windows-latest
     steps:
@@ -61,6 +64,7 @@ jobs:
         run: |
           $ffmpegVersion = "7.1"
           $ncnnVersion = "20240820"
+          $opencvVersion = "4.10.0"
 
           git submodule update --init --recursive
 
@@ -71,9 +75,16 @@ jobs:
           curl -Lo ncnn-shared.zip "https://github.com/Tencent/ncnn/releases/download/$ncnnVersion/ncnn-$ncnnVersion-windows-vs2022-shared.zip"
           Expand-Archive -Path ncnn-shared.zip -DestinationPath third_party
           Rename-Item -Path "third_party/ncnn-$ncnnVersion-windows-vs2022-shared" -NewName ncnn-shared
+
+          curl -Lo opencv-shared.exe "https://github.com/opencv/opencv/releases/download/$opencvVersion/opencv-$opencvVersion-windows.exe"
+          7z x opencv-shared.exe -y
+          Move-Item -Path opencv -Destination third_party\opencv-shared
       - name: Build Video2X
+        shell: pwsh
         run: |
-          cmake -S . -B build -DUSE_SYSTEM_NCNN=OFF -DCMAKE_BUILD_TYPE=Debug -DCMAKE_INSTALL_PREFIX=build/video2x_install
+          cmake -S . -B build `
+            -DUSE_SYSTEM_NCNN=OFF -DUSE_SYSTEM_SPDLOG=OFF -DUSE_SYSTEM_OPENCV=OFF `
+            -DCMAKE_BUILD_TYPE=Debug -DCMAKE_INSTALL_PREFIX=build/video2x_install
           cmake --build build --config Debug --parallel --target install
       - name: Upload artifacts
         uses: actions/upload-artifact@v4

.github/workflows/release.yml

@@ -4,17 +4,20 @@ on:
     tags:
       - "*"
 
+permissions:
+  contents: write
+
 jobs:
   setup:
     if: github.event.base_ref == 'refs/heads/master'
     name: Setup
     runs-on: ubuntu-latest
     outputs:
-      tag: ${{ steps.get_tag.outputs.tag }}
+      version: ${{ steps.get_version.outputs.version }}
     steps:
-      - name: Get tag
+      - name: Get version
-        id: get_tag
+        id: get_version
-        run: echo ::set-output name=tag::${GITHUB_REF/refs\/tags\//}
+        run: echo version=${GITHUB_REF/refs\/tags\//} >> $GITHUB_OUTPUT
 
   container:
     name: Build and upload container
@@ -32,7 +35,7 @@ jobs:
           password: ${{ secrets.GHCR_TOKEN }}
           dockerfile: Dockerfile
           image: video2x
-          tags: latest, ${{ needs.setup.outputs.tag }}
+          tags: latest, ${{ needs.setup.outputs.version }}
 
   create-release:
     name: Create release
@@ -45,11 +48,10 @@ jobs:
     steps:
       - name: Create release
         id: create_release
-        uses: actions/create-release@v1
+        uses: softprops/action-gh-release@v2
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
-          tag_name: ${{ needs.setup.outputs.tag }}
+          token: ${{ secrets.GITHUB_TOKEN }}
-          release_name: Video2X ${{ needs.setup.outputs.tag }}
+          tag_name: ${{ needs.setup.outputs.version }}
+          name: ${{ needs.setup.outputs.version }}
           draft: true
           prerelease: false

.gitmodules

@@ -1,6 +1,12 @@
-[submodule "third_party/libreal_esrgan_ncnn_vulkan"]
+[submodule "third_party/librealesrgan_ncnn_vulkan"]
-	path = third_party/libreal_esrgan_ncnn_vulkan
+	path = third_party/librealesrgan_ncnn_vulkan
-	url = https://github.com/k4yt3x/libreal-esrgan-ncnn-vulkan.git
+	url = https://github.com/k4yt3x/librealesrgan-ncnn-vulkan.git
 [submodule "third_party/ncnn"]
 	path = third_party/ncnn
 	url = https://github.com/Tencent/ncnn.git
+[submodule "third_party/spdlog"]
+	path = third_party/spdlog
+	url = https://github.com/gabime/spdlog.git
+[submodule "third_party/opencv"]
+	path = third_party/opencv
+	url = https://github.com/opencv/opencv.git

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.10)
-project(video2x VERSION 6.0.0 LANGUAGES CXX C)
+project(video2x VERSION 6.0.0 LANGUAGES C CXX)
 
 # Set the C standard
 set(CMAKE_C_STANDARD 11)
@@ -28,18 +28,47 @@ if(CMAKE_BUILD_TYPE STREQUAL "Release")
     endif()
 endif()
 
+# Set global compile options for all targets
+if (CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
+    add_compile_options(/W4 /permissive-)
+elseif (CMAKE_CXX_COMPILER_ID STREQUAL "GNU" OR CMAKE_CXX_COMPILER_ID MATCHES "Clang")
+    add_compile_options(-Wall -Wextra -Wpedantic -Wconversion -Wshadow)
+endif()
+
 # Build options
 option(BUILD_SHARED_LIBS "Build libvideo2x as a shared library" ON)
-option(BUILD_VIDEO2X "Build the video2x executable" ON)
+option(BUILD_VIDEO2X_CLI "Build the video2x executable" ON)
+option(USE_SYSTEM_SPDLOG "Use system spdlog library" ON)
+option(USE_SYSTEM_OPENCV "Use system OpenCV library" ON)
 option(USE_SYSTEM_NCNN "Use system ncnn library" ON)
 
+# Generate the version header file
+configure_file(
+    "${CMAKE_CURRENT_SOURCE_DIR}/include/libvideo2x/version.h.in"
+    "${CMAKE_CURRENT_BINARY_DIR}/libvideo2x/version.h"
+    @ONLY
+)
+
+# Find the required packages
 set(ALL_INCLUDE_DIRS)
 set(ALL_LIBRARIES)
 
+# spdlog
+if (USE_SYSTEM_SPDLOG)
+    find_package(spdlog REQUIRED)
+    list(APPEND ALL_INCLUDE_DIRS ${spdlog_INCLUDE_DIRS})
+    list(APPEND ALL_LIBRARIES spdlog::spdlog)
+else()
+    add_subdirectory(third_party/spdlog)
+    list(APPEND ALL_LIBRARIES spdlog::spdlog_header_only)
+endif()
+
+# Platform-specific dependencies
 if(WIN32)
     # Define base paths for FFmpeg and ncnn
     set(FFMPEG_BASE_PATH ${PROJECT_SOURCE_DIR}/third_party/ffmpeg-shared)
     set(NCNN_BASE_PATH ${PROJECT_SOURCE_DIR}/third_party/ncnn-shared/x64)
+    set(OPENCV_BASE_PATH ${PROJECT_SOURCE_DIR}/third_party/opencv-shared)
 
     # FFmpeg
     list(APPEND ALL_LIBRARIES
@@ -54,7 +83,9 @@ if(WIN32)
 
     # ncnn
     # TODO: Figure out why this file is not being copied to the install directory
-    set(SPIRV_BUILD_PATH ${CMAKE_BINARY_DIR}/realesrgan-prefix/src/realesrgan-build/ncnn/glslang/SPIRV)
+    set(SPIRV_BUILD_PATH
+        ${CMAKE_BINARY_DIR}/realesrgan-prefix/src/realesrgan-build/ncnn/glslang/SPIRV
+    )
     if (CMAKE_BUILD_TYPE STREQUAL "Release")
         set(SPIRV_LIB ${SPIRV_BUILD_PATH}/Release/SPIRV.lib)
     else()
@@ -66,8 +97,12 @@ if(WIN32)
         ${SPIRV_LIB}
     )
     list(APPEND ALL_INCLUDE_DIRS ${NCNN_BASE_PATH}/include/ncnn)
+
+    # OpenCV
+    list(APPEND ALL_LIBRARIES ${OPENCV_BASE_PATH}/build/x64/vc16/lib/opencv_world4100.lib)
+    list(APPEND ALL_INCLUDE_DIRS ${OPENCV_BASE_PATH}/build/include)
 else()
-    # Find the required packages using pkg-config
+    # FFmpeg
     find_package(PkgConfig REQUIRED)
     set(REQUIRED_PKGS
         libavcodec
@@ -84,11 +119,55 @@ else()
         list(APPEND ALL_INCLUDE_DIRS ${${PKG}_INCLUDE_DIRS})
         list(APPEND ALL_LIBRARIES ${${PKG}_LIBRARIES})
     endforeach()
-endif()
 
-# Remove duplicate entries
+    # OpenCV
-list(REMOVE_DUPLICATES ALL_INCLUDE_DIRS)
+    if (USE_SYSTEM_OPENCV)
-list(REMOVE_DUPLICATES ALL_LIBRARIES)
+        find_package(OpenCV REQUIRED)
+        list(APPEND ALL_INCLUDE_DIRS ${OpenCV_INCLUDE_DIRS}/opencv2)
+        list(APPEND ALL_LIBRARIES opencv_core opencv_videoio)
+    else()
+        option(BUILD_opencv_calib3d "" OFF)
+        option(BUILD_opencv_core "" ON)
+        option(BUILD_opencv_dnn "" OFF)
+        option(BUILD_opencv_features2d "" OFF)
+        option(BUILD_opencv_flann "" OFF)
+        option(BUILD_opencv_gapi "" OFF)
+        option(BUILD_opencv_highgui "" OFF)
+        option(BUILD_opencv_imgcodecs "" OFF)
+        option(BUILD_opencv_imgproc "" OFF)
+        option(BUILD_opencv_java "" OFF)
+        option(BUILD_opencv_js "" OFF)
+        option(BUILD_opencv_ml "" OFF)
+        option(BUILD_opencv_objc "" OFF)
+        option(BUILD_opencv_objdetect "" OFF)
+        option(BUILD_opencv_photo "" OFF)
+        option(BUILD_opencv_python "" OFF)
+        option(BUILD_opencv_python2 "" OFF)
+        option(BUILD_opencv_python3 "" OFF)
+        option(BUILD_opencv_stitching "" OFF)
+        option(BUILD_opencv_ts "" OFF)
+        option(BUILD_opencv_video "" OFF)
+        option(BUILD_opencv_videoio "" ON)
+        option(BUILD_opencv_world "" OFF)
+
+        option(WITH_PNG "" OFF)
+        option(WITH_JPEG "" OFF)
+        option(WITH_TIFF "" OFF)
+        option(WITH_WEBP "" OFF)
+        option(WITH_OPENJPEG "" OFF)
+        option(WITH_JASPER "" OFF)
+        option(WITH_OPENEXR "" OFF)
+        option(WITH_IMGCODEC "" OFF)
+
+        add_subdirectory(third_party/opencv)
+        list(APPEND ALL_INCLUDE_DIRS
+            ${PROJECT_SOURCE_DIR}/third_party/opencv/include
+            ${PROJECT_SOURCE_DIR}/third_party/opencv/modules/core/include
+            ${PROJECT_SOURCE_DIR}/third_party/opencv/modules/videoio/include
+        )
+        list(APPEND ALL_LIBRARIES opencv_core opencv_videoio)
+    endif() # USE_SYSTEM_OPENCV
+endif() # WIN32
 
 # Find ncnn package
 if(USE_SYSTEM_NCNN)
@@ -192,10 +271,10 @@ endif()
 # Include ExternalProject module
 include(ExternalProject)
 
-# Add libreal-esrgan-ncnn-vulkan as an external project
+# Add librealesrgan-ncnn-vulkan as an external project
 ExternalProject_Add(
     realesrgan
-    SOURCE_DIR ${PROJECT_SOURCE_DIR}/third_party/libreal_esrgan_ncnn_vulkan/src
+    SOURCE_DIR ${PROJECT_SOURCE_DIR}/third_party/librealesrgan_ncnn_vulkan/src
     CMAKE_ARGS
         -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
         -DCMAKE_INSTALL_PREFIX=${CMAKE_BINARY_DIR}/realesrgan_install
@@ -205,6 +284,10 @@ ExternalProject_Add(
     INSTALL_COMMAND ${CMAKE_COMMAND} --build . --target install --config ${CMAKE_BUILD_TYPE}
 )
 
+# Remove duplicate entries
+list(REMOVE_DUPLICATES ALL_INCLUDE_DIRS)
+list(REMOVE_DUPLICATES ALL_LIBRARIES)
+
 # Add all source files for libvideo2x
 file(GLOB LIBVIDEO2X_SOURCES src/*.cpp)
 
@@ -223,13 +306,14 @@ add_dependencies(libvideo2x realesrgan)
 # Include directories for the shared library
 target_include_directories(libvideo2x PRIVATE
     ${ALL_INCLUDE_DIRS}
+    ${CMAKE_CURRENT_BINARY_DIR}
     ${PROJECT_SOURCE_DIR}/include
-    ${PROJECT_SOURCE_DIR}/third_party/libreal_esrgan_ncnn_vulkan/src
+    ${PROJECT_SOURCE_DIR}/include/libvideo2x
+    ${PROJECT_SOURCE_DIR}/third_party/librealesrgan_ncnn_vulkan/src
 )
 
 # Compile options for the shared library
 target_compile_options(libvideo2x PRIVATE
-    -Wall
     -fPIC
     $<$<CONFIG:Release>:-Ofast>
     $<$<CONFIG:Debug>:-g -DDEBUG>
@@ -237,7 +321,7 @@ target_compile_options(libvideo2x PRIVATE
 
 # Define the path to the built libresrgan-ncnn-vulkan library
 if(WIN32)
-    set(REALESRGAN_LIB ${CMAKE_BINARY_DIR}/realesrgan_install/lib/realesrgan-ncnn-vulkan.lib)
+    set(REALESRGAN_LIB ${CMAKE_BINARY_DIR}/realesrgan_install/lib/librealesrgan-ncnn-vulkan.lib)
 else()
     set(REALESRGAN_LIB ${CMAKE_BINARY_DIR}/realesrgan_install/lib/librealesrgan-ncnn-vulkan.so)
 endif()
@@ -254,21 +338,19 @@ if(NOT WIN32)
 endif()
 
 # Create the executable 'video2x'
-if (BUILD_VIDEO2X)
+if (BUILD_VIDEO2X_CLI)
     add_executable(video2x src/video2x.c src/getopt.c)
     set_target_properties(video2x PROPERTIES OUTPUT_NAME video2x)
 
     # Include directories for the executable
     target_include_directories(video2x PRIVATE
         ${ALL_INCLUDE_DIRS}
+        ${CMAKE_CURRENT_BINARY_DIR}
         ${PROJECT_SOURCE_DIR}/include
     )
 
     # Compile options for the executable
-    target_compile_options(video2x PRIVATE
+    target_compile_options(video2x PRIVATE $<$<CONFIG:Debug>:-g -DDEBUG>)
-        -Wall
-        $<$<CONFIG:Debug>:-g -DDEBUG>
-    )
 
     # Link the executable with the shared library
     target_link_libraries(video2x PRIVATE ${ALL_LIBRARIES} libvideo2x)
@@ -277,16 +359,20 @@ endif()
 # Define the default installation directories
 if(WIN32)
     set(BIN_DESTINATION_DEFAULT ".")
-    set(INCLUDE_DESTINATION_DEFAULT "include")
+    set(INCLUDE_DESTINATION_DEFAULT "include/libvideo2x")
     set(LIB_DESTINATION_DEFAULT ".")
     set(MODEL_DESTINATION_DEFAULT ".")
 else()
     set(BIN_DESTINATION_DEFAULT "bin")
-    set(INCLUDE_DESTINATION_DEFAULT "include")
+    set(INCLUDE_DESTINATION_DEFAULT "include/libvideo2x")
     set(LIB_DESTINATION_DEFAULT "lib")
     set(MODEL_DESTINATION_DEFAULT "share/video2x")
 endif()
 
