---
license: mit
pipeline_tag: image-to-image
tags:
- image-super-resolution
- real-world-sr
- diffusion
- one-step-diffusion
- aaai-2026
---

# Realism Control One-step Diffusion for Real-World Image Super-Resolution (RCOD)

Official pretrained model checkpoints for **RCOD** (AAAI 2026).

- **GitHub Repository**: [https://github.com/Zongliang-Wu/RCOD](https://github.com/Zongliang-Wu/RCOD)
- **Project Page**: [https://zongliang-wu.github.io/RCOD-SR/](https://zongliang-wu.github.io/RCOD-SR/)

## Checkpoints Included

| File | Base Architecture | Description |
| :--- | :--- | :--- |
| `rcod_o.pkl` | OSEDiff (SD 2.1) | Unified RCOD-O denoiser with LDG (Fidelity / Neutral / Realism) |
| `rcod_s.pkl` | S3Diff (SD-Turbo) | Unified RCOD-S denoiser with LDG (Fidelity / Neutral / Realism) |
| `rcod_s_mem.pkl` | MLP | Metric Estimation Module (MEM) for adaptive realism selection |

## External Dependencies

For training and external components, please download the respective third-party models from their original authors:
- **DAPE (`DAPE.pth`)**: Domain-Adaptive Prior Extractor from [OSEDiff / DAPE](https://github.com/cswry/OSEDiff).
- **RAM (`ram_swin_large_14m.pth`)**: Recognize Anything Model from [xinyu1205/recognize-anything](https://huggingface.co/xinyu1205/recognize-anything-plus-model).
- **de_net (`de_net.pth`)**: Degradation Estimator from [S3Diff](https://github.com/ArcticHare105/S3Diff) (included in `RCOD_S/assets/mm-realsr/`).

## Quick Download

```bash
# Using huggingface-cli
pip install huggingface_hub
huggingface-cli download MMQDD/RCOD --local-dir weights/
```