image/gif
The model predicts the inbetween frames (mid frame), given two key frames.
pip install opencv-python
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
This will load the model from checkpoints.
This generates images for evaluation.
This evaluates the generated images.
Add frames in test_frames folder.
This combines those 3 frames into .mp4 format.