+# Explicitly set the output paths since OpenCV changes these variables
+set(EXECUTABLE_OUTPUT_PATH ${CMAKE_BINARY_DIR})
+set(LIBRARY_OUTPUT_PATH ${CMAKE_BINARY_DIR})
+
 # Set the installation directories
 set(INSTALL_BIN_DESTINATION ${BIN_DESTINATION_DEFAULT} CACHE STRING "")
 set(INSTALL_INCLUDE_DESTINATION ${INCLUDE_DESTINATION_DEFAULT} CACHE STRING "")
@@ -306,31 +392,58 @@ install(TARGETS libvideo2x
 # Install model files
 install(DIRECTORY ${CMAKE_SOURCE_DIR}/models DESTINATION ${INSTALL_MODEL_DESTINATION})
 
-# Install the executable if BUILD_VIDEO2X is enabled
+# Install the executable if BUILD_VIDEO2X_CLI is enabled
-if(BUILD_VIDEO2X)
+if(BUILD_VIDEO2X_CLI)
     install(TARGETS video2x RUNTIME DESTINATION ${INSTALL_BIN_DESTINATION})
 endif()
 
 # Install the header file
-install(FILES ${PROJECT_SOURCE_DIR}/include/libvideo2x.h DESTINATION ${INSTALL_INCLUDE_DESTINATION})
+install(FILES ${PROJECT_SOURCE_DIR}/include/libvideo2x/libvideo2x.h
+    DESTINATION ${INSTALL_INCLUDE_DESTINATION}
+)
+install(FILES ${CMAKE_CURRENT_BINARY_DIR}/libvideo2x/version.h
+    DESTINATION ${INSTALL_INCLUDE_DESTINATION}
+)
 
 # Platform-specific installation rules
 if(WIN32)
     # Install Windows-specific dependencies
-    install(FILES ${CMAKE_BINARY_DIR}/realesrgan_install/bin/realesrgan-ncnn-vulkan.dll
+    install(FILES ${CMAKE_BINARY_DIR}/realesrgan_install/bin/librealesrgan-ncnn-vulkan.dll
         DESTINATION ${INSTALL_BIN_DESTINATION}
         PERMISSIONS OWNER_READ OWNER_WRITE OWNER_EXECUTE
                     GROUP_READ GROUP_EXECUTE
                     WORLD_READ WORLD_EXECUTE
     )
-    install(FILES ${NCNN_BASE_PATH}/bin/ncnn.dll DESTINATION ${INSTALL_BIN_DESTINATION}
+    install(FILES ${FFMPEG_BASE_PATH}/bin/swscale-8.dll
+                  ${FFMPEG_BASE_PATH}/bin/avcodec-61.dll
+                  ${FFMPEG_BASE_PATH}/bin/avdevice-61.dll
+                  ${FFMPEG_BASE_PATH}/bin/avfilter-10.dll
+                  ${FFMPEG_BASE_PATH}/bin/avformat-61.dll
+                  ${FFMPEG_BASE_PATH}/bin/avutil-59.dll
+                  ${FFMPEG_BASE_PATH}/bin/postproc-58.dll
+                  ${FFMPEG_BASE_PATH}/bin/swresample-5.dll
+        DESTINATION ${INSTALL_BIN_DESTINATION}
+        PERMISSIONS OWNER_READ OWNER_WRITE OWNER_EXECUTE
+                    GROUP_READ GROUP_EXECUTE
+                    WORLD_READ WORLD_EXECUTE
+    )
+    install(FILES ${OPENCV_BASE_PATH}/build/x64/vc16/bin/opencv_world4100.dll
+                  ${OPENCV_BASE_PATH}/build/x64/vc16/bin/opencv_videoio_msmf4100_64.dll
+        DESTINATION ${INSTALL_BIN_DESTINATION}
+        PERMISSIONS OWNER_READ OWNER_WRITE OWNER_EXECUTE
+                    GROUP_READ GROUP_EXECUTE
+                    WORLD_READ WORLD_EXECUTE
+    )
+    install(FILES ${NCNN_BASE_PATH}/bin/ncnn.dll
+        DESTINATION ${INSTALL_BIN_DESTINATION}
         PERMISSIONS OWNER_READ OWNER_WRITE OWNER_EXECUTE
                     GROUP_READ GROUP_EXECUTE
                     WORLD_READ WORLD_EXECUTE
     )
 else()
     # Install Unix-specific dependencies
-    install(FILES ${REALESRGAN_LIB} DESTINATION ${INSTALL_LIB_DESTINATION}
+    install(FILES ${REALESRGAN_LIB}
+        DESTINATION ${INSTALL_LIB_DESTINATION}
         PERMISSIONS OWNER_READ OWNER_WRITE OWNER_EXECUTE
                     GROUP_READ GROUP_EXECUTE
                     WORLD_READ WORLD_EXECUTE

Dockerfile

@@ -1,14 +1,15 @@
 # Name: Video2X Dockerfile
 # Creator: K4YT3X
 # Date Created: February 3, 2022
-# Last Modified: October 7, 2024
+# Last Modified: October 21, 2024
 
 # stage 1: build the python components into wheels
 FROM docker.io/archlinux:latest AS builder
 
 # Install dependencies and create a non-root user
 RUN pacman -Syy --noconfirm \
-        base-devel ffmpeg ncnn git cmake make clang pkgconf vulkan-headers openmp sudo \
+        base-devel git cmake make clang pkgconf sudo \
+        ffmpeg ncnn vulkan-headers openmp spdlog opencv \
         nvidia-utils vulkan-radeon vulkan-intel vulkan-swrast \
     && useradd -m builder \
     && echo 'builder ALL=(ALL) NOPASSWD: ALL' > /etc/sudoers.d/builder
@@ -31,11 +32,12 @@ LABEL maintainer="K4YT3X <i@k4yt3x.com>" \
 
 ENV VK_ICD_FILENAMES=/usr/share/vulkan/icd.d/nvidia_icd.json\
 :/usr/share/vulkan/icd.d/radeon_icd.x86_64.json\
-:/usr/share/vulkan/icd.d/intel_icd.x86_64.json
+:/usr/share/vulkan/icd.d/intel_icd.x86_64.json\
+:/usr/share/vulkan/icd.d/lvp_icd.x86_64.json
 
 COPY --from=builder /tmp/video2x.pkg.tar.zst /video2x.pkg.tar.zst
-RUN pacman -Sy --noconfirm ffmpeg ncnn \
+RUN pacman -Sy --noconfirm nvidia-utils vulkan-radeon vulkan-intel vulkan-swrast \
-        nvidia-utils vulkan-radeon vulkan-intel vulkan-swrast \
+        ffmpeg ncnn spdlog opencv \
     && pacman -U --noconfirm /video2x.pkg.tar.zst \
     && rm -rf /video2x.pkg.tar.zst /var/cache/pacman/pkg/*
 

Makefile

@@ -1,9 +1,15 @@
-.PHONY: build static debug windows test-realesrgan test-libplacebo leakcheck clean
+.PHONY: build static debug clean \
+	test-realesrgan test-libplacebo \
+	memcheck-realesrgan memcheck-libplacebo \
+	heaptrack-realesrgan heaptrack-libplacebo
 
 BINDIR=build
 CC=clang
 CXX=clang++
 
+TEST_VIDEO=data/standard-test.mp4
+TEST_OUTPUT=data/output.mp4
+
 build:
 	cmake -S . -B $(BINDIR) \
 		-DCMAKE_EXPORT_COMPILE_COMMANDS=ON \
@@ -19,8 +25,7 @@ static:
 		-DCMAKE_C_COMPILER=$(CC) \
 		-DCMAKE_CXX_COMPILER=$(CXX) \
 		-DCMAKE_BUILD_TYPE=Release \
-		-DBUILD_SHARED_LIBS=OFF \
+		-DBUILD_SHARED_LIBS=OFF
-		-DUSE_SYSTEM_NCNN=OFF
 	cmake --build $(BINDIR) --config Release --parallel
 	cp $(BINDIR)/compile_commands.json .
 
@@ -45,23 +50,28 @@ debian:
 		libswscale-dev \
 		libvulkan-dev \
 		glslang-tools \
-		libomp-dev
+		libomp-dev \
+		libspdlog-dev \
+		libopencv-dev
 	cmake -B /tmp/build -S . -DUSE_SYSTEM_NCNN=OFF \
-		-DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ \
+		-DCMAKE_C_COMPILER=$(CC) -DCMAKE_CXX_COMPILER=$(CXX) \
 		-DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/tmp/install \
 		-DINSTALL_BIN_DESTINATION=. -DINSTALL_INCLUDE_DESTINATION=include \
 		-DINSTALL_LIB_DESTINATION=. -DINSTALL_MODEL_DESTINATION=.
 	cmake --build /tmp/build --config Release --target install --parallel
 
+clean:
+	rm -vrf $(BINDIR) data/output*.* heaptrack*.zst valgrind.log
+
 test-realesrgan:
-	LD_LIBRARY_PATH=$(BINDIR) $(BINDIR)/video2x -i data/standard-test.mp4 -o data/output.mp4 \
+	LD_LIBRARY_PATH=$(BINDIR) $(BINDIR)/video2x -i $(TEST_VIDEO) -o $(TEST_OUTPUT) \
-		-f realesrgan -r 4 --model realesr-animevideov3
+		-f realesrgan -r 4 -m realesr-animevideov3
 
 test-libplacebo:
-	LD_LIBRARY_PATH=$(BINDIR) $(BINDIR)/video2x -i data/standard-test.mp4 -o data/output.mp4 \
+	LD_LIBRARY_PATH=$(BINDIR) $(BINDIR)/video2x -i $(TEST_VIDEO) -o $(TEST_OUTPUT) \
-		-f libplacebo -w 1920 -h 1080 -s anime4k-mode-a
+		-f libplacebo -w 1920 -h 1080 -s anime4k-v4-a
 
-leakcheck-realesrgan:
+memcheck-realesrgan:
 	LD_LIBRARY_PATH=$(BINDIR) valgrind \
 		--tool=memcheck \
 		--leak-check=full \
@@ -70,11 +80,11 @@ leakcheck-realesrgan:
 		--show-reachable=yes \
 		--verbose --log-file="valgrind.log" \
 		$(BINDIR)/video2x \
-		-i data/standard-test.mp4 -o data/output.mp4 \
+		-i $(TEST_VIDEO) -o $(TEST_OUTPUT) \
-		-f realesrgan -r 2 --model realesr-animevideov3 \
+		-f realesrgan -r 2 -m realesr-animevideov3 \
 		-p veryfast -b 1000000 -q 30
 
-leakcheck-libplacebo:
+memcheck-libplacebo:
 	LD_LIBRARY_PATH=$(BINDIR) valgrind \
 		--tool=memcheck \
 		--leak-check=full \
@@ -83,9 +93,20 @@ leakcheck-libplacebo:
 		--show-reachable=yes \
 		--verbose --log-file="valgrind.log" \
 		$(BINDIR)/video2x \
-		-i data/standard-test.mp4 -o data/output.mp4 \
+		-i $(TEST_VIDEO) -o $(TEST_OUTPUT) \
-		-f libplacebo -w 1920 -h 1080 -s anime4k-mode-a \
+		-f libplacebo -w 1920 -h 1080 -s anime4k-v4-a \
 		-p veryfast -b 1000000 -q 30
 
-clean:
+heaptrack-realesrgan:
-	rm -rf $(BINDIR)
+	LD_LIBRARY_PATH=$(BINDIR) HEAPTRACK_ENABLE_DEBUGINFOD=1 heaptrack \
+		$(BINDIR)/video2x \
+		-i $(TEST_VIDEO) -o $(TEST_OUTPUT) \
+		-f realesrgan -r 4 -m realesr-animevideov3 \
+		-p veryfast -b 1000000 -q 30
+
+heaptrack-libplacebo:
+	LD_LIBRARY_PATH=$(BINDIR) HEAPTRACK_ENABLE_DEBUGINFOD=1 heaptrack \
+		$(BINDIR)/video2x \
+		-i $(TEST_VIDEO) -o $(TEST_OUTPUT) \
+		-f libplacebo -w 1920 -h 1080 -s anime4k-v4-a \
+		-p veryfast -b 1000000 -q 30

PKGBUILD

@@ -1,11 +1,11 @@
 pkgname=video2x
-pkgver=r862.f590ead
+pkgver=r843.e09f348
 pkgrel=1
-pkgdesc="A lossless video super resolution framework"
+pkgdesc="A machine learning-based lossless video super resolution framework"
 arch=('x86_64')
 url="https://github.com/k4yt3x/video2x"
 license=('AGPL3')
-depends=('ffmpeg' 'ncnn' 'vulkan-driver')
+depends=('ffmpeg' 'ncnn' 'vulkan-driver' 'opencv' 'spdlog')
 makedepends=('git' 'cmake' 'make' 'clang' 'pkgconf' 'vulkan-headers' 'openmp')
 
 pkgver() {

README.md

@@ -8,11 +8,14 @@
    <img src="https://img.shields.io/badge/dynamic/json?color=%23e85b46&label=Patreon&query=data.attributes.patron_count&suffix=%20patrons&url=https%3A%2F%2Fwww.patreon.com%2Fapi%2Fcampaigns%2F4507807&style=flat-square"/>
 </p>
 
+> [!IMPORTANT]
+> Versions 4 and 5 have reached end-of-life (EOL) status. Due to limited development resources, issues related to any version earlier than 6 will no longer be addressed.
+
 ## 🌟 Version 6.0.0 Preview
 
-**[Direct download link for Windows](https://github.com/k4yt3x/video2x/releases/download/6.0.0-beta.2/video2x-qt6-windows-amd64.zip)**
+**[Direct download link for Windows (Installer)](https://github.com/k4yt3x/video2x/releases/download/6.0.0-beta.5/video2x-qt6-windows-amd64-installer.exe)**
 
-![6.0.0-beta-screenshot](https://github.com/user-attachments/assets/bde4e4e2-2f97-412f-8e34-848f384be720)
+![6.0.0-beta-screenshot](https://github.com/user-attachments/assets/e4318eaf-f726-4193-885f-030593a5078a)
 
 Version 6.0.0 is a complete rewrite of this project in C/C++. It:
 

include/libvideo2x/decoder.h

@@ -9,10 +9,10 @@ extern "C" {
 int init_decoder(
     AVHWDeviceType hw_type,
     AVBufferRef *hw_ctx,
-    const char *input_filename,
+    const char *in_fname,
     AVFormatContext **fmt_ctx,
     AVCodecContext **dec_ctx,
-    int *video_stream_index
+    int *vstream_idx
 );
 
 #endif  // DECODER_H

include/libvideo2x/encoder.h

@@ -11,21 +11,21 @@ extern "C" {
 
 int init_encoder(
     AVBufferRef *hw_ctx,
-    const char *output_filename,
+    const char *out_fname,
     AVFormatContext *ifmt_ctx,
     AVFormatContext **ofmt_ctx,
     AVCodecContext **enc_ctx,
     AVCodecContext *dec_ctx,
     EncoderConfig *encoder_config,
-    int video_stream_index,
+    int vstream_idx,
-    int **stream_mapping
+    int **stream_map
 );
 
