Improve model card: add metadata, links and sample usage

Hi! I'm Niels from the Hugging Face community science team. I've opened this PR to improve the model card for RSEdit-DiT. The updates include:
- Adding YAML metadata for `library_name` and `pipeline_tag`.
- Adding tags for `remote-sensing` and `image-editing` to help with discoverability.
- Including links to the research paper, code repository, and project page.
- Refining the sample usage snippet based on the official README.

These changes will help users better understand the model and how to use it with the `diffusers` library.

README.md

@@ -1,26 +1,42 @@
-# RSEdit-DiT - Inference Guide
+---
+library_name: diffusers
+pipeline_tag: image-to-image
+tags:
+- remote-sensing
+- image-editing
+- diffusion
+---
 
-Quick guide for running inference with RSEdit DiT model for remote sensing image editing.
+# RSEdit-DiT
 
-## Quick Start
+RSEdit is a unified framework for instruction-based remote sensing image editing. This repository contains the DiT-based variant (based on PixArt-α) presented in the paper [RSEdit: Text-Guided Image Editing for Remote Sensing](https://huggingface.co/papers/2603.13708).
 
-### Python Code Example
+[**Project Page**](https://bili-sakura.github.io/RSEdit-Preview/) | [**Code**](https://github.com/Bili-Sakura/RSEdit-Preview) | [**Paper**](https://huggingface.co/papers/2603.13708)
+
+## Model Description
+General-domain text-guided image editors often introduce artifacts or break the orthographic constraints of remote sensing (RS) imagery. RSEdit addresses these challenges by adapting pretrained diffusion models into instruction-following editors via channel concatenation and in-context token concatenation. 
+
+The DiT-based variant leverages a transformer-based backbone to learn precise, physically coherent edits (e.g., flooding, urban growth, seasonal shifts) while preserving the geospatial content of the original image.
+
+## Quick Start (Inference)
+
+To run inference with the RSEdit-DiT model, use the `DiffusionPipeline` with the custom pipeline provided in the repository.
 
 ```python
 import torch
 from PIL import Image
 from diffusers import DiffusionPipeline
+from diffusers.models.attention_processor import AttnProcessor
 
 # Load model with custom pipeline
-model_path = "/data/models/ours/BiliSakura/RSEdit-DiT"
+model_id = "BiliSakura/RSEdit-DiT"
 pipe = DiffusionPipeline.from_pretrained(
-    model_path,
+    model_id,
     torch_dtype=torch.bfloat16,
     custom_pipeline="pipeline_rsedit_dit"
 ).to("cuda")
 
 # Switch to AttnProcessor (required for RSEdit DiT)
-from diffusers.models.attention_processor import AttnProcessor
 pipe.transformer.set_attn_processor(AttnProcessor())
 
 # Load source image
@@ -41,3 +57,17 @@ edited_image = pipe(
 # Save result
 edited_image.save("edited_image.png")
 ```
+
+## Citation
+
+```bibtex
+@misc{zhenyuan2026rsedittextguidedimageediting,
+      title={RSEdit: Text-Guided Image Editing for Remote Sensing}, 
+      author={Chen Zhenyuan and Zhang Zechuan and Zhang Feng},
+      year={2026},
+      eprint={2603.13708},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2603.13708}, 
+}
+```