Scribd Logo
Upload

Welcome to Scribd!

  • 52 views

    Gigapixel AI For Video Help Document

    Uploaded by

    Emmanuel Tovar
    This document provides help and guidance for using Gigapixel AI for Video. It supports common video formats like MP4, MOV, and AVI. For non-command line use, right click a video file and select the program from the context menu. The command line interface allows batch processing and customization using parameters for factors like upscaling level, output format and size, GPU device selection, and video clipping. Minimum hardware is a GTX 1050 GPU but CPU or iGPU can also be used at lower performance.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Gigapixel AI For Video Help Document

    Uploaded by

    Emmanuel Tovar
    52 views6 pages
    This document provides help and guidance for using Gigapixel AI for Video. It supports common video formats like MP4, MOV, and AVI. For non-command line use, right click a video file and select the program from the context menu. The command line interface allows batch processing and customization using parameters for factors like upscaling level, output format and size, GPU device selection, and video clipping. Minimum hardware is a GTX 1050 GPU but CPU or iGPU can also be used at lower performance.

    Original Title

    Giga

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document provides help and guidance for using Gigapixel AI for Video. It supports common video formats like MP4, MOV, and AVI. For non-command line use, right click a video file and select the program from the context menu. The command line interface allows batch processing and customization using parameters for factors like upscaling level, output format and size, GPU device selection, and video clipping. Minimum hardware is a GTX 1050 GPU but CPU or iGPU can also be used at lower performance.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    52 views6 pages

    Gigapixel AI For Video Help Document

    Uploaded by

    Emmanuel Tovar
    This document provides help and guidance for using Gigapixel AI for Video. It supports common video formats like MP4, MOV, and AVI. For non-command line use, right click a video file and select the program from the context menu. The command line interface allows batch processing and customization using parameters for factors like upscaling level, output format and size, GPU device selection, and video clipping. Minimum hardware is a GTX 1050 GPU but CPU or iGPU can also be used at lower performance.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 6

    Gigapixel AI for Video Help Document

            If using via command line (videosrcmd.exe), please refer to the usage text for 
    parameter information.

            For non-command line usage, Gigapixel AI for Video is registered with many 
    common video formats by default. File types supported include avi, flv, m1v, mkv, 
    mov, mp4, mpg, mpeg, webm, and wmv.

    To use the program, follow these steps for your video file.

    1. Navigate to your file

    2. Right click your file and find the Gigapixel AI for Video entry that is made after 
    install.

    3. Use the context menu to select your operation. It may take a few seconds for it to 
    open.
    Gigapixel AI for Video Command Line Mode Guide

    1. Please open a command line terminal. You can type "cmd" in your run window to 
    find it.
    2. Run videosrcmd.exe "inputVideoPath" with the following parameters:

    Parameter Usage Default setting

    -help Print this help N/A

    -o outputPath Set output video path. Must have  "inputvideo_Nx.mp4" in the same 


    extension ".mp4" or ".png"or  folder of input video where N for 
    ".tif" or ".tiff" upscale factor (1, 2, or 4)

    -16bit Output 16 bit png sequence. Only  8 bit pngs


    effect for png output

    -s 1|2|4  Set upscale factor as 100%,  200%


    200%, or 400%

    -w pixels Explicitly set output video width 200% of input video width

    -h pixels Explicitly set output video height 200% of input video height

    -fps outputFPS Explicitly set output video FPS Input video FPS or 30 if input as image 


    sequence

    -c Fit
    Crop output video if needed, 
    otherwise fit video inside output 
    size

    -b seconds Set processing start point (in  0
    second) 

    -e seconds Set processing end point (in  End of video


    second)

    -nvidia 0|1|2|3| 0,1,2,3: explicitly uses nvidia  Auto detection


    10 GPU device #0,1,2,3 (same index 
    as nvidia-smi)
    10: use CPU/iGPU.

    -vram 10-90  Set available VRAM manually.  Auto detection


    (in percentage) Will use only a fraction of the 
    VRAM (10% - 90%)

    -l username  Login with username(email  N/A


    password address) and password

    -nd No preview display windows N/A

    Examples:

    1). videosrcmd.exe "C:\test.mp4"

    Will process the video under path "C:\test.mp4" and save the output as a .mp4 file into 
    "C:\test_2x.mp4". The upscale factor will be 200%. Whole video will be processed. Device 
    will be automatically chosen.