-int encode_and_write_frame(
+int write_frame(
     AVFrame *frame,
     AVCodecContext *enc_ctx,
     AVFormatContext *ofmt_ctx,
-    int video_stream_index
+    int vstream_idx
 );
 
 int flush_encoder(AVCodecContext *enc_ctx, AVFormatContext *ofmt_ctx);

include/libvideo2x/filter.h

@@ -12,10 +12,10 @@ extern "C" {
 // Abstract base class for filters
 class Filter {
    public:
-    virtual ~Filter() {}
+    virtual ~Filter() = default;
     virtual int init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVBufferRef *hw_ctx) = 0;
-    virtual int process_frame(AVFrame *input_frame, AVFrame **output_frame) = 0;
+    virtual int process_frame(AVFrame *in_frame, AVFrame **out_frame) = 0;
-    virtual int flush(std::vector<AVFrame *> &processed_frames) = 0;
+    virtual int flush(std::vector<AVFrame *> &_) { return 0; }
 };
 
 #endif  // FILTER_H

include/libvideo2x/libplacebo.h

@@ -14,8 +14,8 @@ int init_libplacebo(
     AVFilterContext **buffersrc_ctx,
     AVFilterContext **buffersink_ctx,
     AVCodecContext *dec_ctx,
-    int output_width,
+    int out_width,
-    int output_height,
+    int out_height,
     const std::filesystem::path &shader_path
 );
 

include/libvideo2x/libplacebo_filter.h

@@ -17,26 +17,27 @@ class LibplaceboFilter : public Filter {
     AVFilterGraph *filter_graph;
     AVFilterContext *buffersrc_ctx;
     AVFilterContext *buffersink_ctx;
-    int output_width;
+    int out_width;
-    int output_height;
+    int out_height;
     const std::filesystem::path shader_path;
-    AVRational output_time_base;
+    AVRational in_time_base;
+    AVRational out_time_base;
 
    public:
     // Constructor
     LibplaceboFilter(int width, int height, const std::filesystem::path &shader_path);
 
     // Destructor
-    virtual ~LibplaceboFilter();
+    virtual ~LibplaceboFilter() override;
 
     // Initializes the filter with decoder and encoder contexts
     int init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVBufferRef *hw_ctx) override;
 
     // Processes an input frame and returns the processed frame
-    int process_frame(AVFrame *input_frame, AVFrame **output_frame) override;
+    int process_frame(AVFrame *in_frame, AVFrame **out_frame) override;
 
     // Flushes any remaining frames
-    int flush(std::vector<AVFrame *> &processed_frames) override;
+    int flush(std::vector<AVFrame *> &flushed_frames) override;
 };
 
 #endif  // LIBPLACEBO_FILTER_H

include/libvideo2x/libvideo2x.h

@@ -28,10 +28,21 @@ enum FilterType {
     FILTER_REALESRGAN
 };
 
+// Enum to specify log level
+enum Libvideo2xLogLevel {
+    LIBVIDEO2X_LOG_LEVEL_TRACE,
+    LIBVIDEO2X_LOG_LEVEL_DEBUG,
+    LIBVIDEO2X_LOG_LEVEL_INFO,
+    LIBVIDEO2X_LOG_LEVEL_WARNING,
+    LIBVIDEO2X_LOG_LEVEL_ERROR,
+    LIBVIDEO2X_LOG_LEVEL_CRITICAL,
+    LIBVIDEO2X_LOG_LEVEL_OFF
+};
+
 // Configuration for Libplacebo filter
 struct LibplaceboConfig {
-    int output_width;
+    int out_width;
-    int output_height;
+    int out_height;
     const char *shader_path;
 };
 
@@ -54,8 +65,8 @@ struct FilterConfig {
 
 // Encoder configuration
 struct EncoderConfig {
-    int output_width;
+    int out_width;
-    int output_height;
+    int out_height;
     bool copy_streams;
     enum AVCodecID codec;
     enum AVPixelFormat pix_fmt;
@@ -76,8 +87,9 @@ struct VideoProcessingContext {
 
 // C-compatible process_video function
 LIBVIDEO2X_API int process_video(
-    const char *input_filename,
+    const char *in_fname,
-    const char *output_filename,
+    const char *out_fname,
+    enum Libvideo2xLogLevel log_level,
     bool benchmark,
     enum AVHWDeviceType hw_device_type,
     const struct FilterConfig *filter_config,

include/libvideo2x/realesrgan_filter.h

@@ -20,9 +20,9 @@ class RealesrganFilter : public Filter {
     const char *model;
     const std::filesystem::path custom_model_param_path;
     const std::filesystem::path custom_model_bin_path;
-    AVRational input_time_base;
+    AVRational in_time_base;
-    AVRational output_time_base;
+    AVRational out_time_base;
-    AVPixelFormat output_pix_fmt;
+    AVPixelFormat out_pix_fmt;
 
    public:
     // Constructor
@@ -31,21 +31,18 @@ class RealesrganFilter : public Filter {
         bool tta_mode = false,
         int scaling_factor = 4,
         const char *model = "realesr-animevideov3",
-        const std::filesystem::path custom_model_bin_pathmodel_param_path = std::filesystem::path(),
+        const std::filesystem::path custom_model_param_path = std::filesystem::path(),
-        const std::filesystem::path custom_model_bin_pathmodel_bin_path = std::filesystem::path()
+        const std::filesystem::path custom_model_bin_path = std::filesystem::path()
     );
 
     // Destructor
-    virtual ~RealesrganFilter();
+    virtual ~RealesrganFilter() override;
 
     // Initializes the filter with decoder and encoder contexts
     int init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVBufferRef *hw_ctx) override;
 
     // Processes an input frame and returns the processed frame
-    int process_frame(AVFrame *input_frame, AVFrame **output_frame) override;
+    int process_frame(AVFrame *in_frame, AVFrame **out_frame) override;
-
-    // Flushes any remaining frames (if necessary)
-    int flush(std::vector<AVFrame *> &processed_frames) override;
 };
 
 #endif

include/libvideo2x/version.h.in

@@ -0,0 +1,6 @@
+#ifndef VERSION_H
+#define VERSION_H
+
+#define LIBVIDEO2X_VERSION_STRING "@PROJECT_VERSION@"
+
+#endif  // VERSION_H

scripts/download_anime4k_glsl.py

@@ -1,46 +0,0 @@
-#!/usr/bin/python
-# -*- coding: utf-8 -*-
-import shutil
-from pathlib import Path
-
-import requests
-
-ANIME4K_COMMIT = "master"
-GITHUB_GLSL_ROOT = (
-    f"https://raw.githubusercontent.com/bloc97/Anime4K/{ANIME4K_COMMIT}/glsl"
-)
-SHADERS_DIR = Path(__file__).parent.parent / "data"
-
-
-def download_and_combine_files():
-
-    modes = {
-        "ModeA": [
-            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Clamp_Highlights.glsl",
-            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_CNN_VL.glsl",
-            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_VL.glsl",
-            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x2.glsl",
-            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x4.glsl",
-            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_M.glsl",
-        ]
-    }
-
-    for mode in modes:
-        file_contents = ""
-        for file in modes[mode]:
-            response = requests.get(file, timeout=5)
-            response.raise_for_status()
-            file_contents += response.text + "\n"
-
-        with (SHADERS_DIR / Path(f"Anime4K_{mode}.glsl")).open("w") as output_file:
-            output_file.write(file_contents)
-
-
-if __name__ == "__main__":
-    # clear shaders directory
-    if SHADERS_DIR.exists():
-        shutil.rmtree(SHADERS_DIR)
-    SHADERS_DIR.mkdir(exist_ok=True)
-
-    # download and combine shaders
-    download_and_combine_files()

scripts/download_merge_anime4k_glsl.py

@@ -0,0 +1,98 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+import shutil
+from pathlib import Path
+
+import requests
+
+ANIME4K_COMMIT = "master"
+GITHUB_GLSL_ROOT = (
+    f"https://raw.githubusercontent.com/bloc97/Anime4K/{ANIME4K_COMMIT}/glsl"
+)
+SHADERS_DIR = Path(__file__).parent.parent / "models" / "libplacebo"
+
+
+def download_and_combine_files():
+    modes = {
+        "a": [
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Clamp_Highlights.glsl",
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_CNN_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x2.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x4.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_M.glsl",
+        ],
+        "b": [
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Clamp_Highlights.glsl",
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_CNN_Soft_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x2.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x4.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_M.glsl",
+        ],
+        "c": [
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Clamp_Highlights.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale+Denoise/Anime4K_Upscale_Denoise_CNN_x2_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x2.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x4.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_M.glsl",
+        ],
+        "a+a": [
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Clamp_Highlights.glsl",
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_CNN_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_CNN_M.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x2.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x4.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_M.glsl",
+        ],
+        "b+b": [
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Clamp_Highlights.glsl",
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_CNN_Soft_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x2.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x4.glsl",
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_CNN_Soft_M.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_M.glsl",
+        ],
+        "c+a": [
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Clamp_Highlights.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale+Denoise/Anime4K_Upscale_Denoise_CNN_x2_VL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x2.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_AutoDownscalePre_x4.glsl",
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_CNN_M.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_M.glsl",
+        ],
+        "gan": [
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_GAN_UUL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_GAN_x4_UUL.glsl",
+            f"{GITHUB_GLSL_ROOT}/Restore/Anime4K_Restore_CNN_Soft_M.glsl",
+            f"{GITHUB_GLSL_ROOT}/Upscale/Anime4K_Upscale_CNN_x2_M.glsl",
+        ],
+    }
+
+    for mode in modes:
+        file_contents = ""
+        for file in modes[mode]:
+            response = requests.get(file, timeout=5)
+            response.raise_for_status()
+            file_contents += response.text + "\n"
+
+        version = "v4"
+        if mode == "gan":
+            version = "v4.1"
+
+        with (SHADERS_DIR / Path(f"anime4k-{version}-{mode}.glsl")).open(
+            "w"
+        ) as output_file:
+            output_file.write(file_contents)
+
+
+if __name__ == "__main__":
+    # clear shaders directory
+    if SHADERS_DIR.exists():
+        shutil.rmtree(SHADERS_DIR)
+    SHADERS_DIR.mkdir(exist_ok=True)
+
+    # download and combine shaders
+    download_and_combine_files()

src/conversions.cpp

@@ -1,12 +1,15 @@
 #include "conversions.h"
 
+#include <cstddef>
 #include <cstdio>
 
+#include <spdlog/spdlog.h>
+
 // Convert AVFrame format
 AVFrame *convert_avframe_pix_fmt(AVFrame *src_frame, AVPixelFormat pix_fmt) {
     AVFrame *dst_frame = av_frame_alloc();
     if (dst_frame == nullptr) {
-        fprintf(stderr, "Failed to allocate destination AVFrame.\n");
+        spdlog::error("Failed to allocate destination AVFrame.");
         return nullptr;
     }
 
@@ -16,7 +19,7 @@ AVFrame *convert_avframe_pix_fmt(AVFrame *src_frame, AVPixelFormat pix_fmt) {
 
     // Allocate memory for the converted frame
     if (av_frame_get_buffer(dst_frame, 32) < 0) {
-        fprintf(stderr, "Failed to allocate memory for AVFrame.\n");
+        spdlog::error("Failed to allocate memory for AVFrame.");
         av_frame_free(&dst_frame);
         return nullptr;
     }
@@ -36,7 +39,7 @@ AVFrame *convert_avframe_pix_fmt(AVFrame *src_frame, AVPixelFormat pix_fmt) {
     );
 
     if (sws_ctx == nullptr) {
-        fprintf(stderr, "Failed to initialize swscale context.\n");
+        spdlog::error("Failed to initialize swscale context.");
         av_frame_free(&dst_frame);
         return nullptr;
     }
@@ -66,7 +69,7 @@ ncnn::Mat avframe_to_ncnn_mat(AVFrame *frame) {
     if (frame->format != AV_PIX_FMT_BGR24) {
         converted_frame = convert_avframe_pix_fmt(frame, AV_PIX_FMT_BGR24);
         if (!converted_frame) {
-            fprintf(stderr, "Failed to convert AVFrame to BGR24.\n");
+            spdlog::error("Failed to convert AVFrame to BGR24.");
             return ncnn::Mat();
         }
     } else {
@@ -77,14 +80,16 @@ ncnn::Mat avframe_to_ncnn_mat(AVFrame *frame) {
     // Allocate a new ncnn::Mat and copy the data
     int width = converted_frame->width;
     int height = converted_frame->height;
-    ncnn::Mat ncnn_image = ncnn::Mat(width, height, (size_t)3, 3);  // BGR has 3 channels
+    ncnn::Mat ncnn_image = ncnn::Mat(width, height, static_cast<size_t>(3), 3);
 
     // Manually copy the pixel data from AVFrame to the new ncnn::Mat
     const uint8_t *src_data = converted_frame->data[0];
     for (int y = 0; y < height; y++) {
         uint8_t *dst_row = ncnn_image.row<uint8_t>(y);
         const uint8_t *src_row = src_data + y * converted_frame->linesize[0];
-        memcpy(dst_row, src_row, width * 3);  // Copy 3 channels (BGR) per pixel
+
+        // Copy 3 channels (BGR) per pixel
+        memcpy(dst_row, src_row, static_cast<size_t>(width) * 3);
     }
 
     // If we allocated a converted frame, free it
@@ -102,7 +107,7 @@ AVFrame *ncnn_mat_to_avframe(const ncnn::Mat &mat, AVPixelFormat pix_fmt) {
     // Step 1: Allocate a destination AVFrame for the specified pixel format
     AVFrame *dst_frame = av_frame_alloc();
     if (!dst_frame) {
-        fprintf(stderr, "Failed to allocate destination AVFrame.\n");
+        spdlog::error("Failed to allocate destination AVFrame.");
         return nullptr;
     }
 
@@ -112,7 +117,7 @@ AVFrame *ncnn_mat_to_avframe(const ncnn::Mat &mat, AVPixelFormat pix_fmt) {
 
     // Allocate memory for the frame buffer
     if (av_frame_get_buffer(dst_frame, 32) < 0) {
-        fprintf(stderr, "Failed to allocate memory for destination AVFrame.\n");
+        spdlog::error("Failed to allocate memory for destination AVFrame.");
         av_frame_free(&dst_frame);
         return nullptr;
     }
@@ -120,7 +125,7 @@ AVFrame *ncnn_mat_to_avframe(const ncnn::Mat &mat, AVPixelFormat pix_fmt) {
     // Step 2: Convert ncnn::Mat to BGR AVFrame
     AVFrame *bgr_frame = av_frame_alloc();
     if (!bgr_frame) {
-        fprintf(stderr, "Failed to allocate intermediate BGR AVFrame.\n");
+        spdlog::error("Failed to allocate intermediate BGR AVFrame.");
         av_frame_free(&dst_frame);
         return nullptr;
     }
@@ -131,7 +136,7 @@ AVFrame *ncnn_mat_to_avframe(const ncnn::Mat &mat, AVPixelFormat pix_fmt) {
 
     // Allocate memory for the intermediate BGR frame
     if (av_frame_get_buffer(bgr_frame, 32) < 0) {
-        fprintf(stderr, "Failed to allocate memory for BGR AVFrame.\n");
+        spdlog::error("Failed to allocate memory for BGR AVFrame.");
         av_frame_free(&dst_frame);
         av_frame_free(&bgr_frame);
         return nullptr;
@@ -141,7 +146,9 @@ AVFrame *ncnn_mat_to_avframe(const ncnn::Mat &mat, AVPixelFormat pix_fmt) {
     for (int y = 0; y < mat.h; y++) {
         uint8_t *dst_row = bgr_frame->data[0] + y * bgr_frame->linesize[0];
         const uint8_t *src_row = mat.row<const uint8_t>(y);
-        memcpy(dst_row, src_row, mat.w * 3);  // Copy 3 channels (BGR) per pixel
+
+        // Copy 3 channels (BGR) per pixel
+        memcpy(dst_row, src_row, static_cast<size_t>(mat.w) * 3);
     }
 
