Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- text-to-image
+- text-to-video
 - lora
 - diffusers
 - template:diffusion-lora
@@ -26,13 +26,118 @@ base_model: Wan-AI/Wan2.1-T2V-1.3B
 instance_prompt: null
 license: apache-2.0
 ---
+<a align="center">
+  <video src='https://github.com/user-attachments/assets/238d45f9-9335-42be-9b03-27ed6880ce29'></video>
+</a>
+
+<p align="center">
+   <a href='https://panowan.variantconst.com'><img src='https://img.shields.io/badge/Project-Page-Green'></a> &nbsp;
+   <a href='https://arxiv.org/abs/2505.22016'><img src='https://img.shields.io/badge/arXiv-2505.22016-b31b1b.svg'></a> &nbsp;
+   <a href='https://huggingface.co/datasets/yousiki/PanoWan'><img src='https://img.shields.io/badge/Dataset-PanoWan-yellow'></a>
+</p>
+
 # PanoWan
 
-<Gallery />
+Official repository for "PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms"
+
+## Text-to-360° Video Generation
+
+Generate panoramic videos from text prompts:
+
+<table>
+  <tr>
+    <td align="center" valign="top">
+      <video src="https://github.com/user-attachments/assets/6453d67b-60ad-42be-9a72-013f1449341a" width="200"></video>
+    </td>
+    <td align="center" valign="top">
+      <video src="https://github.com/user-attachments/assets/a494213c-ca3f-4ff1-93d2-a36df8ad8790" width="200"></video>
+    </td>
+    <td align="center" valign="top">
+      <video src="https://github.com/user-attachments/assets/4614969f-9973-421a-9fc0-4f4222e2b84b" width="200"></video>
+    </td>
+    <td align="center" valign="top">
+      <video src="https://github.com/user-attachments/assets/746e5c19-18ef-4fab-b25b-68521f0dcea9" width="200"></video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center" valign="top">
+      <video src="https://github.com/user-attachments/assets/92b0c1d9-5005-4cf4-adf2-5042e7bf0abf" width="200"></video>
+    </td>
+    <td align="center" valign="top">
+      <video src="https://github.com/user-attachments/assets/7c040660-4a9e-408f-9490-79fb5f349297" width="200"></video>
+    </td>
+    <td align="center" valign="top">
+      <video src="https://github.com/user-attachments/assets/add58417-e00c-4fae-af6f-2cbfb0b8019b" width="200"></video>
+    </td>
+    <td align="center" valign="top">
+      <video src="https://github.com/user-attachments/assets/96c64c3d-a3f3-4832-94e2-c3c1c6a3edf0" width="200"></video>
+    </td>
+  </tr>
+</table>
+
+## Zero-Shot Applications
+
+### Long Video Generation
+
+Generate extended panoramic videos using temporal windowing and seamless blending:
+
+https://github.com/user-attachments/assets/1e404ed9-0165-4a67-89e3-9f9ac9ecd052
+
+### Super Resolution
+
+Enhance low-resolution panoramic videos to 2x resolution:
+
+<div align="center">
+  <table>
+    <tr>
+      <td width="50%">
+        <video src="https://github.com/user-attachments/assets/ccb31e1f-133b-4fbb-86e2-084cf2edce28" width="100%"></video>
+        <p align="center">Low Resolution</p>
+      </td>
+      <td width="50%">
+        <video src="https://github.com/user-attachments/assets/d06ad051-9d25-4589-89aa-f15b85894119" width="100%"></video>
+        <p align="center">High Resolution</p>
+      </td>
+    </tr>
+  </table>
+</div>
+
+### Semantic Editing
+
+Edit panoramic videos with text-guided modifications:
+
+<div align="center">
+  <table>
+    <tr>
+      <td width="50%">
+        <video src="https://github.com/user-attachments/assets/951cd6ff-60df-4480-a728-9a3d38568117" width="100%"></video>
+        <p align="center">Original</p>
+      </td>
+      <td width="50%">
+        <video src="https://github.com/user-attachments/assets/c0e12443-a479-40eb-aa67-d4874b745fde" width="100%"></video>
+        <p align="center">Edited</p>
+      </td>
+    </tr>
+  </table>
+</div>
+
+### Video Outpainting
+
+Transform conventional videos to panoramic format:
 
+https://github.com/user-attachments/assets/92dca130-d5c0-423e-a285-9f6402b8db9d
 
+## Dataset
 
-## Download model
+The metadata for our dataset is released at [HuggingFace](https://huggingface.co/datasets/yousiki/PanoWan).
 
+## Citation
 
-[Download](/YOUSIKI/PanoWan/tree/main) them in the Files & versions tab.
+```bibtex
+@article{xia2025panowan,
+  title={PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms},
+  author={Xia, Yifei and Weng, Shuchen and Yang, Siqi and Liu, Jingqi and Zhu, Chengxuan and Teng, Minggui and Jia, Zijian and Jiang, Han and Shi, Boxin},
+  journal={arXiv preprint arXiv:2505.22016},
+  year={2025}
+}
+```