Add pipeline tag and improve model card

Hi! I'm Niels from the Hugging Face team. I'm opening this PR to improve the model card for DreamID-V:
- Added the `image-to-video` pipeline tag to the metadata for better discoverability.
- Fixed the broken Arxiv link in the README.
- Added a link to the official GitHub repository.
- Standardized the citation to BibTeX format.

README.md

@@ -1,21 +1,24 @@
 ---
 license: apache-2.0
+pipeline_tag: image-to-video
 ---
+
 # DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer
 
 <p align="center">
   <a href="https://guoxu1233.github.io/DreamID-V/">🌐 Project Page</a> |
-  <a href="https://arxiv.org5">📜 Arxiv</a> |
+  <a href="https://arxiv.org/abs/2601.01425">📜 Arxiv</a> |
+  <a href="https://github.com/bytedance/DreamID-V">💻 GitHub</a> |
   <a href="https://huggingface.co/XuGuo699/DreamID-V">🤗 Models</a> |
 </p>
 
 > **DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer**<br>
-> [Xu Guo](https://github.com/Guoxu1233/)<sup> * </sup>, [Fulong Ye](https://scholar.google.com/citations?user=-BbQ5VgAAAAJ&hl=zh-CN/)<sup> * </sup>, [Xinghui Li](https://crayon-shinchan.github.io/xinghui99.github.io/)<sup> *</sup>, [Pengqi Tu](https://openreview.net/profile?id=%7EPengqi_Tu1), [Pengze Zhang](https://pangzecheung.github.io/Homepage/), [Qichao Sun](https://github.com/sun631998316), [Songtao Zhao](https://openreview.net/profile?id=~Songtao_Zhao1)<sup> &dagger;</sup>, [Xiangwang Hou](https://scholar.google.com/citations?user=bpskf9kAAAAJ&hl=zh-CN)<sup> &dagger;</sup> [Qian He](https://scholar.google.com/citations?user=9rWWCgUAAAAJ)
-> <br><sup> * </sup>Equal contribution,<sup> &dagger; </sup>Corresponding author
+> [Xu Guo](https://github.com/Guoxu1233/)<sup> * </sup>, [Fulong Ye](https://scholar.google.com/citations?user=-BbQ5VgAAAAJ&hl=zh-CN/)<sup> * </sup>, [Xinghui Li](https://crayon-shinchan.github.io/xinghui99.github.io/)<sup> *</sup>, [Pengqi Tu](https://openreview.net/profile?id=%7EPengqi_Tu1), [Pengze Zhang](https://pangzecheung.github.io/Homepage/), [Qichao Sun](https://github.com/sun631998316), [Songtao Zhao](https://openreview.net/profile?id=~Songtao_Zhao1)<sup> †</sup>, [Xiangwang Hou](https://scholar.google.com/citations?user=bpskf9kAAAAJ&hl=zh-CN)<sup> †</sup> [Qian He](https://scholar.google.com/citations?user=9rWWCgUAAAAJ)
+> <br><sup> * </sup>Equal contribution,<sup> † </sup>Corresponding author
 > <br>Tsinghua University | Intelligent Creation Team, ByteDance<br>
 
 <p align="center">
-<img src="teaser.png" width=95%>
+<img src="https://huggingface.co/XuGuo699/DreamID-V/resolve/main/teaser.png" width=95%>
 <p>
 
 ## ⚡️ Quickstart
@@ -43,8 +46,8 @@ pip install -r requirements.txt
 ``` sh
 python generate_dreamidv.py \
     --size 832*480 \
-    --ckpt_dir wan2.1-1.3B path \
-    --dreamidv_ckpt dreamidv.pth path  \
+    --ckpt_dir wan2.1-1.3B_path \
+    --dreamidv_ckpt dreamidv.pth_path  \
     --sample_steps 50 \
     --base_seed 42
 ```
@@ -55,8 +58,8 @@ python generate_dreamidv.py \
 pip install "xfuser>=0.4.1"
 torchrun --nproc_per_node=2 generate_dreamidv.py \
     --size 832*480 \
-    --ckpt_dir wan2.1-1.3B path \
-    --dreamidv_ckpt dreamidv.pth path  \
+    --ckpt_dir wan2.1-1.3B_path \
+    --dreamidv_ckpt dreamidv.pth_path  \
     --sample_steps 50 \
     --dit_fsdp \
     --t5_fsdp \
@@ -70,14 +73,14 @@ Our work builds upon and is greatly inspired by several outstanding open-source
 
 
 ## 📧 Contact
-If you have any comments or questions regarding this open-source project, please open a new issue or contact [Xu Guo](https://github.com/Guoxu1233/).
+If you have any comments or questions regarding this open-source project, please open a new issue or contact [Xu Guo](https://github.com/Guoxu1233/) and [Fulong Ye](https://github.com/superhero-7).
 
 
 ## ⭐ Citation
 
-If you find our work helpful, please consider citing our paper and leaving valuable stars
+If you find our work helpful, please consider citing our paper:
 
-```
+```bibtex
 @misc{guo2026dreamidvbridgingimagetovideogaphighfidelity,
       title={DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer}, 
       author={Xu Guo and Fulong Ye and Xinghui Li and Pengqi Tu and Pengze Zhang and Qichao Sun and Songtao Zhao and Xiangwang Hou and Qian He},
@@ -87,4 +90,4 @@ If you find our work helpful, please consider citing our paper and leaving valua
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2601.01425}, 
 }
-```
+```