     // Step 3: Convert the BGR frame to the desired pixel format
@@ -159,7 +166,7 @@ AVFrame *ncnn_mat_to_avframe(const ncnn::Mat &mat, AVPixelFormat pix_fmt) {
     );
 
     if (sws_ctx == nullptr) {
-        fprintf(stderr, "Failed to initialize swscale context.\n");
+        spdlog::error("Failed to initialize swscale context.");
         av_frame_free(&bgr_frame);
         av_frame_free(&dst_frame);
         return nullptr;
@@ -181,7 +188,7 @@ AVFrame *ncnn_mat_to_avframe(const ncnn::Mat &mat, AVPixelFormat pix_fmt) {
     av_frame_free(&bgr_frame);
 
     if (ret != dst_frame->height) {
-        fprintf(stderr, "Failed to convert BGR AVFrame to destination pixel format.\n");
+        spdlog::error("Failed to convert BGR AVFrame to destination pixel format.");
         av_frame_free(&dst_frame);
         return nullptr;
     }

src/decoder.cpp

@@ -4,45 +4,47 @@
 #include <stdlib.h>
 #include <string.h>
 
+#include <spdlog/spdlog.h>
+
 static enum AVPixelFormat hw_pix_fmt = AV_PIX_FMT_NONE;
 
 // Callback function to choose the hardware-accelerated pixel format
-static enum AVPixelFormat get_hw_format(AVCodecContext *ctx, const enum AVPixelFormat *pix_fmts) {
+static enum AVPixelFormat get_hw_format(AVCodecContext *_, const enum AVPixelFormat *pix_fmts) {
     for (const enum AVPixelFormat *p = pix_fmts; *p != AV_PIX_FMT_NONE; p++) {
         if (*p == hw_pix_fmt) {
             return *p;
         }
     }
-    fprintf(stderr, "Failed to get HW surface format.\n");
+    spdlog::error("Failed to get HW surface format.");
     return AV_PIX_FMT_NONE;
 }
 
 int init_decoder(
     AVHWDeviceType hw_type,
     AVBufferRef *hw_ctx,
-    const char *input_filename,
+    const char *in_fname,
     AVFormatContext **fmt_ctx,
     AVCodecContext **dec_ctx,
-    int *video_stream_index
+    int *vstream_idx
 ) {
     AVFormatContext *ifmt_ctx = NULL;
     AVCodecContext *codec_ctx = NULL;
     int ret;
 
-    if ((ret = avformat_open_input(&ifmt_ctx, input_filename, NULL, NULL)) < 0) {
+    if ((ret = avformat_open_input(&ifmt_ctx, in_fname, NULL, NULL)) < 0) {
-        fprintf(stderr, "Could not open input file '%s'\n", input_filename);
+        spdlog::error("Could not open input file '{}'", in_fname);
         return ret;
     }
 
     if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
-        fprintf(stderr, "Failed to retrieve input stream information\n");
+        spdlog::error("Failed to retrieve input stream information");
         return ret;
     }
 
     // Find the first video stream
     ret = av_find_best_stream(ifmt_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, NULL, 0);
     if (ret < 0) {
-        fprintf(stderr, "Could not find video stream in the input, aborting\n");
+        spdlog::error("Could not find video stream in the input file");
         return ret;
     }
 
@@ -52,13 +54,16 @@ int init_decoder(
     // Set up the decoder
     const AVCodec *decoder = avcodec_find_decoder(video_stream->codecpar->codec_id);
     if (!decoder) {
-        fprintf(stderr, "Failed to find decoder for stream #%u\n", stream_index);
+        spdlog::error(
+            "Failed to find decoder for codec ID {}",
+            static_cast<int>(video_stream->codecpar->codec_id)
+        );
         return AVERROR_DECODER_NOT_FOUND;
     }
 
     codec_ctx = avcodec_alloc_context3(decoder);
     if (!codec_ctx) {
-        fprintf(stderr, "Failed to allocate the decoder context\n");
+        spdlog::error("Failed to allocate the decoder context");
         return AVERROR(ENOMEM);
     }
 
@@ -71,9 +76,8 @@ int init_decoder(
         for (int i = 0;; i++) {
             const AVCodecHWConfig *config = avcodec_get_hw_config(decoder, i);
             if (config == nullptr) {
-                fprintf(
+                spdlog::error(
-                    stderr,
+                    "Decoder {} does not support device type {}.",
-                    "Decoder %s does not support device type %s.\n",
                     decoder->name,
                     av_hwdevice_get_type_name(hw_type)
                 );
@@ -90,7 +94,7 @@ int init_decoder(
     }
 
     if ((ret = avcodec_parameters_to_context(codec_ctx, video_stream->codecpar)) < 0) {
-        fprintf(stderr, "Failed to copy decoder parameters to input decoder context\n");
+        spdlog::error("Failed to copy decoder parameters to input decoder context");
         return ret;
     }
 
@@ -100,13 +104,13 @@ int init_decoder(
     codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, video_stream, NULL);
 
     if ((ret = avcodec_open2(codec_ctx, decoder, NULL)) < 0) {
-        fprintf(stderr, "Failed to open decoder for stream #%u\n", stream_index);
+        spdlog::error("Failed to open decoder for stream #{}", stream_index);
         return ret;
     }
 
     *fmt_ctx = ifmt_ctx;
     *dec_ctx = codec_ctx;
-    *video_stream_index = stream_index;
+    *vstream_idx = stream_index;
 
     return 0;
 }

src/encoder.cpp

@@ -4,12 +4,14 @@
 #include <stdlib.h>
 #include <string.h>
 
+#include <spdlog/spdlog.h>
+
 #include "conversions.h"
 
 static enum AVPixelFormat get_encoder_default_pix_fmt(const AVCodec *encoder) {
     const enum AVPixelFormat *p = encoder->pix_fmts;
     if (!p) {
-        fprintf(stderr, "No pixel formats supported by encoder\n");
+        spdlog::error("No pixel formats supported by encoder");
         return AV_PIX_FMT_NONE;
     }
     return *p;
@@ -17,31 +19,30 @@ static enum AVPixelFormat get_encoder_default_pix_fmt(const AVCodec *encoder) {
 
 int init_encoder(
     AVBufferRef *hw_ctx,
-    const char *output_filename,
+    const char *out_fname,
     AVFormatContext *ifmt_ctx,
     AVFormatContext **ofmt_ctx,
     AVCodecContext **enc_ctx,
     AVCodecContext *dec_ctx,
     EncoderConfig *encoder_config,
-    int video_stream_index,
+    int vstream_idx,
-    int **stream_mapping
+    int **stream_map
 ) {
     AVFormatContext *fmt_ctx = NULL;
     AVCodecContext *codec_ctx = NULL;
     int stream_index = 0;
     int ret;
 
-    avformat_alloc_output_context2(&fmt_ctx, NULL, NULL, output_filename);
+    avformat_alloc_output_context2(&fmt_ctx, NULL, NULL, out_fname);
     if (!fmt_ctx) {
-        fprintf(stderr, "Could not create output context\n");
+        spdlog::error("Could not create output context");
         return AVERROR_UNKNOWN;
     }
 
     const AVCodec *encoder = avcodec_find_encoder(encoder_config->codec);
     if (!encoder) {
-        fprintf(
+        spdlog::error(
-            stderr,
+            "Required video encoder not found for vcodec {}",
-            "Required video encoder not found for vcodec %s\n",
             avcodec_get_name(encoder_config->codec)
         );
         return AVERROR_ENCODER_NOT_FOUND;
@@ -50,13 +51,13 @@ int init_encoder(
     // Create a new video stream in the output file
     AVStream *out_stream = avformat_new_stream(fmt_ctx, NULL);
     if (!out_stream) {
-        fprintf(stderr, "Failed to allocate the output video stream\n");
+        spdlog::error("Failed to allocate the output video stream");
         return AVERROR_UNKNOWN;
     }
 
     codec_ctx = avcodec_alloc_context3(encoder);
     if (!codec_ctx) {
-        fprintf(stderr, "Failed to allocate the encoder context\n");
+        spdlog::error("Failed to allocate the encoder context");
         return AVERROR(ENOMEM);
     }
 
@@ -66,8 +67,8 @@ int init_encoder(
     }
 
     // Set encoding parameters
-    codec_ctx->height = encoder_config->output_height;
+    codec_ctx->height = encoder_config->out_height;
-    codec_ctx->width = encoder_config->output_width;
+    codec_ctx->width = encoder_config->out_width;
     codec_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
     codec_ctx->bit_rate = encoder_config->bit_rate;
 
@@ -79,20 +80,28 @@ int init_encoder(
         // Fall back to the default pixel format
         codec_ctx->pix_fmt = get_encoder_default_pix_fmt(encoder);
         if (codec_ctx->pix_fmt == AV_PIX_FMT_NONE) {
-            fprintf(stderr, "Could not get the default pixel format for the encoder\n");
+            spdlog::error("Could not get the default pixel format for the encoder");
             return AVERROR(EINVAL);
         }
     }
 
-    // Set the time base
+    // Set the output video's time base
-    codec_ctx->time_base = av_inv_q(dec_ctx->framerate);
+    if (dec_ctx->time_base.num > 0 && dec_ctx->time_base.den > 0) {
-    if (codec_ctx->time_base.num == 0 || codec_ctx->time_base.den == 0) {
+        codec_ctx->time_base = dec_ctx->time_base;
+    } else {
         codec_ctx->time_base = av_inv_q(av_guess_frame_rate(ifmt_ctx, out_stream, NULL));
     }
 
+    // Set the output video's frame rate
+    if (dec_ctx->framerate.num > 0 && dec_ctx->framerate.den > 0) {
+        codec_ctx->framerate = dec_ctx->framerate;
+    } else {
+        codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, out_stream, NULL);
+    }
+
     // Set the CRF and preset for any codecs that support it
     char crf_str[16];
-    snprintf(crf_str, sizeof(crf_str), "%.f", encoder_config->crf);
+    snprintf(crf_str, sizeof(crf_str), "%.f", static_cast<double>(encoder_config->crf));
     av_opt_set(codec_ctx->priv_data, "crf", crf_str, 0);
     av_opt_set(codec_ctx->priv_data, "preset", encoder_config->preset, 0);
 
@@ -101,71 +110,74 @@ int init_encoder(
     }
 
     if ((ret = avcodec_open2(codec_ctx, encoder, NULL)) < 0) {
-        fprintf(stderr, "Cannot open video encoder\n");
+        spdlog::error("Cannot open video encoder");
         return ret;
     }
 
     ret = avcodec_parameters_from_context(out_stream->codecpar, codec_ctx);
     if (ret < 0) {
-        fprintf(stderr, "Failed to copy encoder parameters to output video stream\n");
+        spdlog::error("Failed to copy encoder parameters to output video stream");
         return ret;
     }
 
     out_stream->time_base = codec_ctx->time_base;
+    out_stream->avg_frame_rate = codec_ctx->framerate;
+    out_stream->r_frame_rate = codec_ctx->framerate;
 
     if (encoder_config->copy_streams) {
         // Allocate the stream map
-        *stream_mapping = (int *)av_malloc_array(ifmt_ctx->nb_streams, sizeof(**stream_mapping));
+        *stream_map =
-        if (!*stream_mapping) {
+            reinterpret_cast<int *>(av_malloc_array(ifmt_ctx->nb_streams, sizeof(**stream_map)));
-            fprintf(stderr, "Could not allocate stream mapping\n");
+        if (!*stream_map) {
+            spdlog::error("Could not allocate stream mapping");
             return AVERROR(ENOMEM);
         }
 
         // Map the video stream
-        (*stream_mapping)[video_stream_index] = stream_index++;
+        (*stream_map)[vstream_idx] = stream_index++;
 
         // Loop through each stream in the input file
-        for (int i = 0; i < ifmt_ctx->nb_streams; i++) {
+        for (int i = 0; i < static_cast<int>(ifmt_ctx->nb_streams); i++) {
             AVStream *in_stream = ifmt_ctx->streams[i];
             AVCodecParameters *in_codecpar = in_stream->codecpar;
 
-            if (i == video_stream_index) {
+            if (i == vstream_idx) {
                 // Video stream is already handled
                 continue;
             }
 
             if (in_codecpar->codec_type != AVMEDIA_TYPE_AUDIO &&
                 in_codecpar->codec_type != AVMEDIA_TYPE_SUBTITLE) {
-                (*stream_mapping)[i] = -1;
+                (*stream_map)[i] = -1;
                 continue;
             }
 
             // Create corresponding output stream
-            AVStream *out_stream = avformat_new_stream(fmt_ctx, NULL);
+            AVStream *out_copied_stream = avformat_new_stream(fmt_ctx, NULL);
-            if (!out_stream) {
+            if (!out_copied_stream) {
-                fprintf(stderr, "Failed allocating output stream\n");
+                spdlog::error("Failed allocating output stream");
                 return AVERROR_UNKNOWN;
             }
 
-            ret = avcodec_parameters_copy(out_stream->codecpar, in_codecpar);
+            ret = avcodec_parameters_copy(out_copied_stream->codecpar, in_codecpar);
             if (ret < 0) {
-                fprintf(stderr, "Failed to copy codec parameters\n");
+                spdlog::error("Failed to copy codec parameters");
                 return ret;
             }
-            out_stream->codecpar->codec_tag = 0;
+            out_copied_stream->codecpar->codec_tag = 0;
 
             // Copy time base
-            out_stream->time_base = in_stream->time_base;
+            out_copied_stream->time_base = in_stream->time_base;
 
-            (*stream_mapping)[i] = stream_index++;
+            (*stream_map)[i] = stream_index++;
         }
     }
 
     // Open the output file
     if (!(fmt_ctx->oformat->flags & AVFMT_NOFILE)) {
-        ret = avio_open(&fmt_ctx->pb, output_filename, AVIO_FLAG_WRITE);
+        ret = avio_open(&fmt_ctx->pb, out_fname, AVIO_FLAG_WRITE);
         if (ret < 0) {
-            fprintf(stderr, "Could not open output file '%s'\n", output_filename);
+            spdlog::error("Could not open output file '{}'", out_fname);
             return ret;
         }
     }
@@ -176,35 +188,40 @@ int init_encoder(
     return 0;
 }
 
-int encode_and_write_frame(
+int write_frame(
     AVFrame *frame,
     AVCodecContext *enc_ctx,
     AVFormatContext *ofmt_ctx,
-    int video_stream_index
+    int vstream_idx
 ) {
+    AVFrame *converted_frame = nullptr;
     int ret;
 
     // Convert the frame to the encoder's pixel format if needed
     if (frame->format != enc_ctx->pix_fmt) {
-        AVFrame *converted_frame = convert_avframe_pix_fmt(frame, enc_ctx->pix_fmt);
+        converted_frame = convert_avframe_pix_fmt(frame, enc_ctx->pix_fmt);
         if (!converted_frame) {
-            fprintf(stderr, "Error converting frame to encoder's pixel format\n");
+            spdlog::error("Error converting frame to encoder's pixel format");
             return AVERROR_EXTERNAL;
         }
 
         converted_frame->pts = frame->pts;
-        frame = converted_frame;
     }
 
     AVPacket *enc_pkt = av_packet_alloc();
     if (!enc_pkt) {
-        fprintf(stderr, "Could not allocate AVPacket\n");
+        spdlog::error("Could not allocate AVPacket");
         return AVERROR(ENOMEM);
     }
 
