These three models support multi-modal control video customization tasks, including reference-to-video, reference-mask-to-video, reference-depth-to-video, and reference-instruction-to-video generation. Our models are based on Wan2.1-1.3B, Wan2.1-14B, Wan2.2-14B, and VACE. Here are some comparisons with the state-of-the-art method VACE on video customization:

· (a) 2.1-1.3B model

· (b) 2.1-14B model

· (c) 2.2-14B model

Please refer to our GitHub repo for more detailed instructions on using our code and models.

Our models are trained on our curated dataset:

We provide 648 data samples to test our models

For more video customization results, please refer to our project page:

For more technical details, please refer to our NeurIPS 2025 paper:

If you find our code, data, and models useful, please consider citing our paper: