Skip to content
  • There are no suggestions because the search field is empty.

Training Data

Improve the quality of your Vub by uploading additional Training Data

Training Data is more content of the person you are vubbing.

NOTE: Additional Training Data can only be added to Standard, Professional and Theatrical Vubs.

How Training Data Works

Clean shots of the character from other takes or excess footage can loaded into DeepEditor. This enables DeepEditor to create a more accurate mask & smoother mouth movements.

Training Data does not direct how your Vub will sound, additional information will ultimately produce a better visual result

Training data must be the same character that you are Vubbing. For the best results:

  • Use alternate takes of the same shot as your Source Media
  • Keep the actor's face pointing towards camera with both eyes in frame 
  • The actor's face should be clear and unobstructed
  • Each clip should have lighting similar to your Source Media

For more information on creating and preparing Training Data for your shot visit "Asset Specifications" here in the Knowledge Base.

Uploading Driving Data

Drag and drop training data files or click "Add Training Data" just like you did with the Source and Driving Data media. Currently, you can upload a maximum of 10 video files limited to a total of 1400 frames each.

Once you have uploaded them, you will be prompted to select which files you want to use before creating your Vub.

Your Training Data uploads can take a bit longer to upload than your Source Media & Driving Data.

The Benefit of Training Data

Here is an example of how adding Training Data can improve your Vub.

Original

 

Without Training Data

 

With Training Data

 

You can see in the final image, with Training Data, how her teeth and mouth interior is a lot more defined.