---
title: Harmon-1.5B-RecA
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Harmon-1.5B-RecA"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Harmon-1.5B-RecA.md"
repository: AI-ModelScope/Harmon-1.5B-RecA
last_updated: 2025-11-13
license: apache-2.0
pipeline_tag: any-to-any
tasks:
  - any-to-any
base_model:
  - wusize/Harmon-1_5B
base_model_relation: finetune
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 100
stars: 0
---

# Harmon-1.5B-RecA

> Harmon-1.5B-RecA - AI-ModelScope 在 ModelScope 开源的模型。A self-supervised training framework that aligns understanding and generation in modest compute, with huge zero-shot gain on generation and editing capability.

AI-ModelScope/Harmon-1.5B-RecA 是 ModelScope 魔搭社区上的any-to-any模型，采用 apache-2.0 许可，基于 wusize/Harmon-1_5B 构建。

- **Repository**: AI-ModelScope/Harmon-1.5B-RecA
- **License**: apache-2.0
- **Tasks**: any-to-any
- **Base model**: wusize/Harmon-1_5B
- **Downloads**: 100
- **Stars**: 0
- **Last updated**: 2025-11-13

Source: https://www.modelscope.cn/models/AI-ModelScope/Harmon-1.5B-RecA

---

# Harmon-1.5B-RecA

> A self-supervised training framework that aligns understanding and generation in modest compute, with huge **zero-shot** gain on generation and editing capability.

This repository hosts the model weights for **Harmon-1.5B-RecA**, a model from the paper [Reconstruction Alignment Improves Unified Multimodal Models](https://huggingface.co/papers/2509.07295). For installation, usage instructions, and further documentation, please visit Harmon's original [GitHub repository](https://github.com/wusize/Harmon).

## 🧠 Method

  [![Paper](https://img.shields.io/badge/paper-A42C25?style=for-the-badge&logo=arxiv&logoColor=white)](https://huggingface.co/papers/2509.07295)
  [![ArXiv](https://img.shields.io/badge/arXiv-A42C25?style=for-the-badge&logo=arxiv&logoColor=white&color=blue)](https://arxiv.org/abs/2509.07295)
  [![Github](https://img.shields.io/badge/RecA-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white)](https://github.com/HorizonWind2004/reconstruction-alignment)
  [![Hugging Face Collection](https://img.shields.io/badge/HF_Models-fcd022?style=for-the-badge&logo=huggingface&logoColor=000)](https://huggingface.co/collections/sanaka87/realign-68ad2176380355a3dcedc068)
  [![HF Demo](https://img.shields.io/badge/Demo_(BAGEL)-fcd022?style=for-the-badge&logo=huggingface&logoColor=000)](https://huggingface.co/spaces/sanaka87/BAGEL-ReAlign)
  [![Project Page](https://img.shields.io/badge/Project_Page-00CED1?style=for-the-badge&logo=web&logoColor=white)](https://reconstruction-alignment.github.io/)


## 📊 Benchmarks

| Model        | GenEval ↑ | DPGBench ↑ | WISE ↑ |
| ------------ | --------- | --------- | --------- |
| **Harmon-1.5B**    | 0.73  | 80.93  | 0.41 |
| **Harmon-1.5B-RecA**    | **0.86**  | **87.21** | **0.50** |

## ✍️ Citation

If you find our work inspiring or use our codebase in your research, please consider giving a star ⭐ and a citation~


```
@article{xie2025reconstruction,
  title={Reconstruction Alignment Improves Unified Multimodal Models},
  author={Xie, Ji and Darrell, Trevor and Zettlemoyer, Luke and Wang, XuDong},
  journal={arXiv preprint arXiv:2509.07295},
  year={2025}
}
```