-    ret = avcodec_send_frame(enc_ctx, frame);
+    if (converted_frame != nullptr) {
+        ret = avcodec_send_frame(enc_ctx, converted_frame);
+        av_frame_free(&converted_frame);
+    } else {
+        ret = avcodec_send_frame(enc_ctx, frame);
+    }
     if (ret < 0) {
-        fprintf(stderr, "Error sending frame to encoder\n");
+        spdlog::error("Error sending frame to encoder");
         av_packet_free(&enc_pkt);
         return ret;
     }
@@ -215,22 +232,22 @@ int encode_and_write_frame(
             av_packet_unref(enc_pkt);
             break;
         } else if (ret < 0) {
-            fprintf(stderr, "Error encoding frame\n");
+            spdlog::error("Error encoding frame");
             av_packet_free(&enc_pkt);
             return ret;
         }
 
         // Rescale packet timestamps
         av_packet_rescale_ts(
-            enc_pkt, enc_ctx->time_base, ofmt_ctx->streams[video_stream_index]->time_base
+            enc_pkt, enc_ctx->time_base, ofmt_ctx->streams[vstream_idx]->time_base
         );
-        enc_pkt->stream_index = video_stream_index;
+        enc_pkt->stream_index = vstream_idx;
 
         // Write the packet
         ret = av_interleaved_write_frame(ofmt_ctx, enc_pkt);
         av_packet_unref(enc_pkt);
         if (ret < 0) {
-            fprintf(stderr, "Error muxing packet\n");
+            spdlog::error("Error muxing packet");
             av_packet_free(&enc_pkt);
             return ret;
         }
@@ -244,7 +261,7 @@ int flush_encoder(AVCodecContext *enc_ctx, AVFormatContext *ofmt_ctx) {
     int ret;
     AVPacket *enc_pkt = av_packet_alloc();
     if (!enc_pkt) {
-        fprintf(stderr, "Could not allocate AVPacket\n");
+        spdlog::error("Could not allocate AVPacket");
         return AVERROR(ENOMEM);
     }
 
@@ -255,7 +272,7 @@ int flush_encoder(AVCodecContext *enc_ctx, AVFormatContext *ofmt_ctx) {
             av_packet_unref(enc_pkt);
             break;
         } else if (ret < 0) {
-            fprintf(stderr, "Error encoding frame\n");
+            spdlog::error("Error encoding frame");
             av_packet_free(&enc_pkt);
             return ret;
         }
@@ -268,7 +285,7 @@ int flush_encoder(AVCodecContext *enc_ctx, AVFormatContext *ofmt_ctx) {
         ret = av_interleaved_write_frame(ofmt_ctx, enc_pkt);
         av_packet_unref(enc_pkt);
         if (ret < 0) {
-            fprintf(stderr, "Error muxing packet\n");
+            spdlog::error("Error muxing packet");
             av_packet_free(&enc_pkt);
             return ret;
         }

src/fsutils.cpp

@@ -8,14 +8,16 @@
 #include <cstring>
 #endif
 
+#include <spdlog/spdlog.h>
+
 #if _WIN32
-std::filesystem::path get_executable_directory() {
+static std::filesystem::path get_executable_directory() {
     std::vector<wchar_t> filepath(MAX_PATH);
 
     // Get the executable path, expanding the buffer if necessary
     DWORD size = GetModuleFileNameW(NULL, filepath.data(), static_cast<DWORD>(filepath.size()));
     if (size == 0) {
-        fprintf(stderr, "Error getting executable path: %lu\n", GetLastError());
+        spdlog::error("Error getting executable path: {}", GetLastError());
         return std::filesystem::path();
     }
 
@@ -24,7 +26,7 @@ std::filesystem::path get_executable_directory() {
         filepath.resize(filepath.size() * 2);
         size = GetModuleFileNameW(NULL, filepath.data(), static_cast<DWORD>(filepath.size()));
         if (size == 0) {
-            fprintf(stderr, "Error getting executable path: %lu\n", GetLastError());
+            spdlog::error("Error getting executable path: {}", GetLastError());
             return std::filesystem::path();
         }
     }
@@ -34,12 +36,12 @@ std::filesystem::path get_executable_directory() {
     return execpath.parent_path();
 }
 #else   // _WIN32
-std::filesystem::path get_executable_directory() {
+static std::filesystem::path get_executable_directory() {
     std::error_code ec;
     std::filesystem::path filepath = std::filesystem::read_symlink("/proc/self/exe", ec);
 
     if (ec) {
-        fprintf(stderr, "Error reading /proc/self/exe: %s\n", ec.message().c_str());
+        spdlog::error("Error reading /proc/self/exe: {}", ec.message());
         return std::filesystem::path();
     }
 

src/getopt.c

@@ -185,7 +185,7 @@ int getopt_long(
             return (-1);
         }
         if ((has_equal = strchr(current_argv, '=')) != NULL) {
-            current_argv_len = has_equal - current_argv;
+            current_argv_len = (size_t)(has_equal - current_argv);
             has_equal++;
         } else {
             current_argv_len = strlen(current_argv);

src/libplacebo.cpp

@@ -3,6 +3,8 @@
 #include <stdio.h>
 #include <stdlib.h>
 
+#include <spdlog/spdlog.h>
+
 #include "fsutils.h"
 
 int init_libplacebo(
@@ -11,8 +13,8 @@ int init_libplacebo(
     AVFilterContext **buffersrc_ctx,
     AVFilterContext **buffersink_ctx,
     AVCodecContext *dec_ctx,
-    int output_width,
+    int out_width,
-    int output_height,
+    int out_height,
     const std::filesystem::path &shader_path
 ) {
     char args[512];
@@ -20,7 +22,7 @@ int init_libplacebo(
 
     AVFilterGraph *graph = avfilter_graph_alloc();
     if (!graph) {
-        fprintf(stderr, "Unable to create filter graph.\n");
+        spdlog::error("Unable to create filter graph.");
         return AVERROR(ENOMEM);
     }
 
@@ -30,7 +32,7 @@ int init_libplacebo(
         args,
         sizeof(args),
         "video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:frame_rate=%d/%d:"
-        "pixel_aspect=%d/%d:colorspace=%d",
+        "pixel_aspect=%d/%d:colorspace=%d:range=%d",
         dec_ctx->width,
         dec_ctx->height,
         dec_ctx->pix_fmt,
@@ -40,12 +42,13 @@ int init_libplacebo(
         dec_ctx->framerate.den,
         dec_ctx->sample_aspect_ratio.num,
         dec_ctx->sample_aspect_ratio.den,
-        dec_ctx->colorspace
+        dec_ctx->colorspace,
+        dec_ctx->color_range
     );
 
     ret = avfilter_graph_create_filter(buffersrc_ctx, buffersrc, "in", args, NULL, graph);
     if (ret < 0) {
-        fprintf(stderr, "Cannot create buffer source\n");
+        spdlog::error("Cannot create buffer source.");
         avfilter_graph_free(&graph);
         return ret;
     }
@@ -55,7 +58,7 @@ int init_libplacebo(
     // Create the libplacebo filter
     const AVFilter *libplacebo_filter = avfilter_get_by_name("libplacebo");
     if (!libplacebo_filter) {
-        fprintf(stderr, "Filter 'libplacebo' not found\n");
+        spdlog::error("Filter 'libplacebo' not found.");
         avfilter_graph_free(&graph);
         return AVERROR_FILTER_NOT_FOUND;
     }
@@ -69,22 +72,29 @@ int init_libplacebo(
 #endif
 
     // Prepare the filter arguments
-    char filter_args[512];
+    char filter_args[4096];
-    snprintf(
+    int filter_args_size = snprintf(
         filter_args,
         sizeof(filter_args),
-        "w=%d:h=%d:upscaler=ewa_lanczos:custom_shader_path=%s",
+        "w=%d:h=%d:custom_shader_path='%s'",
-        output_width,
+        out_width,
-        output_height,
+        out_height,
         shader_path_string.c_str()
     );
 
+    // Check if the filter arguments are too long
+    if (filter_args_size < 0 || filter_args_size >= static_cast<int>(sizeof(filter_args))) {
+        spdlog::error("libplacebo filter arguments too long.");
+        avfilter_graph_free(&graph);
+        return AVERROR(EINVAL);
+    }
+
     AVFilterContext *libplacebo_ctx;
     ret = avfilter_graph_create_filter(
         &libplacebo_ctx, libplacebo_filter, "libplacebo", filter_args, NULL, graph
     );
     if (ret < 0) {
-        fprintf(stderr, "Cannot create libplacebo filter\n");
+        spdlog::error("Cannot create libplacebo filter.");
         avfilter_graph_free(&graph);
         return ret;
     }
@@ -97,7 +107,7 @@ int init_libplacebo(
     // Link buffersrc to libplacebo
     ret = avfilter_link(last_filter, 0, libplacebo_ctx, 0);
     if (ret < 0) {
-        fprintf(stderr, "Error connecting buffersrc to libplacebo filter\n");
+        spdlog::error("Error connecting buffersrc to libplacebo filter.");
         avfilter_graph_free(&graph);
         return ret;
     }
@@ -108,7 +118,7 @@ int init_libplacebo(
     const AVFilter *buffersink = avfilter_get_by_name("buffersink");
     ret = avfilter_graph_create_filter(buffersink_ctx, buffersink, "out", NULL, NULL, graph);
     if (ret < 0) {
-        fprintf(stderr, "Cannot create buffer sink\n");
+        spdlog::error("Cannot create buffer sink.");
         avfilter_graph_free(&graph);
         return ret;
     }
@@ -116,7 +126,7 @@ int init_libplacebo(
     // Link libplacebo to buffersink
     ret = avfilter_link(last_filter, 0, *buffersink_ctx, 0);
     if (ret < 0) {
-        fprintf(stderr, "Error connecting libplacebo filter to buffersink\n");
+        spdlog::error("Error connecting libplacebo filter to buffersink.");
         avfilter_graph_free(&graph);
         return ret;
     }
@@ -124,7 +134,7 @@ int init_libplacebo(
     // Configure the filter graph
     ret = avfilter_graph_config(graph, NULL);
     if (ret < 0) {
-        fprintf(stderr, "Error configuring the filter graph\n");
+        spdlog::error("Error configuring the filter graph.");
         avfilter_graph_free(&graph);
         return ret;
     }

src/libplacebo_filter.cpp

@@ -2,15 +2,21 @@
 
 #include <cstdio>
 
+#include <spdlog/spdlog.h>
+
 #include "fsutils.h"
 #include "libplacebo.h"
 
-LibplaceboFilter::LibplaceboFilter(int width, int height, const std::filesystem::path &shader_path)
+LibplaceboFilter::LibplaceboFilter(
+    int out_width,
+    int out_height,
+    const std::filesystem::path &shader_path
+)
     : filter_graph(nullptr),
       buffersrc_ctx(nullptr),
       buffersink_ctx(nullptr),
-      output_width(width),
+      out_width(out_width),
-      output_height(height),
+      out_height(out_height),
       shader_path(std::move(shader_path)) {}
 
 LibplaceboFilter::~LibplaceboFilter() {
@@ -36,66 +42,77 @@ int LibplaceboFilter::init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVB
         shader_full_path = shader_path;
     } else {
         // Construct the fallback path using std::filesystem
-        shader_full_path =
+        shader_full_path = find_resource_file(
-            find_resource_file(std::filesystem::path("models") / (shader_path.string() + ".glsl"));
+            std::filesystem::path("models") / "libplacebo" / (shader_path.string() + ".glsl")
+        );
     }
 
     // Check if the shader file exists
     if (!std::filesystem::exists(shader_full_path)) {
-        fprintf(stderr, "libplacebo shader file not found: %s\n", shader_full_path.c_str());
+        spdlog::error("libplacebo shader file not found: {}", shader_full_path.string());
         return -1;
     }
 
     // Save the output time base
-    output_time_base = enc_ctx->time_base;
+    in_time_base = dec_ctx->time_base;
+    out_time_base = enc_ctx->time_base;
 
-    return init_libplacebo(
+    // Initialize the libplacebo filter
+    int ret = init_libplacebo(
         hw_ctx,
         &filter_graph,
         &buffersrc_ctx,
         &buffersink_ctx,
         dec_ctx,
-        output_width,
+        out_width,
-        output_height,
+        out_height,
         shader_full_path
     );
+
+    // Set these resources to nullptr since they are already freed by `avfilter_graph_free`
+    if (ret < 0) {
+        buffersrc_ctx = nullptr;
+        buffersink_ctx = nullptr;
+        filter_graph = nullptr;
+    }
+    return ret;
 }
 
-int LibplaceboFilter::process_frame(AVFrame *input_frame, AVFrame **output_frame) {
+int LibplaceboFilter::process_frame(AVFrame *in_frame, AVFrame **out_frame) {
     int ret;
 
     // Get the filtered frame
-    *output_frame = av_frame_alloc();
+    *out_frame = av_frame_alloc();
-    if (*output_frame == nullptr) {
+    if (*out_frame == nullptr) {
-        fprintf(stderr, "Failed to allocate output frame\n");
+        spdlog::error("Failed to allocate output frame");
         return -1;
     }
 
     // Feed the frame to the filter graph
-    ret = av_buffersrc_add_frame(buffersrc_ctx, input_frame);
+    ret = av_buffersrc_add_frame(buffersrc_ctx, in_frame);
     if (ret < 0) {
-        fprintf(stderr, "Error while feeding the filter graph\n");
+        spdlog::error("Error while feeding the filter graph");
+        av_frame_free(out_frame);
         return ret;
     }
 
-    ret = av_buffersink_get_frame(buffersink_ctx, *output_frame);
+    ret = av_buffersink_get_frame(buffersink_ctx, *out_frame);
     if (ret < 0) {
-        av_frame_free(output_frame);
+        av_frame_free(out_frame);
         return ret;
     }
 
     // Rescale PTS to encoder's time base
-    (*output_frame)->pts =
+    (*out_frame)->pts = av_rescale_q((*out_frame)->pts, in_time_base, out_time_base);
-        av_rescale_q((*output_frame)->pts, buffersink_ctx->inputs[0]->time_base, output_time_base);
 
     // Return the processed frame to the caller
     return 0;
 }
 
-int LibplaceboFilter::flush(std::vector<AVFrame *> &processed_frames) {
+int LibplaceboFilter::flush(std::vector<AVFrame *> &flushed_frames) {
     int ret = av_buffersrc_add_frame(buffersrc_ctx, nullptr);
     if (ret < 0) {
-        fprintf(stderr, "Error while flushing filter graph\n");
+        spdlog::error("Error while flushing filter graph");
         return ret;
     }
 
@@ -117,11 +134,10 @@ int LibplaceboFilter::flush(std::vector<AVFrame *> &processed_frames) {
         }
 
         // Rescale PTS to encoder's time base
-        filt_frame->pts =
+        filt_frame->pts = av_rescale_q(filt_frame->pts, in_time_base, out_time_base);
-            av_rescale_q(filt_frame->pts, buffersink_ctx->inputs[0]->time_base, output_time_base);
 
         // Add to processed frames
-        processed_frames.push_back(filt_frame);
+        flushed_frames.push_back(filt_frame);
     }
 
     return 0;

src/libvideo2x.cpp

@@ -1,12 +1,13 @@
 #include "libvideo2x.h"
 
-#include <libavutil/mathematics.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <cstdint>
 #include <thread>
 
