README.md

---
pipeline_tag: video-to-video
license: apache-2.0
language:
- en
base_model:
- Wan-AI/Wan2.1-T2V-1.3B
---

# DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory

We propose DecMem, a decoupled memory architecture that employs Sparse Global Memory for efficient fine-grained access to global history and Anchored Local Memory for stable and high-quality extrapolation. 

[**Project Page**](https://jeffreyyzh.github.io/DecMem-Page/) | [**Paper**](https://arxiv.org/abs/2605.31336) | [**Code**](https://github.com/KlingAIResearch/DecMem)

## Checkpoints

Download the Wan2.1 backbone (VAE + tokenizer weights used by the pipeline):

```bash
huggingface-cli download Wan-AI/Wan2.1-T2V-1.3B \
    --local-dir-use-symlinks False \
    --local-dir wan_models/Wan2.1-T2V-1.3B
```

Download DecMem trained checkpoints from HuggingFace:

```bash
huggingface-cli download KlingTeam/DecMem --local-dir checkpoints
```

Checkpoint layout expected by training / inference scripts:

```
checkpoints/
└── decmem.pt             # released weights
```

## Quick start

We provide the example video-pose pairs for quick inference. The inference is Block-by-block causal denoising manner with KV cache.

```bash
bash scripts/infer_example.sh
```

## Citation
If you find our work helpful, please cite our paper:

```bibtex
@misc{yang2026decmemminutelongconsistentworld,
      title={DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory}, 
      author={Zhenhao Yang and Xiaoshi Wu and Zhengyao Lv and Xiaoyu Shi and Xintao Wang and Pengfei Wan and Kun Gai and Kwan-Yee K. Wong},
      year={2026},
      eprint={2605.31336},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2605.31336}, 
}
```