Improve model card

This PR ensures the model is linked to (and can be found at) MatAnyone: Stable Video Matting with Consistent Memory Propagation](https://huggingface.co/papers/2501.14677).

README.md

@@ -5,6 +5,12 @@ tags:
 - pytorch_model_hub_mixin
 ---
 
+# MatAnyone
+
+This repository contains the model described in [MatAnyone: Stable Video Matting with Consistent Memory Propagation](https://huggingface.co/papers/2501.14677).
+
+Code: https://github.com/pq-yang/MatAnyone
+
 ## Usage
 `pip install huggingface_hub` required.
 
@@ -16,4 +22,6 @@ Users will only need to use these 2 lines to load and instantiate the model.
 ```python
 from matanyone.model.matanyone import MatAnyone
 model = MatAnyone.from_pretrained("PeiqingYang/MatAnyone")
-```
+```
+
+For inference, see the [inference script](https://github.com/pq-yang/MatAnyone/blob/main/inference_matanyone.py).