| | --- |
| | library_name: matanyone |
| | tags: |
| | - model_hub_mixin |
| | - 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. |
| |
|
| | ```shell |
| | pip install -q git+https://github.com/pq-yang/MatAnyone |
| | ``` |
| |
|
| | 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). |
