Downloads · 30 days
15
100% of all-time downloads
Harmon-0.5B-RecA
sanaka87/Harmon-0.5B-RecA
Harmon-0.5B-RecA is a text-to-image model from sanaka87. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
A self-supervised training framework that aligns understanding and generation in modest compute, with huge zero-shot gain on generation and editing capability.
All-time downloads
15
Public
Repo size
1.4 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.pth1.4 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Access
- Public
- Created
- Aug 26, 2025
- Updated
- Nov 13, 2025
- SHA
- b3020bdd
Base models
Datasets
Model card
From the Hugging Face model README
Harmon-0.5B-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-0.5B-RecA. For installation, usage instructions, and further documentation, please visit Harmon's original GitHub repository.
🧠 Method
-fcd022?style=for-the-badge&logo=huggingface&logoColor=000){kind=icon}
📊 Benchmarks
| Model | GenEval ↑ | DPGBench ↑ | WISE ↑ |
|---|---|---|---|
| Harmon-0.5B | 0.68 | 80.12 | 0.33 |
| Harmon-0.5B-RecA | 0.79 | 84.67 | 0.40 |
License
Harmon-0.5B-RecA is licensed under the Apache 2.0 license.
✍️ 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}
}
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Languages
- en, zh
- Created
- Aug 26, 2025
- Updated
- Nov 13, 2025