Basic Configuration
k4yt3x edited this page Feb 11, 2022
·
1 revision
This page will cover the basics of the Video2X configuration file.
# Name: Video2X Configuration File
# Creator: K4YT3X
# Date Created: October 23, 2018
# Last Modified: May 14, 2020
# Values here are the default values. Change the value here to
# save the default value permanently.
# Items commented out are parameters irrelevant to this context
# or parameters handled by Video2X internally.
waifu2x_caffe:
path: '%LOCALAPPDATA%\video2x\waifu2x-caffe\waifu2x-caffe-cui'
tta: 0 # <0|1> 8x slower and slightly high quality
gpu: 0 # gpu device no
batch_size: 1 # input batch size
crop_h: null # input image split size(height)
crop_w: null # input image split size(width)
crop_size: 128 # input image split size
output_depth: 8 # output image chanel depth bit
output_quality: -1 # output image quality
process: gpu # <cpu|gpu|cudnn> process mode
model_dir: null # path to custom model directory (don't append last / )
scale_height: 0 # custom scale height (specifying this will overwrite scale_ratio)
scale_width: 0 # custom scale width (specifying this will overwrite scale_ratio)
#scale_ratio: null # custom scale ratio
noise_level: 3 # <0|1|2|3> noise reduction level
mode: noise_scale # <noise|scale|noise_scale|auto_scale> image processing mode
output_extention: null # extension to output image file when output_path is (auto) or input_path is folder
input_extention_list: null # extension to input image file when input_path is folder
#output_path: null # path to output image file (when input_path is folder, output_path must be folder)
#input_path: null # (required) path to input image file
waifu2x_converter_cpp:
path: '%LOCALAPPDATA%\video2x\waifu2x-converter-cpp\waifu2x-converter-cpp'
#list-supported-formats: null # dump currently supported format list
#list-opencv-formats: null # (deprecated. Use --list-supported-formats) dump opencv supported format list
#list-processor # dump processor list
output-format: null # The format used when running in recursive/folder mode
png-compression: 5 # Set PNG compression level (0-9), 9 = Max compression (slowest & smallest)
image-quality: -1 # JPEG & WebP Compression quality (-1-101, 0 being smallest size and lowest quality, -1 being default), use 101 for lossless WebP
block-size: 0 # block size
disable-gpu: false # disable GPU
force-OpenCL: false # force to use OpenCL on Intel Platform
processor: -1 # set target processor (-1 uses default device)
jobs: 0 # number of threads launching at the same time
model-dir: null # path to custom model directory (don't append last / ) default: models_rgb
#scale-ratio: 2.0 # custom scale ratio
noise-level: 1 # <0|1|2|3> noise reduction level
mode: noise-scale # <noise|scale|noise-scale> image processing mode
log-level: 1 # <0|1|2|3|4> Set log level
silent: true # Enable silent mode. (same as --log-level 1)
tta: 0 # Enable Test-Time Augmentation mode. (0 or 1)
#generate-subdir: 0 # Generate sub folder when recursive directory is enabled.
#auto-naming: 0 # Add postfix to output name when output path is not specified.
#recursive-directory: 0 # Search recursively through directories to find more images to process.
#output: null # path to output image file or directory (you should use the full path)
#input: null # (required) path to input image file or directory (you should use the full path)
waifu2x_ncnn_vulkan:
path: '%LOCALAPPDATA%\video2x\waifu2x-ncnn-vulkan\waifu2x-ncnn-vulkan'
v: null # verbose output
#i: null # input-path: input image path (jpg/png) or directory
#o: null # output-path: output image path (png) or directory
'n': 2 # noise-level: denoise level (-1/0/1/2/3, default=0)
s: 2 # scale: upscale ratio (1/2, default=2)
t: 400 # tile-size: tile size (>=32, default=400)
m: null # model-path: waifu2x model path (default=models-cunet)
g: 0 # gpu-id: gpu device to use (default=0)
j: '1:2:2' # thread count for load/proc/save (default=1:2:2)
x: false # enable tta mode
srmd_ncnn_vulkan:
path: '%LOCALAPPDATA%\video2x\srmd-ncnn-vulkan\srmd-ncnn-vulkan'
v: null # verbose output
#i: null # input-path: input image path (jpg/png) or directory
#o: null # output-path: output image path (png) or directory
'n': 3 # noise-level: denoise level (-1/0/1/2/3/4/5/6/7/8/9/10, default=3)
s: 2 # upscale ratio (2/3/4, default=2)
t: 400 # tile-size: tile size (>=32, default=400)
m: null # srmd model path (default=models-srmd)
g: 0 # gpu device to use (default=0)
j: '1:2:2' # thread count for load/proc/save (default=1:2:2)
x: false # enable tta mode
anime4kcpp:
path: '%LOCALAPPDATA%\video2x\anime4kcpp\CLI\Anime4KCPP_CLI\Anime4KCPP_CLI'
