KALEIDO: OPEN-SOURCED MULTI-SUBJECT REFERENCE VIDEO GENERATION MODEL This repository contains the official implementation of Kaleido, proposed in our paper:
Update and News 2025.10.28: 🔥 We release the checkpoints of Kaleido-14B-S2V. 2025.10.22: 🔥 We propose Kaleido, a novel multi-subject reference video generation model. Checkpoints Download
| ckpts | Download Link | Notes | |--------------|---------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------| | Kaleido-14B | 🤗 Huggingface | Supports 512P
Use the following commands to download the model weights (We have integrated both Wan VAE and T5 modules into this checkpoint for convenience).
Arrange the model files into the following structure:
Citation If you find our work helpful, please cite our paper:
```bibtex @misc{zhang2025kaleidoopensourcedmultisubjectreference, title={Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model}, author={Zhenxing Zhang and Jiayan Teng and Zhuoyi Yang and Tiankun Cao and Cheng Wang and Xiaotao Gu and Jie Tang and Dan Guo and Meng Wang}, year={2025}, eprint={2510.18573}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2510.18573}, }