---
license: apache-2.0
base_model:
- Wan-AI/Wan2.2-T2V-A14B
pipeline_tag: text-to-video
tags:
- looping
- RGB
- RGBA
- video
- generation
---

<div align="center">

  <h1 style="font-size:2.5em; font-weight:700; line-height:1.25; margin:0 0 16px; padding-bottom:.3em; border-bottom:1px solid rgba(128,128,128,.35);">
    <img src="assets/loopy-logo.apng" alt="Loopy logo" height="42" style="height:1.2em; width:auto; display:inline-block; vertical-align:middle; margin-right:10px;"/>
    Loopy
  </h1>

  <h3 style="font-size:1.5em; font-weight:600; line-height:1.3; margin:0 0 16px;">Seamless Video Loop Generation via Anchored Looping Shift of Positional Embedding</h3>

[![arXiv](https://img.shields.io/badge/arXiv-2608.23090-red)](http://arxiv.org/abs/2608.23090)
[![Project Page](https://img.shields.io/badge/Project_Page-Link-green)](https://donghaotian123.github.io/Loopy/)
[![GitHub](https://img.shields.io/badge/GitHub-Repo-black?logo=github)](https://github.com/WeChatCV/Loopy)

</div>

<img src="assets/teaser.png" alt="Loopy Qualitative Results" style="max-width: 100%; height: auto;">

>Our **Loopy** generates high-quality looping videos with seamless transitions at loop boundaries and diverse motion. It also supports RGBA with semi-transparent effects. In the application block, all elements—including game assets and Loopy character stickers—are generated by our **Loopy**.

---

### 🔥 News
* **[2026.8.24]** Released Loopy, the Wan2.2-T2V-A14B–adapted weights and inference code are now open-sourced.
* **[2026.8.24]** Our technical report is available on [arXiv](https://arxiv.org/abs/XXXX.XXXXX).

---

### 📝 To-Do List

- [x] **Paper**: Release the technical report on arXiv.
- [x] **Inference Code**: Released the looping inference pipeline for Loopy.
- [x] **Model Weights**: Release the high-noise / low-noise LoRA checkpoints.

---
### 🌟 Showcase

##### Seamless Looping Video Generation

<!-- | Prompt | Preview Video | Alpha Video |
| :---: | :---: | :---: |
| "Medium shot. A little girl holds a bubble wand and blows out colorful bubbles that float and pop in the air. The background of this video is transparent. Realistic style." |
  <div style="display: flex; gap: 10px;">
    <img src="girl.gif" alt="..." style="flex: 1; min-width: 200px;">
  </div> |
  <div style="display: flex; gap: 10px;">
    <img src="girl_pha.gif" alt="..." style="flex: 1; min-width: 200px;">
  </div> | -->
| Preview Video | Preview Video |
| :---: | :---: |
| <img src="assets/human.apng" width="320" height="180" style="object-fit:contain; display:block; margin:auto;"/> | <img src="assets/loopy-6.apng" width="320" height="180" style="object-fit:contain; display:block; margin:auto;"/> |

##### For more results, please visit [Our Website](https://donghaotian123.github.io/Loopy/)

### 🚀 Quick Start

##### 1. Environment Setup

```bash
# Clone the project repository
git clone https://github.com/WeChatCV/Loopy.git
cd Loopy

# Create and activate Conda environment
conda create -n Loopy python=3.11 -y
conda activate Loopy

# Install dependencies
pip install -r requirements.txt
```

##### 2. Model Download

Download [Wan2.2-T2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B)

Download the LightX2V 4-step distillation LoRAs for both experts:
[high noise](https://huggingface.co/lightx2v/Wan2.2-Distill-Loras/blob/main/wan2.2_t2v_A14b_high_noise_lora_rank64_lightx2v_4step_1217.safetensors) /
[low noise](https://huggingface.co/lightx2v/Wan2.2-Distill-Loras/blob/main/wan2.2_t2v_A14b_low_noise_lora_rank64_lightx2v_4step_1217.safetensors)

Download [Loopy](https://huggingface.co/htdong/Loopy) (`high_noise.safetensors` and
`low_noise.safetensors`)

---

### 🧪 Usage

Write one prompt per line in a plain UTF-8 text file, then launch the batch inference:

```bash
output_path="./checkpoints"
mkdir -p $output_path

torchrun --nproc_per_node=8  generate_2.2_new.py --task t2v-A14B --size 832*480 \
        --ckpt_dir Wan-AI/Wan2.2-T2V-A14B \
        --dit_fsdp --t5_fsdp --ulysses_size 8 \
        --frame_num 53 \
        --sample_steps 4 \
        --high_lightx2v_path "wan2.2_lora/wan2.2_t2v_A14b_high_noise_lora_rank64_lightx2v_4step_1217.safetensors" \
        --low_lightx2v_path "wan2.2_lora/wan2.2_t2v_A14b_low_noise_lora_rank64_lightx2v_4step_1217.safetensors" \
        --high_lora_path high_noise.safetensors \
        --low_lora_path low_noise.safetensors \
        --prompt_file prompt.txt \
        --output_dir $output_path/results  2>&1 | tee -a $output_path/results.log

```

Or simply run the packaged script after editing the paths inside it:

```bash
bash test.sh
```

You can specify the weights of `Wan2.2-T2V-A14B` with `--ckpt_dir`, the LightX2V distillation
LoRAs with `--high_lightx2v_path` / `--low_lightx2v_path`, and the Loopy LoRAs with
`--high_lora_path` / `--low_lora_path`. Wan2.2-T2V-A14B is a two-expert MoE model, so the
high-noise and low-noise branches each need their own pair of LoRAs.

Generated videos are written to `--output_dir`, one subdirectory per prompt, each containing
`fgr.mp4`.



**Prompt Writing Tip:** Describe a subject whose motion is naturally periodic or continuous —
falling snow, drifting clouds, flowing water, a walking animal, a rotating object. State the
visual style and the shot type (close-up, medium shot, wide shot) as well. Prompts support
both Chinese and English input.

```bash
# An example of prompt.
An Arctic fox leaps nimbly through the snow while hunting, its white fur blending seamlessly with the snowflakes. Realistic style; a scene of winter wildlife.
```

---

### 🤝 Acknowledgements

This project is built upon the following excellent open-source projects:
* [Wan2.2](https://github.com/Wan-Video/Wan2.2) (base video generation model)
* [LightX2V](https://github.com/ModelTC/LightX2V) (inference acceleration)
* [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) (training/inference framework)

We sincerely thank the authors and contributors of these projects.

---

### ✏️ Citation

If you find our work helpful for your research, please consider citing our paper:

```bibtex
@article{haotiandong2026loopy,
  title   = {Loopy: Seamless Video Loop Generation via Anchored Looping Shift of Positional Embedding},
  author  = {Haotian Dong, Wenjing Wang, Chen Li, Jing Lyu, Xin Wang, Di Lin},
  journal = {arXiv preprint},
  year    = {2026}
}
```

---

### 📬 Contact Us

If you have any questions or suggestions, feel free to reach out via
[GitHub Issues](https://github.com/WeChatCV/Loopy/issues). We look forward to your feedback!