Head Swap
Replaces the head of a person on screen with the head from a photo, hair and head shape included. The plugin redraws only the head area, so facial expressions, head turns, gestures and everything else in the frame stay as they were in the source. It works best when the head is clearly visible and does not turn too far from the camera. Processing runs on the GPU and takes noticeably longer than the clip itself.
Requirements
Linux, Windows. NVIDIA GPU with 8 GB VRAM, 16 GB of free RAM. Python 3.11. Models: ~16 GB download.
Disclaimer
The plugin code is developed by Wunjo. The models are made by third-party authors and come under their own licenses. The plugin is licensed CC BY-NC 4.0 for personal and research work, not for commercial use. Results depend on the source material and are not guaranteed. You are responsible for the content you create and for the consent of anyone whose face appears in it.
How to use
Right-click on the video clip that contains at least one human face. In the menu that appears, select “Artificial Intelligence” > “Enable Face Detection”. Rectangular overlays will appear around the detected faces in the “Project Monitor”. These overlays are only used for face detection and will not appear in the final render.
Left-click on the face rectangle and select “Head Swap” from the menu that appears. Then click on the video clip in the timeline. The “Head Region” and “Head Swap” effects will appear in the “Effects / Composition Stack” panel on the left side of the screen. The “Head Region” effect marks whose head will be replaced. If there are several people in the frame, make sure it stays on the right person throughout the clip.
In the “Head Swap” effect settings, find the “Head source” section and select the photo with the new head. If the photo has not been loaded yet, click the edit icon to load a new one. In the window that opens, select and load the desired photo. You can also use this window to view photos that have already been loaded.
Once you have selected the photo, click “Generate into the bin” and wait for the generation process to finish. When the process is complete, the generated clip with the original sound will appear in the project bin. The clip on the timeline is left unchanged.
How to install
Download the .wmplugin file. In Wunjo Make, open “Settings” and then “Plugins”, and click “Add plugin…”. Select the downloaded .wmplugin file. The plugin will be copied into the application.
The plugin’s Python environment and model weights are downloaded automatically the first time you run it, so keep your internet connection active until the process is complete. You can also download the required Python libraries and models manually from the plugin settings. An internet connection is required for the initial download, but it is not needed for subsequent use.