WoLNamesBlackedOut for OBS v1.0.3

WoLNamesBlackedOut for OBS

This plugin hides character names from the FF14 screen when streaming (capturing) with OBS.
This is an OBS plugin port of the Windows application "WoLNamesBlackedOut".
This program partially utilizes AI-generated code.

The original is here:
https://github.com/royshil/obs-detect

This fork adds the YOLODetector class and supports custom YOLO26 models.
It also improves FPS by threading inference.

Changes from the Original

• YOLODetector Class: Newly added YOLO26 object detection class
• Threaded ONNX Runtime inference achieved 50 FPS in our environment
• Removed EdgeYOLO, face detection, tracking, etc.

Operating Environment
Tested on the following:

• Windows 11 25H2 64bit
• OBS 32.1.2
• Intel 11400F
• Geforce RTX 4700TiS 16GB

Since it uses DirectML, it should also work with Radeon.

DirectML inference is performed while running FF14, but the load is not that high and it does not interfere with gameplay.
This plugin automatically hides character names in Final Fantasy XIV.
Just add the filter to your game capture source and it works instantly.

Installation

1. Download the latest obs-wolnamesblackedout_x.x.x.zip from Releases.
2. Close OBS.
3. Extract the entire ZIP file and copy the resulting obs-wolnamesblackedout folder to %ProgramData%\obs-studio\plugins\.
   Alternatively, check the contents of the included install.ps1, right-click on it, and select "Run with PowerShell". Copy it to the folder mentioned above. Administrator privileges are required, so a Smart Screen confirmation screen will appear.
   (Usually it's `C:\ProgramData\obs-studio\plugins\`.
   ProgramData is a hidden folder, so it's recommended to copy and paste it into the address bar of Explorer and open the corresponding folder.)
4. Add the "WoLNamesBlackedOut" filter to game capture in OBS and use it.

## Third Party Libraries & Licenses

This project incorporates the following third-party components:

• ONNX Runtime(MIT): High-performance ML inference runtime
• OpenCV(Apache 2.0): Computer vision library

Note: This project is distributed under the GPLv2 license as per the original work.