Improve model card: Add pipeline tag, library name, and enrich content with abstract, usage, and results

This PR enhances the model card for the ROSE model by:
- Adding `pipeline_tag: video-to-video` to improve discoverability on the Hub.
- Adding `library_name: diffusers`, as the model is built on Diffusion Transformers and uses `diffusers` components, enabling automated usage snippets.
- Updating the paper link to the official Hugging Face paper page: https://huggingface.co/papers/2508.18633.
- Including the paper's abstract to provide a comprehensive overview of the model's capabilities and methodology.
- Adding explicit links to the project page, GitHub repository, and Hugging Face Space for easy access.
- Incorporating detailed "Dependencies and Installation" and "Usage (Quick Test)" sections with code snippets directly from the official GitHub README.
- Adding a "Results" section with visual examples and an "Overview" diagram from the GitHub README (with updated image links to raw GitHub URLs).
- Including the "Citation" and "Acknowledgement" sections for proper attribution.

These changes significantly improve the model card's completeness and user-friendliness.

README.md

@@ -1,6 +1,245 @@
 ---
-license: apache-2.0
 base_model:
 - alibaba-pai/Wan2.1-Fun-1.3B-InP
+license: apache-2.0
+pipeline_tag: video-to-video
+library_name: diffusers
 ---
-This repository contains the finetuned WanTransformer3D weights for [ROSE](https://rose2025-inpaint.github.io/). For instructions about how to use our model, please refer to our [Github repository](https://github.com/Kunbyte-AI/ROSE) and [HuggingFace Space](https://huggingface.co/spaces/Kunbyte/ROSE).
+
+# ROSE: Remove Objects with Side Effects in Videos
+
+This repository contains the finetuned WanTransformer3D weights for **ROSE**, a model for removing objects with side effects in videos.
+
+[\ud83d\udcda Paper](https://huggingface.co/papers/2508.18633) - [\ud83c\udf10 Project Page](https://rose2025-inpaint.github.io/) - [\ud83d\udcbb Code](https://github.com/Kunbyte-AI/ROSE) - [\ud83e\udd17 Demo](https://huggingface.co/spaces/Kunbyte/ROSE)
+
+## Abstract
+Video object removal has achieved advanced performance due to the recent success of video generative models. However, when addressing the side effects of objects, e.g., their shadows and reflections, existing works struggle to eliminate these effects for the scarcity of paired video data as supervision. This paper presents ROSE, termed Remove Objects with Side Effects, a framework that systematically studies the object's effects on environment, which can be categorized into five common cases: shadows, reflections, light, translucency and mirror. Given the challenges of curating paired videos exhibiting the aforementioned effects, we leverage a 3D rendering engine for synthetic data generation. We carefully construct a fully-automatic pipeline for data preparation, which simulates a large-scale paired dataset with diverse scenes, objects, shooting angles, and camera trajectories. ROSE is implemented as an video inpainting model built on diffusion transformer. To localize all object-correlated areas, the entire video is fed into the model for reference-based erasing. Moreover, additional supervision is introduced to explicitly predict the areas affected by side effects, which can be revealed through the differential mask between the paired videos. To fully investigate the model performance on various side effect removal, we presents a new benchmark, dubbed ROSE-Bench, incorporating both common scenarios and the five special side effects for comprehensive evaluation. Experimental results demonstrate that ROSE achieves superior performance compared to existing video object erasing models and generalizes well to real-world video scenarios.
+
+## Dependencies and Installation
+
+1.  **Clone Repo**
+    ```bash
+    git clone https://github.com/Kunbyte-AI/ROSE.git
+    ```
+
+2.  **Create Conda Environment and Install Dependencies**
+    ```bash
+    # create new anaconda env
+    conda create -n rose python=3.12 -y
+    conda activate rose
+
+    # install python dependencies
+    pip3 install -r requirements.txt
+    ```
+    -   CUDA = 12.4
+    -   PyTorch = 2.6.0
+    -   Torchvision = 0.21.0
+    -   Other required packages in `requirements.txt`
+
+## Usage (Quick Test)
+
+To get started, you need to prepare the pretrained models first.
+
+1.  **Prepare pretrained models**
+    We use pretrained [`Wan2.1-Fun-1.3B-InP`](https://huggingface.co/alibaba-pai/Wan2.1-Fun-1.3B-InP) as our base model. During training, we only train the WanTransformer3D part and keep other parts frozen. You can download the weight of Transformer3D of ROSE from this [`link`](https://huggingface.co/Kunbyte/ROSE).
+
+    For local inference, the `weights` directory should be arranged like this:
+    ```
+    weights
+     ├── transformer
+       ├── config.json
+       ├── diffusion_pytorch_model.safetensors
+    ```
+
+    Also, it's necessary to prepare the base model in the models directory. You can download the Wan2.1-Fun-1.3B-InP base model from this [`link`](https://huggingface.co/alibaba-pai/Wan2.1-Fun-1.3B-InP).
+
+    The `models` directory will be arranged like this:
+    ```
+    models
+     ├── Wan2.1-Fun-1.3B-InP
+       ├── google
+         ├── umt5-xxl
