There are 2 repositories under video-prediction-models topic.
A TensorFlow Implementation of "Deep Multi-Scale Video Prediction Beyond Mean Square Error" by Mathieu, Couprie & LeCun.
This's an implementation of deepmind Visual Interaction Networks paper using pytorch
Video Predicting using ConvLSTM and pytorch
Adds a block that predicts state variables (velocity, acceleration) to seq2seq motion prediction models