#input: null # File for loading (string [=./pic/p1.png])
#output: null # File for outputting (string [=output.png])
passes: 2 # Passes for processing (int [=2])
pushColorCount: 2 # Limit the number of color pushes (int [=2])
strengthColor: 0.3 # Strength for pushing color,range 0 to 1,higher for thinner (double [=0.3])
strengthGradient: 1.0 # Strength for pushing gradient,range 0 to 1,higher for sharper (double [=1])
zoomFactor: 2.0 # zoom factor for resizing (double [=2])
threads: 16 # Threads count for video processing (unsigned int [=16])
fastMode: false # Faster but maybe low quality
videoMode: false # Video process
preview: null # Preview image
preprocessing: False # Enable pre processing
postprocessing: False # Enable post processing
preFilters: 4 # Enhancement filter, only working when preProcessing is true,there are 5 options by binary:Median blur=0000001, Mean blur=0000010, CAS Sharpening=0000100, Gaussian blur weak=0001000, Gaussian blur=0010000, Bilateral filter=0100000, Bilateral filter faster=1000000, you can freely combine them, eg: Gaussian blur weak + Bilateral filter = 0001000 | 0100000 = 0101000 = 40(D) (unsigned int [=4])
postFilters: 40 # Enhancement filter, only working when postProcessing is true,there are 5 options by binary:Median blur=0000001, Mean blur=0000010, CAS Sharpening=0000100, Gaussian blur weak=0001000, Gaussian blur=0010000, Bilateral filter=0100000, Bilateral filter faster=1000000, you can freely combine them, eg: Gaussian blur weak + Bilateral filter = 0001000 | 0100000 = 0101000 = 40(D), so you can put 40 to enable Gaussian blur weak and Bilateral filter, which also is what I recommend for image that < 1080P, 48 for image that >= 1080P, and for performance I recommend to use 72 for video that < 1080P, 80 for video that >=1080P (unsigned int [=40])
GPUMode: False # Enable GPU acceleration
listGPUs: null # list GPUs
platformID: 0 # Specify the platform ID (unsigned int [=0])
deviceID: 0 # Specify the device ID (unsigned int [=0])
codec: mp4v # Specify the codec for encoding from mp4v(recommended in Windows), dxva(for Windows), avc1(H264, recommended in Linux), vp09(very slow), hevc(not support in Windowds), av01(not support in Windowds) (string [=mp4v])
ffmpeg:
ffmpeg_path: '%LOCALAPPDATA%\video2x\ffmpeg-latest-win64-static\bin'
intermediate_file_name: 'intermediate.mkv'
# Step 1: Frame Extraction
# extract all frames from original input into temporary directory
extract_frames:
'-hwaccel': auto # automatically select hardware acceleration method
'-y': true
input_options: {} # empty dict, expand if necessary
output_options:
'-pix_fmt': rgba64be # extracted frames pixel format
'-qscale:v': null # output image quality control for JPEG (1-31, 1 being highest)
# Step 2: Video Assembly
# assemble all frames back into a video with only a video track
assemble_video:
'-hwaccel': auto # automatically select hardware acceleration method
'-y': true
input_options:
'-f': image2 # force image2 format
output_options:
'-vcodec': libx264 # video codec
'-pix_fmt': 'yuv444p10le' # overwrite default pixel format
'-crf': 17 # H.264 Constant Rate Factor
'-b:v': null # target average bitrate
'-vf': 'pad=ceil(iw/2)*2:ceil(ih/2)*2' # ensure output is divisible by 2, recommended for libx264
# Step 3: Streams Migration
# migrate audio and subtitle streams from original
# video into the upscaled video
migrate_streams:
'-hwaccel': auto # automatically select hardware acceleration method
'-y': true
input_options: {} # empty dict, expand if necessary
output_options:
'-map':
- '0:v?' # copy video streams
- '1:a?' # copy audio streams
- '1:s?' # copy subtitle streams
- '1:d?' # copy data streams
- '1:t?' # copy fonts
'-c': copy # copy codec for all streams
'-map_metadata': 0 # copy known metadata tags
# '-movflags': 'use_metadata_tags' # copy custom/arbitrary metadata tags
'-pix_fmt': null
'-metadata': 'comment=Upscaled by Video2X'
gifski:
gifski_path: '%LOCALAPPDATA%\video2x\gifski\win\gifski'
# output: null # Destination file to write to
# fps: 20 # Animation frames per second (for PNG frames only) [default: 20]
fast: false # 3 times faster encoding, but 10% lower quality and bigger file
quality: 100 # Lower quality may give smaller file
width: null # Maximum width
height: null # Maximum height (if width is also set)
once: false # Do not loop the GIF
nosort: false # Use files exactly in the order given, rather than sorted
quiet: false # Do not show a progress bar
video2x:
video2x_cache_directory: null # default: %TEMP%\video2x
image_format: png
preserve_frames: false