We would decide a length and a resolution (say 1920x1080@30fps, 90 seconds), then how to partition those seconds and pixels among the participants. Layered? Sequential? Blended together? What is the topic of the day? B&W? Color? Which palette? What constraints do we apply?
We could have a whiteboard to have an overview of who is doing what. And some tools like a microphone, video camera, a green screen to record video and remove the background for easy layering...