Update README.md

README.md

@@ -2,7 +2,6 @@
 license: apache-2.0
 library_name: seedvr
 ---
-
 <div align="center">
   <img src="assets/seedvr_logo.png" alt="SeedVR" width="400"/>
 </div>
@@ -24,6 +23,18 @@ library_name: seedvr
       alt="SeedVR2 Paper on ArXiv"
     />
   </a>
+  <a href="https://github.com/ByteDance-Seed/SeedVR">
+            <img 
+              alt="Github" src="https://img.shields.io/badge/SeedVR2-Codebase-536af5?color=536af5&logo=github"
+              alt="SeedVR2 Codebase"
+            />
+  </a>
+  <a href="https://huggingface.co/models?other=seedvr">
+    <img 
+        src="https://img.shields.io/badge/SeedVR2-Models-yellow?logo=huggingface&logoColor=yellow" 
+        alt="SeedVR2 Models"
+    />
+  </a>
   <a href="https://www.youtube.com/watch?v=tM8J-WhuAH0" target='_blank'>
     <img 
         src="https://img.shields.io/badge/Demo%20Video-%23FF0000.svg?logo=YouTube&logoColor=white"
@@ -31,9 +42,8 @@ library_name: seedvr
     />
   </a>
 </p>
-
 >
-> Recent advances in diffusion-based video restoration (VR) demonstrate significant improvement in visual quality, yet yield a prohibitive computational cost during inference. While several distillation-based approaches have exhibited the potential of one-step image restoration, extending existing approaches to VR remains challenging and underexplored, due to the limited generation ability and poor temporal consistency, particularly when dealing with high-resolution video in real-world settings. In this work, we propose a one-step diffusion-based VR model, termed as AnonymousVR, which performs adversarial VR training against real data. To handle the challenging high-resolution VR within a single step, we introduce several enhancements to both model architecture and training procedures. Specifically, an adaptive window attention mechanism is proposed, where the window size is dynamically adjusted to fit the output resolutions, avoiding window inconsistency observed under high-resolution VR using window attention with a predefined window size. To stabilize and improve the adversarial post-training towards VR, we further verify the effectiveness of a series of losses, including a proposed feature matching loss without significantly sacrificing training efficiency. Extensive experiments show that AnonymousVR can achieve comparable or even better performance compared with existing VR approaches in a single step.
+> Recent advances in diffusion-based video restoration (VR) demonstrate significant improvement in visual quality, yet yield a prohibitive computational cost during inference. While several distillation-based approaches have exhibited the potential of one-step image restoration, extending existing approaches to VR remains challenging and underexplored, due to the limited generation ability and poor temporal consistency, particularly when dealing with high-resolution video in real-world settings. In this work, we propose a one-step diffusion-based VR model, termed as SeedVR2, which performs adversarial VR training against real data. To handle the challenging high-resolution VR within a single step, we introduce several enhancements to both model architecture and training procedures. Specifically, an adaptive window attention mechanism is proposed, where the window size is dynamically adjusted to fit the output resolutions, avoiding window inconsistency observed under high-resolution VR using window attention with a predefined window size. To stabilize and improve the adversarial post-training towards VR, we further verify the effectiveness of a series of losses, including a proposed feature matching loss without significantly sacrificing training efficiency. Extensive experiments show that SeedVR2 can achieve comparable or even better performance compared with existing VR approaches in a single step.
 
 <p align="center"><img src="assets/teaser.png" width="100%"></p>
 
@@ -51,7 +61,6 @@ library_name: seedvr
       booktitle={arXiv preprint arXiv:2506.05301},
       year={2025}
    }
-
 @inproceedings{wang2025seedvr,
       title={SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration},
       author={Wang, Jianyi and Lin, Zhijie and Wei, Meng and Zhao, Yang and Yang, Ceyuan and Loy, Chen Change and Jiang, Lu},