    2). videosrcmd.exe "C:\test2.mp4" -o "C:\test_output_pngs\test2_outputs.png" -s 4 -b 3 -


    e 6 -nvidia 1 -vram 70

    Will process the video under path "C:\test2.mp4" and save the output frames as pngs under the 
    folder
    "C:\test_output_pngs\test2_outputs". If there is no such folder, the software will create one. 
    The upscale factor will be 400%. Video will be processed from the 3rd second to the 6th 
    second. The software will run by Nvidia GPU. If your device has two GPUs, please make sure 
    to set the gpu number to the correct one (same index as nvidia-smi). In this example, Nvidia 
    GPU device number is 1. The VRAM will be used is 70% of the total available VRAM.

    3). videosrcmd.exe "C:\test3.mp4" -o "C:\test_output_pngs\test3_outputs.png" -16bit -w


    1920 -h 1060 - c -nvidia 10 -nd

    Will process the video under path "C:\test3.mp4" and save the output frames as pngs under the 
    folder
    "C:\test_output_pngs\test3_outputs". If there is no such folder, the software will create one. 
    Output pngs will be 16bit with 1920 pixels in width and 1060 pixels in height. If the output 
    aspect ratio is different from the input, it will be cropped. The upscale factor will be 200%. 
    Whole video will be processed. The software will run by iGPU/CPU. No preview display 
    windows will be shown.

    4). videosrcmd.exe "C:\test_image_sequence\image_%06d.png" -fps 60

    Will process the images under path "C:\test_image_sequence\" and save the output as a .mp4 
    file under the same path. Images should be in png format, and their names should be like 
    "image_000000.png", "image_000001.png", "image_000002.png", and so on. Output video 
    will be in 60 FPS.

    3. You are all set! Please wait for your upsampled video and enjoy it!

    Gigapixel AI for Video FAQs

    1. What is the minimum hardware requirement for Gigapixel AI for Video?


    We suggest you to run Gigapixel AI for Video on high end Nvidia graphic cards. The 
    minimum requirement is GTX 1050 with 4 GB VRAM. Any graphic card later than GTX 1080 
    (included) will do a fairly fast job.
    If you do not have a Nvidia graphic card in your device, the software can run on your 
    Intel iGPU. Typically, it will be 5 times slower. If you do not have an Intel iGPU, the software 
    will finally fall back to you CPU, which can be 10 times slower than the Nvidia GPU version.

    2. Can Gigapixel AI for Video work on Macs?


    For now, Gigapixel AI for Video cannot work on Macs. It can only work on Windows 
    devices.

    3. Can I do batch processing on several videos?


    Sure you can! Please check the "Gigapixel AI for Video Command Line Mode Guide" 
    to make sure how to write command line instructions. You can write all the instructions in 
    separated lines into a .bat file and then run it. 
    There is an example .bat file in your video folder after installation. You can check and 
    run the "test.bat" there. It will help you to generate 2 sample upscaled videos.

    4. My machine cannot meet the minimum requirement. Is there a way that I can use this
    product?
    We have a cloud service that can help you to upscale your videos online. Please 
    check https://videoai.topazlabs.com/ for more details!

    5. How long it will take to process a video?


    We tested mainly on Nvidia GTX 1080. For a video from HD to 8K, it typically takes 
    4-5 seconds for each frame. If you upscale a video from SD to HD, it will take about 0.5 
    second for each frame.

    6. What is the maximum size of an output video I can get?


    Now we support up to 8K video output. Any size larger than 8K will cause a failure.

    7. Can I process interlaced video?


    Not directly. If your video is interlaced, please deinterlace it first before using 
    Gigapixel AI for Video to upscaling it. We are working on a deinterlacer AI at this moment, 
    stay tuned.

    8. My machine has more than one Nvidia GPU, can I use all of them?
    Yes and No. The program itself only use one GPU. However, you can open multiple 
    command consoles and use videosrcmd.exe with -gpu 0 or -gpu 1 to run each GPU on a 
    separate video at the same time.

    9. Can I read in a sequence of image as input?


    Yes but you have to set it up via command line. Please refer to example 4) in 
    “Gigapixel AI for Video Command Line Mode Guide”.

    10. My GPU utilization seems low in task manager. Is there something wrong?
    In fact it is normal. The GPU utilization in task manager is not precise. If you want to 
    track the actual GPU usage, please try nvidia-smi.

    You might also like