+#include <spdlog/spdlog.h>
+#include <opencv2/videoio.hpp>
+
 #include "decoder.h"
 #include "encoder.h"
 #include "filter.h"
@@ -16,16 +17,19 @@
 /**
  * @brief Process frames using the selected filter.
  *
+ * @param[in] encoder_config Encoder configurations
  * @param[in,out] proc_ctx Struct containing the processing context
- * @param[in] fmt_ctx Input format context
+ * @param[in] ifmt_ctx Input format context
  * @param[in] ofmt_ctx Output format context
  * @param[in] dec_ctx Decoder context
  * @param[in] enc_ctx Encoder context
  * @param[in] filter Filter instance
- * @param[in] video_stream_index Index of the video stream in the input format context
+ * @param[in] vstream_idx Index of the video stream in the input format context
+ * @param[in] stream_map Array mapping input stream indexes to output stream indexes
+ * @param[in] benchmark Flag to enable benchmarking mode
  * @return int 0 on success, negative value on error
  */
-int process_frames(
+static int process_frames(
     EncoderConfig *encoder_config,
     VideoProcessingContext *proc_ctx,
     AVFormatContext *ifmt_ctx,
@@ -33,26 +37,29 @@ int process_frames(
     AVCodecContext *dec_ctx,
     AVCodecContext *enc_ctx,
     Filter *filter,
-    int video_stream_index,
+    int vstream_idx,
-    int *stream_mapping,
+    int *stream_map,
     bool benchmark = false
 ) {
     int ret;
-    AVPacket packet;
-    std::vector<AVFrame *> flushed_frames;
     char errbuf[AV_ERROR_MAX_STRING_SIZE];
+    std::vector<AVFrame *> flushed_frames;
 
-    // Get the total number of frames in the video
+    // Get the total number of frames in the video with OpenCV
-    AVStream *video_stream = ifmt_ctx->streams[video_stream_index];
+    spdlog::debug("Reading total number of frames with OpenCV");
-    proc_ctx->total_frames = video_stream->nb_frames;
+    cv::VideoCapture cap(ifmt_ctx->url);
+    if (!cap.isOpened()) {
+        spdlog::error("Failed to open video file with OpenCV");
+        return -1;
+    }
+    proc_ctx->total_frames = static_cast<int64_t>(cap.get(cv::CAP_PROP_FRAME_COUNT));
+    cap.release();
 
-    // If nb_frames is not set, calculate total frames using duration and frame rate
+    // Check if the total number of frames is still 0
     if (proc_ctx->total_frames == 0) {
-        int64_t duration = video_stream->duration;
+        spdlog::warn("Unable to determine total number of frames");
-        AVRational frame_rate = video_stream->avg_frame_rate;
+    } else {
-        if (duration != AV_NOPTS_VALUE && frame_rate.num != 0 && frame_rate.den != 0) {
+        spdlog::debug("{} frames to process", proc_ctx->total_frames);
-            proc_ctx->total_frames = duration * frame_rate.num / frame_rate.den;
-        }
     }
 
     // Get start time
@@ -64,29 +71,53 @@ int process_frames(
     AVFrame *frame = av_frame_alloc();
     if (frame == nullptr) {
         ret = AVERROR(ENOMEM);
-        goto end;
+        return ret;
     }
 
+    AVPacket *packet = av_packet_alloc();
+    if (packet == nullptr) {
+        spdlog::error("Could not allocate AVPacket");
+        av_frame_free(&frame);
+        return AVERROR(ENOMEM);
+    }
+
+    // Lambda function for cleaning up resources
+    auto cleanup = [&]() {
+        av_frame_free(&frame);
+        av_packet_free(&packet);
+        for (AVFrame *&flushed_frame : flushed_frames) {
+            if (flushed_frame) {
+                av_frame_free(&flushed_frame);
+                flushed_frame = nullptr;
+            }
+        }
+    };
+
     // Read frames from the input file
     while (!proc_ctx->abort) {
-        ret = av_read_frame(ifmt_ctx, &packet);
+        ret = av_read_frame(ifmt_ctx, packet);
         if (ret < 0) {
-            break;  // End of file or error
+            if (ret == AVERROR_EOF) {
+                spdlog::debug("Reached end of file");
+                break;
+            }
+            av_strerror(ret, errbuf, sizeof(errbuf));
+            spdlog::error("Error reading packet: {}", errbuf);
+            cleanup();
+            return ret;
         }
 
-        if (packet.stream_index == video_stream_index) {
+        if (packet->stream_index == vstream_idx) {
-            // Send the packet to the decoder
+            ret = avcodec_send_packet(dec_ctx, packet);
-            ret = avcodec_send_packet(dec_ctx, &packet);
             if (ret < 0) {
                 av_strerror(ret, errbuf, sizeof(errbuf));
-                fprintf(stderr, "Error sending packet to decoder: %s\n", errbuf);
+                spdlog::error("Error sending packet to decoder: {}", errbuf);
-                av_packet_unref(&packet);
+                av_packet_unref(packet);
-                goto end;
+                cleanup();
+                return ret;
             }
 
-            // Receive and process frames from the decoder
             while (!proc_ctx->abort) {
-                // Check if the processing is paused
                 if (proc_ctx->pause) {
                     std::this_thread::sleep_for(std::chrono::milliseconds(100));
                     continue;
@@ -94,142 +125,110 @@ int process_frames(
 
                 ret = avcodec_receive_frame(dec_ctx, frame);
                 if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
+                    spdlog::debug("Frame not ready");
                     break;
                 } else if (ret < 0) {
                     av_strerror(ret, errbuf, sizeof(errbuf));
-                    fprintf(stderr, "Error decoding video frame: %s\n", errbuf);
+                    spdlog::error("Error decoding video frame: {}", errbuf);
-                    goto end;
+                    av_packet_unref(packet);
+                    cleanup();
+                    return ret;
                 }
 
-                // Process the frame using the selected filter
                 AVFrame *processed_frame = nullptr;
                 ret = filter->process_frame(frame, &processed_frame);
-                if (ret == 0 && processed_frame != nullptr) {
+                if (ret < 0 && ret != AVERROR(EAGAIN)) {
-                    // Encode and write the processed frame
+                    av_strerror(ret, errbuf, sizeof(errbuf));
+                    av_frame_free(&processed_frame);
+                    av_packet_unref(packet);
+                    cleanup();
+                    return ret;
+                } else if (ret == 0 && processed_frame != nullptr) {
                     if (!benchmark) {
-                        ret = encode_and_write_frame(
+                        ret = write_frame(processed_frame, enc_ctx, ofmt_ctx, vstream_idx);
-                            processed_frame, enc_ctx, ofmt_ctx, video_stream_index
-                        );
                         if (ret < 0) {
                             av_strerror(ret, errbuf, sizeof(errbuf));
-                            fprintf(stderr, "Error encoding/writing frame: %s\n", errbuf);
+                            spdlog::error("Error encoding/writing frame: {}", errbuf);
                             av_frame_free(&processed_frame);
-                            goto end;
+                            av_packet_unref(packet);
+                            cleanup();
+                            return ret;
                         }
                     }
-
                     av_frame_free(&processed_frame);
                     proc_ctx->processed_frames++;
-                } else if (ret != AVERROR(EAGAIN) && ret != AVERROR_EOF) {
-                    fprintf(stderr, "Filter returned an error\n");
-                    goto end;
                 }
 
                 av_frame_unref(frame);
-                // TODO: Print the debug processing status
+                spdlog::debug(
+                    "Processed frame {}/{}", proc_ctx->processed_frames, proc_ctx->total_frames
+                );
             }
-        } else if (encoder_config->copy_streams && stream_mapping[packet.stream_index] >= 0) {
+        } else if (encoder_config->copy_streams && stream_map[packet->stream_index] >= 0) {
-            AVStream *in_stream = ifmt_ctx->streams[packet.stream_index];
+            AVStream *in_stream = ifmt_ctx->streams[packet->stream_index];
-            int out_stream_index = stream_mapping[packet.stream_index];
+            int out_stream_index = stream_map[packet->stream_index];
             AVStream *out_stream = ofmt_ctx->streams[out_stream_index];
 
-            // Rescale packet timestamps
+            av_packet_rescale_ts(packet, in_stream->time_base, out_stream->time_base);
-            av_packet_rescale_ts(&packet, in_stream->time_base, out_stream->time_base);
+            packet->stream_index = out_stream_index;
-            packet.stream_index = out_stream_index;
 
-            // If copy streams is enabled, copy the packet to the output
+            ret = av_interleaved_write_frame(ofmt_ctx, packet);
-            ret = av_interleaved_write_frame(ofmt_ctx, &packet);
             if (ret < 0) {
-                fprintf(stderr, "Error muxing packet\n");
+                av_strerror(ret, errbuf, sizeof(errbuf));
-                av_packet_unref(&packet);
+                spdlog::error("Error muxing packet: {}", errbuf);
+                av_packet_unref(packet);
+                cleanup();
                 return ret;
             }
         }
-        av_packet_unref(&packet);
+        av_packet_unref(packet);
     }
 
     // Flush the filter
     ret = filter->flush(flushed_frames);
     if (ret < 0) {
         av_strerror(ret, errbuf, sizeof(errbuf));
-        fprintf(stderr, "Error flushing filter: %s\n", errbuf);
+        spdlog::error("Error flushing filter: {}", errbuf);
-        goto end;
+        cleanup();
+        return ret;
     }
 
     // Encode and write all flushed frames
     for (AVFrame *&flushed_frame : flushed_frames) {
-        ret = encode_and_write_frame(flushed_frame, enc_ctx, ofmt_ctx, video_stream_index);
+        ret = write_frame(flushed_frame, enc_ctx, ofmt_ctx, vstream_idx);
         if (ret < 0) {
             av_strerror(ret, errbuf, sizeof(errbuf));
-            fprintf(stderr, "Error encoding/writing flushed frame: %s\n", errbuf);
+            spdlog::error("Error encoding/writing flushed frame: {}", errbuf);
             av_frame_free(&flushed_frame);
             flushed_frame = nullptr;
-            goto end;
+            cleanup();
+            return ret;
         }
         av_frame_free(&flushed_frame);
         flushed_frame = nullptr;
+        proc_ctx->processed_frames++;
     }
 
     // Flush the encoder
     ret = flush_encoder(enc_ctx, ofmt_ctx);
     if (ret < 0) {
         av_strerror(ret, errbuf, sizeof(errbuf));
-        fprintf(stderr, "Error flushing encoder: %s\n", errbuf);
+        spdlog::error("Error flushing encoder: {}", errbuf);
-        goto end;
+        cleanup();
+        return ret;
     }
 
-end:
+    cleanup();
-    av_frame_free(&frame);
-    // Free any flushed frames not yet freed
-    for (AVFrame *flushed_frame : flushed_frames) {
-        if (flushed_frame) {
-            av_frame_free(&flushed_frame);
-        }
-    }
     return ret;
 }
 
-// Cleanup resources after processing the video
-void cleanup(
-    AVFormatContext *ifmt_ctx,
-    AVFormatContext *ofmt_ctx,
-    AVCodecContext *dec_ctx,
-    AVCodecContext *enc_ctx,
-    AVBufferRef *hw_ctx,
-    int *stream_mapping,
-    Filter *filter
-) {
-    if (ifmt_ctx) {
-        avformat_close_input(&ifmt_ctx);
-    }
-    if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
-        avio_closep(&ofmt_ctx->pb);
-    }
-    if (ofmt_ctx) {
-        avformat_free_context(ofmt_ctx);
-    }
-    if (dec_ctx) {
-        avcodec_free_context(&dec_ctx);
-    }
-    if (enc_ctx) {
-        avcodec_free_context(&enc_ctx);
-    }
-    if (hw_ctx) {
-        av_buffer_unref(&hw_ctx);
-    }
-    if (stream_mapping) {
-        av_free(stream_mapping);
-    }
-    if (filter) {
-        delete filter;
-    }
-}
-
 /**
  * @brief Process a video file using the selected filter and encoder settings.
  *
- * @param[in] input_filename Path to the input video file
+ * @param[in] in_fname Path to the input video file
- * @param[in] output_filename Path to the output video file
+ * @param[in] out_fname Path to the output video file
+ * @param[in] log_level Log level
+ * @param[in] benchmark Flag to enable benchmarking mode
  * @param[in] hw_type Hardware device type
  * @param[in] filter_config Filter configurations
  * @param[in] encoder_config Encoder configurations
@@ -237,8 +236,9 @@ void cleanup(
  * @return int 0 on success, non-zero value on error
  */
 extern "C" int process_video(
-    const char *input_filename,
+    const char *in_fname,
-    const char *output_filename,
+    const char *out_fname,
+    Libvideo2xLogLevel log_level,
     bool benchmark,
     AVHWDeviceType hw_type,
     const FilterConfig *filter_config,
@@ -250,126 +250,191 @@ extern "C" int process_video(
     AVCodecContext *dec_ctx = nullptr;
     AVCodecContext *enc_ctx = nullptr;
     AVBufferRef *hw_ctx = nullptr;
-    int *stream_mapping = nullptr;
+    int *stream_map = nullptr;
     Filter *filter = nullptr;
-    int video_stream_index = -1;
+    int vstream_idx = -1;
+    char errbuf[AV_ERROR_MAX_STRING_SIZE];
     int ret = 0;
 
+    // Lambda function for cleaning up resources
+    auto cleanup = [&]() {
+        if (ifmt_ctx) {
+            avformat_close_input(&ifmt_ctx);
+            ifmt_ctx = nullptr;
+        }
+        if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
+            avio_closep(&ofmt_ctx->pb);
+            ofmt_ctx->pb = nullptr;
+        }
+        if (ofmt_ctx) {
+            avformat_free_context(ofmt_ctx);
+            ofmt_ctx = nullptr;
+        }
+        if (dec_ctx) {
+            avcodec_free_context(&dec_ctx);
+            dec_ctx = nullptr;
+        }
+        if (enc_ctx) {
+            avcodec_free_context(&enc_ctx);
+            enc_ctx = nullptr;
+        }
+        if (hw_ctx) {
+            av_buffer_unref(&hw_ctx);
+            hw_ctx = nullptr;
+        }
+        if (stream_map) {
+            av_free(stream_map);
+            stream_map = nullptr;
+        }
+        if (filter) {
+            delete filter;
+            filter = nullptr;
+        }
+    };
+
+    // Set the log level for FFmpeg and spdlog (libvideo2x)
+    switch (log_level) {
+        case LIBVIDEO2X_LOG_LEVEL_TRACE:
+            av_log_set_level(AV_LOG_TRACE);
+            spdlog::set_level(spdlog::level::trace);
+            break;
+        case LIBVIDEO2X_LOG_LEVEL_DEBUG:
+            av_log_set_level(AV_LOG_DEBUG);
+            spdlog::set_level(spdlog::level::debug);
+            break;
+        case LIBVIDEO2X_LOG_LEVEL_INFO:
+            av_log_set_level(AV_LOG_INFO);
+            spdlog::set_level(spdlog::level::info);
+            break;
+        case LIBVIDEO2X_LOG_LEVEL_WARNING:
+            av_log_set_level(AV_LOG_WARNING);
+            spdlog::set_level(spdlog::level::warn);
+            break;
+        case LIBVIDEO2X_LOG_LEVEL_ERROR:
+            av_log_set_level(AV_LOG_ERROR);
+            spdlog::set_level(spdlog::level::err);
+            break;
+        case LIBVIDEO2X_LOG_LEVEL_CRITICAL:
+            av_log_set_level(AV_LOG_FATAL);
+            spdlog::set_level(spdlog::level::critical);
+            break;
+        case LIBVIDEO2X_LOG_LEVEL_OFF:
+            av_log_set_level(AV_LOG_QUIET);
+            spdlog::set_level(spdlog::level::off);
+            break;
+        default:
+            av_log_set_level(AV_LOG_INFO);
+            spdlog::set_level(spdlog::level::info);
+            break;
+    }
+
     // Initialize hardware device context
     if (hw_type != AV_HWDEVICE_TYPE_NONE) {
         ret = av_hwdevice_ctx_create(&hw_ctx, hw_type, NULL, NULL, 0);
         if (ret < 0) {
-            fprintf(stderr, "Unable to initialize hardware device context\n");
+            av_strerror(ret, errbuf, sizeof(errbuf));
+            spdlog::error("Error initializing hardware device context: {}", errbuf);
+            cleanup();
             return ret;
         }
     }
 
