Create model card for RFMSR

This PR creates a comprehensive model card for RFMSR (Residual Flow Matching for Image Super-Resolution). It includes:
- The `image-to-image` pipeline tag in the YAML metadata.
- Links to the paper and the official GitHub repository.
- Setup and quickstart instructions for installation, downloading weights, and running inference.
- The BibTeX citation for the paper.

README.md

@@ -0,0 +1,69 @@
+---
+pipeline_tag: image-to-image
+---
+
+# RFMSR: Residual Flow Matching for Image Super-Resolution
+
+This repository contains the weights for **RFMSR** (Residual Flow Matching for Image Super-Resolution), a vision-only super-resolution framework that utilizes a residual flow design centering the source distribution at the low-quality (LQ) latent to preserve structural priors.
+
+[📚 Paper](https://huggingface.co/papers/2607.12753) | [💻 GitHub Repository](https://github.com/Faze-Hsw/RFMSR)
+
+## Method Overview
+
+RFMSR centers the source distribution at the LR latent, reducing the transport distance and preserving structural priors throughout the flow trajectory. It uses a two-phase training strategy to achieve high-quality single-step generation without sacrificing multi-step refinement.
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/Faze-Hsw/RFMSR/main/assets/overview.png" alt="RFMSR overview" width="100%">
+</p>
+
+## Pretrained Weights
+
+This repository hosts the following model checkpoints:
+- `rfmsr.safetensors` — Phase I: Multi-step Flow Matching model (15-step recommended)
+- `rfmsr_os.safetensors` — Phase II: One-step model
+- `rfmsr_consistency.safetensors` — Consistency distillation: One-step model
+
+## Quick Start (Inference)
+
+To run inference, please clone the official GitHub repository and install the dependencies:
+
+```bash
+git clone https://github.com/Faze-Hsw/RFMSR.git
+cd RFMSR
+conda create -n rfmsr python=3.12 -y
+conda activate rfmsr
+pip install -r requirements.txt
+```
+
+Download the checkpoints via `huggingface-cli`:
+
+```bash
+pip install huggingface_hub
+huggingface-cli download frozen2001/RFMSR ckpts/ --local-dir . --local-dir-use-symlinks False
+```
+
+Run super-resolution inference on your images:
+
+```bash
+# One-step inference (fast, recommended)
+python infer_rfmsr.py --input input.png --steps 1
+
+# Multi-step inference (higher quality)
+python infer_rfmsr.py --input input.png --steps 15
+```
+
+## Citation
+
+If you find this work useful, please cite:
+
+```bibtex
+@misc{huang2026rfmsrresidualflowmatching,
+      title={RFMSR: Residual Flow Matching for Image Super-Resolution},
+      author={Shuwei Huang and Tianyao Luo and Jicheng Liu and Daizong Liu and Pan Zhou},
+      year={2026},
+      eprint={2607.12753},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2607.12753},
+}
+```