+           ├── spiece.model
+           ├── special_tokens_map.json
+               ...
+       ├── xlm-roberta-large
+         ├── sentencepiece.bpe.model
+         ├── tokenizer_config.json
+             ...
+     ├── config.json
+     ├── configuration.json
+     ├── diffusion_pytorch_model.safetensors
+     ├── models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth
+     ├── models_t5_umt5-xxl-enc-bf16.pth
+     ├── Wan2.1_VAE.pth
+    ```
+
+2.  **Run Inference**
+    We provide some examples in the [`data/eval`](https://github.com/Kunbyte-AI/ROSE/tree/main/data/eval) folder. Run the following command to try it out:
+    ```shell
+    python inference.py \
+      --validation_videos "path/to/your/video.mp4" \
+      --validation_masks "path/to/your/mask.mp4" \
+      --validation_prompts "" \
+      --output_dir "./output" \
+      --video_length 16 \
+      --sample_size 480 720
+    ```
+    For more options, refer to the usage information in the GitHub repository:
+    ```
+    Usage:
+
+    python inference.py [options]
+
+    Options:
+      --validation_videos  Path(s) to input videos
+      --validation_masks   Path(s) to mask videos
+      --validation_prompts Text prompts (default: [""])
+      --output_dir         Output directory
+      --video_length       Number of frames per video (It needs to be 16n+1.)
+      --sample_size        Frame size: height width (default: 480 720)
+
+    ```
+    An interactive demo is also available on [Hugging Face Spaces](https://huggingface.co/spaces/Kunbyte/ROSE).
+
+## Results
+
+### Shadow
+<table>
+  <thead>
+    <tr>
+      <th>Masked Input</th>
+      <th>Output</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Shadow/example-2/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Shadow/example-2/output.gif" width="100%"> </td>
+    </tr>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Shadow/example-7/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Shadow/example-7/output.gif" width="100%"></td>
+    </tr>
+  </tbody>
+</table>
+
+### Reflection
+<table>
+  <thead>
+    <tr>
+      <th>Masked Input</th>
+      <th>Output</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Reflection/example-1/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Reflection/example-1/output.gif" width="100%"></td>
+    </tr>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Reflection/example-2/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Reflection/example-2/output.gif" width="100%"></td>
+    </tr>
+  </tbody>
+</table>
+
+### Common
+<table>
+  <thead>
+    <tr>
+      <th>Masked Input</th>
+      <th>Output</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Common/example-3/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Common/example-3/output.gif" width="100%"></td>
+    </tr>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Common/example-15/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Common/example-15/output.gif" width="100%"></td>
+    </tr>
+  </tbody>
+</table>
+
+### Light Source
+<table>
+  <thead>
+    <tr>
+      <th>Masked Input</th>
+      <th>Output</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Light_source/example-4/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Light_source/example-4/output.gif" width="100%"></td>
+    </tr>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Light_source/example-10/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Light_source/example-10/output.gif" width="100%"></td>
+    </tr>
+  </tbody>
+</table>
+
+### Translucent
+<table>
+  <thead>
+    <tr>
+      <th>Masked Input</th>
+      <th>Output</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Translucent/example-4/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Translucent/example-4/output.gif" width="100%"></td>
+    </tr>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Translucent/example-5/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Translucent/example-5/output.gif" width="100%"></td>
+    </tr>
+  </tbody>
+</table>
+
+### Mirror
+<table>
+  <thead>
+    <tr>
+      <th>Masked Input</th>
+      <th>Output</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Mirror/example-1/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Mirror/example-1/output.gif" width="100%"></td>
+    </tr>
+    <tr>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Mirror/example-2/masked.gif" width="100%"></td>
+      <td><img src="https://github.com/Kunbyte-AI/ROSE/raw/main/assets/Mirror/example-2/output.gif" width="100%"></td>
+    </tr>
+  </tbody>
+</table>
+
+## Overview
+![overall_structure](https://github.com/Kunbyte-AI/ROSE/raw/main/assets/rose_pipeline.png)
+
+## Citation
+
+If you find our repo useful for your research, please consider citing our paper:
+
+```bibtex
+@article{miao2025rose,
+   title={ROSE: Remove Objects with Side Effects in Videos}, 
+   author={Miao, Chenxuan and Feng, Yutong and Zeng, Jianshu and Gao, Zixiang and Liu, Hantang and Yan, Yunfeng and Qi, Donglian and Chen, Xi and Wang, Bin and Zhao, Hengshuang},
+   journal={arXiv preprint arXiv:2508.18633},
+   year={2025}
+}
+```
+
+## Acknowledgement
+
+This code is based on [Wan2.1-Fun-1.3B-Inpaint](https://github.com/aigc-apps/VideoX-Fun) and some code are brought from [ProPainter](https://github.com/sczhou/ProPainter). Thanks for their awesome works!