     // Initialize input
-    ret = init_decoder(hw_type, hw_ctx, input_filename, &ifmt_ctx, &dec_ctx, &video_stream_index);
+    ret = init_decoder(hw_type, hw_ctx, in_fname, &ifmt_ctx, &dec_ctx, &vstream_idx);
     if (ret < 0) {
-        fprintf(stderr, "Failed to initialize decoder\n");
+        av_strerror(ret, errbuf, sizeof(errbuf));
-        cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
+        spdlog::error("Failed to initialize decoder: {}", errbuf);
+        cleanup();
         return ret;
     }
 
-    // Initialize output based on Libplacebo or RealESRGAN configuration
+    // Initialize output dimensions based on filter configuration
     int output_width = 0, output_height = 0;
     switch (filter_config->filter_type) {
         case FILTER_LIBPLACEBO:
-            output_width = filter_config->config.libplacebo.output_width;
+            output_width = filter_config->config.libplacebo.out_width;
-            output_height = filter_config->config.libplacebo.output_height;
+            output_height = filter_config->config.libplacebo.out_height;
             break;
         case FILTER_REALESRGAN:
-            // Calculate the output dimensions based on the scaling factor
             output_width = dec_ctx->width * filter_config->config.realesrgan.scaling_factor;
             output_height = dec_ctx->height * filter_config->config.realesrgan.scaling_factor;
+            break;
+        default:
+            spdlog::error("Unknown filter type");
+            cleanup();
+            return -1;
     }
+    spdlog::info("Output video dimensions: {}x{}", output_width, output_height);
 
     // Initialize output encoder
-    encoder_config->output_width = output_width;
+    encoder_config->out_width = output_width;
-    encoder_config->output_height = output_height;
+    encoder_config->out_height = output_height;
     ret = init_encoder(
         hw_ctx,
-        output_filename,
+        out_fname,
         ifmt_ctx,
         &ofmt_ctx,
         &enc_ctx,
         dec_ctx,
         encoder_config,
-        video_stream_index,
+        vstream_idx,
-        &stream_mapping
+        &stream_map
     );
     if (ret < 0) {
-        fprintf(stderr, "Failed to initialize encoder\n");
+        av_strerror(ret, errbuf, sizeof(errbuf));
-        cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
+        spdlog::error("Failed to initialize encoder: {}", errbuf);
+        cleanup();
         return ret;
     }
 
     // Write the output file header
     ret = avformat_write_header(ofmt_ctx, NULL);
     if (ret < 0) {
-        fprintf(stderr, "Error occurred when opening output file\n");
+        av_strerror(ret, errbuf, sizeof(errbuf));
-        cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
+        spdlog::error("Error occurred when opening output file: {}", errbuf);
+        cleanup();
         return ret;
     }
 
     // Create and initialize the appropriate filter
-    switch (filter_config->filter_type) {
+    if (filter_config->filter_type == FILTER_LIBPLACEBO) {
-        case FILTER_LIBPLACEBO: {
+        const auto &config = filter_config->config.libplacebo;
-            const auto &config = filter_config->config.libplacebo;
+        if (!config.shader_path) {
-
+            spdlog::error("Shader path must be provided for the libplacebo filter");
-            // Validate shader path
+            cleanup();
-            if (!config.shader_path) {
-                fprintf(stderr, "Shader path must be provided for the libplacebo filter\n");
-                cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
-                return -1;
-            }
-
-            // Validate output dimensions
-            if (config.output_width <= 0 || config.output_height <= 0) {
-                fprintf(stderr, "Output dimensions must be provided for the libplacebo filter\n");
-                cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
-                return -1;
-            }
-
-            filter = new LibplaceboFilter{
-                config.output_width, config.output_height, std::filesystem::path(config.shader_path)
-            };
-            break;
-        }
-        case FILTER_REALESRGAN: {
-            const auto &config = filter_config->config.realesrgan;
-
-            // Validate model name
-            if (!config.model) {
-                fprintf(stderr, "Model name must be provided for the RealESRGAN filter\n");
-                cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
-                return -1;
-            }
-
-            // Validate scaling factor
-            if (config.scaling_factor <= 0) {
-                fprintf(stderr, "Scaling factor must be provided for the RealESRGAN filter\n");
-                cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
-                return -1;
-            }
-
-            filter = new RealesrganFilter{
-                config.gpuid, config.tta_mode, config.scaling_factor, config.model
-            };
-            break;
-        }
-        default:
-            fprintf(stderr, "Unknown filter type\n");
-            cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
             return -1;
+        }
+        filter = new LibplaceboFilter{
+            config.out_width, config.out_height, std::filesystem::path(config.shader_path)
+        };
+    } else if (filter_config->filter_type == FILTER_REALESRGAN) {
+        const auto &config = filter_config->config.realesrgan;
+        if (!config.model) {
+            spdlog::error("Model name must be provided for the RealESRGAN filter");
+            cleanup();
+            return -1;
+        }
+        filter = new RealesrganFilter{
+            config.gpuid, config.tta_mode, config.scaling_factor, config.model
+        };
+    } else {
+        spdlog::error("Unknown filter type");
+        cleanup();
+        return -1;
+    }
+
+    // Check if the filter instance was created successfully
+    if (filter == nullptr) {
+        spdlog::error("Failed to create filter instance");
+        cleanup();
+        return -1;
     }
 
     // Initialize the filter
     ret = filter->init(dec_ctx, enc_ctx, hw_ctx);
     if (ret < 0) {
-        fprintf(stderr, "Failed to initialize filter\n");
+        spdlog::error("Failed to initialize filter");
-        cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
+        cleanup();
         return ret;
     }
 
@@ -382,13 +447,14 @@ extern "C" int process_video(
         dec_ctx,
         enc_ctx,
         filter,
-        video_stream_index,
+        vstream_idx,
-        stream_mapping,
+        stream_map,
         benchmark
     );
     if (ret < 0) {
-        fprintf(stderr, "Error processing frames\n");
+        av_strerror(ret, errbuf, sizeof(errbuf));
-        cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
+        spdlog::error("Error processing frames: {}", errbuf);
+        cleanup();
         return ret;
     }
 
@@ -396,12 +462,11 @@ extern "C" int process_video(
     av_write_trailer(ofmt_ctx);
 
     // Cleanup before returning
-    cleanup(ifmt_ctx, ofmt_ctx, dec_ctx, enc_ctx, hw_ctx, stream_mapping, filter);
+    cleanup();
 
     if (ret < 0 && ret != AVERROR_EOF) {
-        char errbuf[AV_ERROR_MAX_STRING_SIZE];
         av_strerror(ret, errbuf, sizeof(errbuf));
-        fprintf(stderr, "Error occurred: %s\n", errbuf);
+        spdlog::error("Error occurred: {}", errbuf);
         return ret;
     }
     return 0;

src/realesrgan_filter.cpp

@@ -4,6 +4,8 @@
 #include <cstdio>
 #include <string>
 
+#include <spdlog/spdlog.h>
+
 #include "conversions.h"
 #include "fsutils.h"
 
@@ -30,16 +32,16 @@ RealesrganFilter::~RealesrganFilter() {
     }
 }
 
-int RealesrganFilter::init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVBufferRef *hw_ctx) {
+int RealesrganFilter::init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVBufferRef *_) {
     // Construct the model paths using std::filesystem
     std::filesystem::path model_param_path;
     std::filesystem::path model_bin_path;
 
     if (model) {
         // Find the model paths by model name if provided
-        model_param_path = std::filesystem::path("models") /
+        model_param_path = std::filesystem::path("models") / "realesrgan" /
                            (std::string(model) + "-x" + std::to_string(scaling_factor) + ".param");
-        model_bin_path = std::filesystem::path("models") /
+        model_bin_path = std::filesystem::path("models") / "realesrgan" /
                          (std::string(model) + "-x" + std::to_string(scaling_factor) + ".bin");
     } else if (!custom_model_param_path.empty() && !custom_model_bin_path.empty()) {
         // Use the custom model paths if provided
@@ -47,7 +49,7 @@ int RealesrganFilter::init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVB
         model_bin_path = custom_model_bin_path;
     } else {
         // Neither model name nor custom model paths provided
-        fprintf(stderr, "Model or model paths must be provided for RealESRGAN filter\n");
+        spdlog::error("Model or model paths must be provided for RealESRGAN filter");
         return -1;
     }
 
@@ -57,13 +59,11 @@ int RealesrganFilter::init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVB
 
     // Check if the model files exist
     if (!std::filesystem::exists(model_param_full_path)) {
-        fprintf(
+        spdlog::error("RealESRGAN model param file not found: {}", model_param_full_path.string());
-            stderr, "RealESRGAN model param file not found: %s\n", model_param_full_path.c_str()
-        );
         return -1;
     }
     if (!std::filesystem::exists(model_bin_full_path)) {
-        fprintf(stderr, "RealESRGAN model bin file not found: %s\n", model_bin_full_path.c_str());
+        spdlog::error("RealESRGAN model bin file not found: {}", model_bin_full_path.string());
         return -1;
     }
 
@@ -71,13 +71,13 @@ int RealesrganFilter::init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVB
     realesrgan = new RealESRGAN(gpuid, tta_mode);
 
     // Store the time bases
-    input_time_base = dec_ctx->time_base;
+    in_time_base = dec_ctx->time_base;
-    output_time_base = enc_ctx->time_base;
+    out_time_base = enc_ctx->time_base;
-    output_pix_fmt = enc_ctx->pix_fmt;
+    out_pix_fmt = enc_ctx->pix_fmt;
 
     // Load the model
     if (realesrgan->load(model_param_full_path, model_bin_full_path) != 0) {
-        fprintf(stderr, "Failed to load RealESRGAN model\n");
+        spdlog::error("Failed to load RealESRGAN model");
         return -1;
     }
 
@@ -100,38 +100,33 @@ int RealesrganFilter::init(AVCodecContext *dec_ctx, AVCodecContext *enc_ctx, AVB
     return 0;
 }
 
-int RealesrganFilter::process_frame(AVFrame *input_frame, AVFrame **output_frame) {
+int RealesrganFilter::process_frame(AVFrame *in_frame, AVFrame **out_frame) {
     int ret;
 
     // Convert the input frame to RGB24
-    ncnn::Mat input_mat = avframe_to_ncnn_mat(input_frame);
+    ncnn::Mat in_mat = avframe_to_ncnn_mat(in_frame);
-    if (input_mat.empty()) {
+    if (in_mat.empty()) {
-        fprintf(stderr, "Failed to convert AVFrame to ncnn::Mat\n");
+        spdlog::error("Failed to convert AVFrame to ncnn::Mat");
         return -1;
     }
 
     // Allocate space for ouptut ncnn::Mat
-    int output_width = input_mat.w * realesrgan->scale;
+    int output_width = in_mat.w * realesrgan->scale;
-    int output_height = input_mat.h * realesrgan->scale;
+    int output_height = in_mat.h * realesrgan->scale;
-    ncnn::Mat output_mat = ncnn::Mat(output_width, output_height, (size_t)3, 3);
+    ncnn::Mat out_mat = ncnn::Mat(output_width, output_height, static_cast<size_t>(3), 3);
 
-    ret = realesrgan->process(input_mat, output_mat);
+    ret = realesrgan->process(in_mat, out_mat);
     if (ret != 0) {
-        fprintf(stderr, "RealESRGAN processing failed\n");
+        spdlog::error("RealESRGAN processing failed");
         return ret;
     }
 
     // Convert ncnn::Mat to AVFrame
-    *output_frame = ncnn_mat_to_avframe(output_mat, output_pix_fmt);
+    *out_frame = ncnn_mat_to_avframe(out_mat, out_pix_fmt);
 
     // Rescale PTS to encoder's time base
-    (*output_frame)->pts = av_rescale_q(input_frame->pts, input_time_base, output_time_base);
+    (*out_frame)->pts = av_rescale_q(in_frame->pts, in_time_base, out_time_base);
 
     // Return the processed frame to the caller
     return ret;
 }
-
-int RealesrganFilter::flush(std::vector<AVFrame *> &processed_frames) {
-    // No special flushing needed for RealESRGAN
-    return 0;
-}

src/video2x.c

@@ -17,31 +17,15 @@
 #include <libavutil/pixdesc.h>
 #include <libavutil/pixfmt.h>
 
-#include <libvideo2x.h>
+#include <libvideo2x/libvideo2x.h>
+#include <libvideo2x/version.h>
 
 #include "getopt.h"
 
-const char *VIDEO2X_VERSION = "6.0.0";
-
-// Set UNIX terminal input to non-blocking mode
-#ifndef _WIN32
-void set_nonblocking_input(bool enable) {
-    static struct termios oldt, newt;
-    if (enable) {
-        tcgetattr(STDIN_FILENO, &oldt);
-        newt = oldt;
-        newt.c_lflag &= ~(ICANON | ECHO);
-        tcsetattr(STDIN_FILENO, TCSANOW, &newt);
-        fcntl(STDIN_FILENO, F_SETFL, O_NONBLOCK);
-    } else {
-        tcsetattr(STDIN_FILENO, TCSANOW, &oldt);
-        fcntl(STDIN_FILENO, F_SETFL, 0);
-    }
-}
-#endif
-
 // Define command line options
 static struct option long_options[] = {
+    {"loglevel", required_argument, NULL, 0},
+    {"noprogress", no_argument, NULL, 0},
     {"version", no_argument, NULL, 'v'},
     {"help", no_argument, NULL, 0},
 
@@ -72,11 +56,23 @@ static struct option long_options[] = {
     {0, 0, 0, 0}
 };
 
+// List of valid RealESRGAN models
+const char *valid_realesrgan_models[] = {
+    "realesrgan-plus",
+    "realesrgan-plus-anime",
+    "realesr-animevideov3",
+};
+
+// Indicate if a newline needs to be printed before the next output
+bool newline_required = false;
+
 // Structure to hold parsed arguments
 struct arguments {
     // General options
-    const char *input_filename;
+    const char *loglevel;
-    const char *output_filename;
+    bool noprogress;
+    const char *in_fname;
+    const char *out_fname;
     const char *filter_type;
     const char *hwaccel;
     bool nocopystreams;
@@ -91,8 +87,8 @@ struct arguments {
 
     // libplacebo options
     const char *shader_path;
-    int output_width;
+    int out_width;
-    int output_height;
+    int out_height;
 
     // RealESRGAN options
     int gpuid;
@@ -108,27 +104,52 @@ struct ProcessVideoThreadArguments {
     struct VideoProcessingContext *proc_ctx;
 };
 
