Depth Map
The plugin builds a depth map for every frame of a video or image. Near objects come out bright and far ones dark. Use the depth video as a control input for generating new videos, or for fog, depth of field, relighting and compositing. The depth is relative, so it shows what is closer and further but not the distance in metres. Each frame is processed on its own, so the map may flicker slightly on moving shots. Glass, mirrors and water can come out wrong.
Requirements
Linux, Windows, macOS. GPU or CPU, 2 GB VRAM for the Small model, more for Base and Large. Python 3.11. Models: from ~100 MB (Small) to ~1.3 GB (Large).
Disclaimer
The plugin code is developed by Wunjo. It uses Depth Anything V2 by its authors. The Small model is licensed under Apache 2.0 and the Base and Large models under CC BY-NC 4.0, which allows non-commercial use only. Results depend on the source material and are not guaranteed.
How to use
Right-click on the audio clip that contains at least one human face. In the menu that appears, select “Artificial Intelligence” > “Depth Map”.
The effect will appear in the “Effects / Composition Stack” panel on the left side of the screen. Сlick “Generate into the bin” within the “Depth Map” effect and wait for the generation process to complete. Upon completion, the generated file will appear on the timeline.
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.