---
license: apache-2.0
---
# Over++: Generative Video Compositing for Layer Interaction Effects 

[Paper](https://huggingface.co/papers/2512.19661) | [Project page](https://overplusplus.github.io/)

## Overview

This Hugging Face repository contains the transformer weights for the model used in the CogVideo pipeline [here](https://github.com/aigc-apps/VideoX-Fun).

You can load the transformer weights using the command below:
```
python inference/cogvideox_fun/predict_v2v.py \
    --config.experiment.save_foreground=True \
    --config.experiment.save_path="output_temp" \
    --config.data.data_rootdir="examples" \
    --config.experiment.run_seqs="boy-water,pexles_car_drift" \
    --config.experiment.skip_if_exists=False \
    --config.data.dilate_width=0 \
    --config.video_model.guidance_scale=6 \
    --config.video_model.transformer_path="PATH/TO/CHECKPOINTS/diffusion_pytorch_model.safetensors"
```

For more details, please refer to the GitHub repository [here](https://github.com/luchaoqi/overplusplus?tab=readme-ov-file#single-gpu-inference)