-const char *valid_models[] = {
+// Set UNIX terminal input to non-blocking mode
-    "realesrgan-plus",
+#ifndef _WIN32
-    "realesrgan-plus-anime",
+void set_nonblocking_input(bool enable) {
-    "realesr-animevideov3",
+    static struct termios oldt, newt;
-};
+    if (enable) {
+        tcgetattr(STDIN_FILENO, &oldt);
+        newt = oldt;
+        newt.c_lflag &= ~(tcflag_t)(ICANON | ECHO);
+        tcsetattr(STDIN_FILENO, TCSANOW, &newt);
+        fcntl(STDIN_FILENO, F_SETFL, O_NONBLOCK);
+    } else {
+        tcsetattr(STDIN_FILENO, TCSANOW, &oldt);
+        fcntl(STDIN_FILENO, F_SETFL, 0);
+    }
+}
+#endif
+
+// Newline-safe log callback for FFmpeg
+void newline_safe_ffmpeg_log_callback(void *ptr, int level, const char *fmt, va_list vl) {
+    if (level <= av_log_get_level() && newline_required) {
+        putchar('\n');
+        newline_required = false;
+    }
+    av_log_default_callback(ptr, level, fmt, vl);
+}
 
 int is_valid_realesrgan_model(const char *model) {
     if (!model) {
         return 0;
     }
-    for (int i = 0; i < sizeof(valid_models) / sizeof(valid_models[0]); i++) {
+    for (unsigned long i = 0;
-        if (strcmp(model, valid_models[i]) == 0) {
+         i < sizeof(valid_realesrgan_models) / sizeof(valid_realesrgan_models[0]);
+         i++) {
+        if (strcmp(model, valid_realesrgan_models[i]) == 0) {
             return 1;
         }
     }
     return 0;
 }
 
-void print_help() {
+void print_help(void) {
     printf("Usage: video2x [OPTIONS]\n");
     printf("\nOptions:\n");
+    printf("  --loglevel		Set log level \n");
+    printf("			(trace, debug, info, warn, error, critical, none)\n");
+    printf("  --noprogress		Do not display the progress bar\n");
     printf("  -v, --version		Print program version\n");
     printf("  -?, --help		Display this help page\n");
     printf("\nGeneral Processing Options:\n");
@@ -147,7 +168,9 @@ void print_help() {
     printf("  -q, --crf		Constant Rate Factor (default: 20.0)\n");
 
     printf("\nlibplacebo Options:\n");
-    printf("  -s, --shader		Name or path to custom GLSL shader file\n");
+    printf("  -s, --shader		Name or path of the GLSL shader file to use \n");
+    printf("			(built-in: 'anime4k-a', 'anime4k-b', 'anime4k-c',\n");
+    printf("			'anime4k-a+a', 'anime4k-b+b', 'anime4k-c+a')\n");
     printf("  -w, --width		Output width\n");
     printf("  -h, --height		Output height\n");
 
@@ -157,7 +180,7 @@ void print_help() {
     printf("  -r, --scale		Scaling factor (2, 3, or 4)\n");
 
     printf("\nExamples Usage:\n");
-    printf("  video2x -i in.mp4 -o out.mp4 -f libplacebo -s anime4k-mode-a -w 3840 -h 2160\n");
+    printf("  video2x -i in.mp4 -o out.mp4 -f libplacebo -s anime4k-a+a -w 3840 -h 2160\n");
     printf("  video2x -i in.mp4 -o out.mp4 -f realesrgan -m realesr-animevideov3 -r 4\n");
 }
 
@@ -166,8 +189,10 @@ void parse_arguments(int argc, char **argv, struct arguments *arguments) {
     int c;
 
     // Default argument values
-    arguments->input_filename = NULL;
+    arguments->loglevel = "info";
-    arguments->output_filename = NULL;
+    arguments->noprogress = false;
+    arguments->in_fname = NULL;
+    arguments->out_fname = NULL;
     arguments->filter_type = NULL;
     arguments->hwaccel = "none";
     arguments->nocopystreams = false;
@@ -182,8 +207,8 @@ void parse_arguments(int argc, char **argv, struct arguments *arguments) {
 
     // libplacebo options
     arguments->shader_path = NULL;
-    arguments->output_width = 0;
+    arguments->out_width = 0;
-    arguments->output_height = 0;
+    arguments->out_height = 0;
 
     // RealESRGAN options
     arguments->gpuid = 0;
@@ -191,14 +216,14 @@ void parse_arguments(int argc, char **argv, struct arguments *arguments) {
     arguments->scaling_factor = 0;
 
     while ((c = getopt_long(
-                argc, argv, "i:o:f:a:c:x:p:b:q:s:w:h:r:m:v", long_options, &option_index
+                argc, argv, "i:o:f:a:c:x:p:b:q:s:w:h:g:m:r:v", long_options, &option_index
             )) != -1) {
         switch (c) {
             case 'i':
-                arguments->input_filename = optarg;
+                arguments->in_fname = optarg;
                 break;
             case 'o':
-                arguments->output_filename = optarg;
+                arguments->out_fname = optarg;
                 break;
             case 'f':
                 arguments->filter_type = optarg;
@@ -223,7 +248,7 @@ void parse_arguments(int argc, char **argv, struct arguments *arguments) {
                 }
                 break;
             case 'q':
-                arguments->crf = atof(optarg);
+                arguments->crf = (float)atof(optarg);
                 if (arguments->crf < 0.0 || arguments->crf > 51.0) {
                     fprintf(stderr, "Error: CRF must be between 0 and 51.\n");
                     exit(1);
@@ -233,15 +258,15 @@ void parse_arguments(int argc, char **argv, struct arguments *arguments) {
                 arguments->shader_path = optarg;
                 break;
             case 'w':
-                arguments->output_width = atoi(optarg);
+                arguments->out_width = atoi(optarg);
-                if (arguments->output_width <= 0) {
+                if (arguments->out_width <= 0) {
                     fprintf(stderr, "Error: Output width must be greater than 0.\n");
                     exit(1);
                 }
                 break;
             case 'h':
-                arguments->output_height = atoi(optarg);
+                arguments->out_height = atoi(optarg);
-                if (arguments->output_height <= 0) {
+                if (arguments->out_height <= 0) {
                     fprintf(stderr, "Error: Output height must be greater than 0.\n");
                     exit(1);
                 }
@@ -269,10 +294,14 @@ void parse_arguments(int argc, char **argv, struct arguments *arguments) {
                 }
                 break;
             case 'v':
-                printf("Video2X v%s\n", VIDEO2X_VERSION);
+                printf("Video2X version %s\n", LIBVIDEO2X_VERSION_STRING);
                 exit(0);
             case 0:  // Long-only options without short equivalents
-                if (strcmp(long_options[option_index].name, "help") == 0) {
+                if (strcmp(long_options[option_index].name, "loglevel") == 0) {
+                    arguments->loglevel = optarg;
+                } else if (strcmp(long_options[option_index].name, "noprogress") == 0) {
+                    arguments->noprogress = true;
+                } else if (strcmp(long_options[option_index].name, "help") == 0) {
                     print_help();
                     exit(0);
                 } else if (strcmp(long_options[option_index].name, "nocopystreams") == 0) {
@@ -288,12 +317,12 @@ void parse_arguments(int argc, char **argv, struct arguments *arguments) {
     }
 
     // Check for required arguments
-    if (!arguments->input_filename) {
+    if (!arguments->in_fname) {
         fprintf(stderr, "Error: Input file path is required.\n");
         exit(1);
     }
 
-    if (!arguments->output_filename && !arguments->benchmark) {
+    if (!arguments->out_fname && !arguments->benchmark) {
         fprintf(stderr, "Error: Output file path is required.\n");
         exit(1);
     }
@@ -304,12 +333,11 @@ void parse_arguments(int argc, char **argv, struct arguments *arguments) {
     }
 
     if (strcmp(arguments->filter_type, "libplacebo") == 0) {
-        if (!arguments->shader_path || arguments->output_width == 0 ||
+        if (!arguments->shader_path || arguments->out_width == 0 || arguments->out_height == 0) {
-            arguments->output_height == 0) {
             fprintf(
                 stderr,
                 "Error: For libplacebo, shader name/path (-s), width (-w), "
-                "and height (-e) are required.\n"
+                "and height (-h) are required.\n"
             );
             exit(1);
         }
@@ -323,11 +351,33 @@ void parse_arguments(int argc, char **argv, struct arguments *arguments) {
     }
 }
 
+enum Libvideo2xLogLevel parse_log_level(const char *level_name) {
+    if (strcmp(level_name, "trace") == 0) {
+        return LIBVIDEO2X_LOG_LEVEL_TRACE;
+    } else if (strcmp(level_name, "debug") == 0) {
+        return LIBVIDEO2X_LOG_LEVEL_DEBUG;
+    } else if (strcmp(level_name, "info") == 0) {
+        return LIBVIDEO2X_LOG_LEVEL_INFO;
+    } else if (strcmp(level_name, "warning") == 0) {
+        return LIBVIDEO2X_LOG_LEVEL_WARNING;
+    } else if (strcmp(level_name, "error") == 0) {
+        return LIBVIDEO2X_LOG_LEVEL_ERROR;
+    } else if (strcmp(level_name, "critical") == 0) {
+        return LIBVIDEO2X_LOG_LEVEL_CRITICAL;
+    } else if (strcmp(level_name, "off") == 0) {
+        return LIBVIDEO2X_LOG_LEVEL_OFF;
+    } else {
+        fprintf(stderr, "Warning: Invalid log level specified. Defaulting to 'info'.\n");
+        return LIBVIDEO2X_LOG_LEVEL_INFO;
+    }
+}
+
 // Wrapper function for video processing thread
 int process_video_thread(void *arg) {
     struct ProcessVideoThreadArguments *thread_args = (struct ProcessVideoThreadArguments *)arg;
 
     // Extract individual arguments
+    enum Libvideo2xLogLevel log_level = parse_log_level(thread_args->arguments->loglevel);
     struct arguments *arguments = thread_args->arguments;
     enum AVHWDeviceType hw_device_type = thread_args->hw_device_type;
     struct FilterConfig *filter_config = thread_args->filter_config;
@@ -336,8 +386,9 @@ int process_video_thread(void *arg) {
 
     // Call the process_video function
     int result = process_video(
-        arguments->input_filename,
+        arguments->in_fname,
-        arguments->output_filename,
+        arguments->out_fname,
+        log_level,
         arguments->benchmark,
         hw_device_type,
         filter_config,
@@ -364,8 +415,8 @@ int main(int argc, char **argv) {
     struct FilterConfig filter_config;
     if (strcmp(arguments.filter_type, "libplacebo") == 0) {
         filter_config.filter_type = FILTER_LIBPLACEBO;
-        filter_config.config.libplacebo.output_width = arguments.output_width;
+        filter_config.config.libplacebo.out_width = arguments.out_width;
-        filter_config.config.libplacebo.output_height = arguments.output_height;
+        filter_config.config.libplacebo.out_height = arguments.out_height;
         filter_config.config.libplacebo.shader_path = arguments.shader_path;
     } else if (strcmp(arguments.filter_type, "realesrgan") == 0) {
         filter_config.filter_type = FILTER_REALESRGAN;
@@ -397,8 +448,8 @@ int main(int argc, char **argv) {
 
     // Setup encoder configuration
     struct EncoderConfig encoder_config = {
-        .output_width = 0,   // To be filled by libvideo2x
+        .out_width = 0,   // To be filled by libvideo2x
-        .output_height = 0,  // To be filled by libvideo2x
+        .out_height = 0,  // To be filled by libvideo2x
         .copy_streams = !arguments.nocopystreams,
         .codec = codec->id,
         .pix_fmt = pix_fmt,
@@ -436,10 +487,9 @@ int main(int argc, char **argv) {
         .proc_ctx = &proc_ctx
     };
 
-// Enable non-blocking input
+    // Register a newline-safe log callback for FFmpeg
-#ifndef _WIN32
+    // This will ensure that log messages are printed on a new line after the progress bar
-    set_nonblocking_input(true);
+    av_log_set_callback(newline_safe_ffmpeg_log_callback);
-#endif
 
     // Create a thread for video processing
     thrd_t processing_thread;
@@ -447,8 +497,12 @@ int main(int argc, char **argv) {
         fprintf(stderr, "Failed to create processing thread\n");
         return 1;
     }
-    printf("[Video2X] Video processing started.\n");
+    printf("Video processing started; press SPACE to pause/resume, 'q' to abort.\n");
-    printf("[Video2X] Press SPACE to pause/resume, 'q' to abort.\n");
+
+// Enable non-blocking input
+#ifndef _WIN32
+    set_nonblocking_input(true);
+#endif
 
     // Main thread loop to display progress and handle input
     while (!proc_ctx.completed) {
@@ -468,37 +522,36 @@ int main(int argc, char **argv) {
             // Toggle pause state
             proc_ctx.pause = !proc_ctx.pause;
             if (proc_ctx.pause) {
-                printf("\n[Video2X] Processing paused. Press SPACE to resume, 'q' to abort.");
+                printf("\nProcessing paused. Press SPACE to resume, 'q' to abort.\n");
             } else {
-                printf("\n[Video2X] Resuming processing...");
+                printf("Resuming processing...\n");
             }
-            fflush(stdout);
         } else if (ch == 'q' || ch == 'Q') {
             // Abort processing
-            printf("\n[Video2X] Aborting processing...");
+            printf("\nAborting processing...\n");
-            fflush(stdout);
             proc_ctx.abort = true;
+            newline_required = false;
             break;
         }
 
         // Display progress
-        if (!proc_ctx.pause && proc_ctx.total_frames > 0) {
+        if (!arguments.noprogress && !proc_ctx.pause && proc_ctx.total_frames > 0) {
             printf(
-                "\r[Video2X] Processing frame %ld/%ld (%.2f%%); time elapsed: %lds",
+                "\rProcessing frame %ld/%ld (%.2f%%); time elapsed: %lds",
                 proc_ctx.processed_frames,
                 proc_ctx.total_frames,
                 proc_ctx.total_frames > 0
-                    ? proc_ctx.processed_frames * 100.0 / proc_ctx.total_frames
+                    ? (double)proc_ctx.processed_frames * 100.0 / (double)proc_ctx.total_frames
                     : 0.0,
                 time(NULL) - proc_ctx.start_time
             );
             fflush(stdout);
+            newline_required = true;
         }
 
-        // Sleep for a short duration
+        // Sleep for 50ms
-        thrd_sleep(&(struct timespec){.tv_sec = 0, .tv_nsec = 100000000}, NULL);  // Sleep for 100ms
+        thrd_sleep(&(struct timespec){.tv_sec = 0, .tv_nsec = 100000000}, NULL);
     }
-    puts("");  // Print newline after progress bar is complete
 
 // Restore terminal to blocking mode
 #ifndef _WIN32
@@ -509,31 +562,37 @@ int main(int argc, char **argv) {
     int process_result;
     thrd_join(processing_thread, &process_result);
 
+    // Print a newline if progress bar was displayed
+    if (newline_required) {
+        putchar('\n');
+    }
+
+    // Print final message based on processing result
     if (proc_ctx.abort) {
         fprintf(stderr, "Video processing aborted\n");
         return 2;
-    }
+    } else if (process_result != 0) {
-
-    if (process_result != 0) {
         fprintf(stderr, "Video processing failed\n");
         return process_result;
+    } else {
+        printf("Video processing completed successfully\n");
     }
 
     // Calculate statistics
     time_t time_elapsed = time(NULL) - proc_ctx.start_time;
     float average_speed_fps =
-        (float)proc_ctx.processed_frames / (time_elapsed > 0 ? time_elapsed : 1);
+        (float)proc_ctx.processed_frames / (time_elapsed > 0 ? (float)time_elapsed : 1);
 
     // Print processing summary
     printf("====== Video2X %s summary ======\n", arguments.benchmark ? "Benchmark" : "Processing");
-    printf("Video file processed: %s\n", arguments.input_filename);
+    printf("Video file processed: %s\n", arguments.in_fname);
     printf("Total frames processed: %ld\n", proc_ctx.processed_frames);
     printf("Total time taken: %lds\n", time_elapsed);
     printf("Average processing speed: %.2f FPS\n", average_speed_fps);
 
     // Print additional information if not in benchmark mode
     if (!arguments.benchmark) {
-        printf("Output written to: %s\n", arguments.output_filename);
+        printf("Output written to: %s\n", arguments.out_fname);
     }
 
     return 0;