README.md

---
language: en
license: apache-2.0
library_name: diffusers
base_model: black-forest-labs/FLUX.1-dev
tags:
- flux
- diffusers
- lora
- cmo
- text-to-image
pipeline_tag: text-to-image
---

# FLUX.1-dev-CMO

<p align="center">
  🤗 <a href="[https://huggingface.co/](https://huggingface.co/)Bruece/FLUX.1-dev-CMO"><b>Hugging Face</b></a> | 
  📄 <a href="[https://arxiv.org/abs/2603.18528](https://arxiv.org/abs/2603.18528)"><b>arXiv</b></a> 
</p>

**🌟 Official LoRA Adapter for [Correlation-Weighted Multi-Reward Optimization for Compositional Generation](https://arxiv.org/abs/2603.18528)**

This repository contains the official LoRA adapter for [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) fine-tuned using **CMO (Correlation-Weighted Multi-Reward Optimization)** to enhance compositional generation capabilities.

## 🚀 Usage

Below is the code to load and merge the LoRA adapter with the base FLUX.1-dev model.

```python
import torch
from diffusers import FluxPipeline
from peft import PeftModel

model_id = "black-forest-labs/FLUX.1-dev"
lora_ckpt_path = "Bruece/FLUX.1-dev-CMO"
device = "cuda"

pipe = FluxPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
pipe.transformer = PeftModel.from_pretrained(pipe.transformer, lora_ckpt_path)
pipe.transformer = pipe.transformer.merge_and_unload()
pipe = pipe.to(device)

prompt = 'a photo of a black kite and a green bear'
image = pipe(prompt, height=512, width=512, num_inference_steps=40, guidance_scale=4.5).images[0]  
image.save("flux_cmo_lora.png")
```

## 🖼️ Qualitative Results

<details>
<summary>ConceptMix (<a href="[https://arxiv.org/abs/2408.14339](https://arxiv.org/abs/2408.14339)">Link</a>)</summary>
<br>
<img src="./conceptmix_results.png" alt="ConceptMix Results">
</details>

<details>
<summary>GenEval 2 (<a href="[https://arxiv.org/abs/2512.16853](https://arxiv.org/abs/2512.16853)">Link</a>)</summary>
<br>
<img src="./GenEval2_results.png" alt="GenEval 2 Results">
</details>

<details>
<summary>T2I-CompBench (<a href="[https://arxiv.org/pdf/2307.06350v2](https://arxiv.org/pdf/2307.06350v2)">Link</a>)</summary>
<br>
<img src="./T2I-CompBench_results.png" alt="T2I-CompBench Results">
</details>

## 🛠️ Training Details
- **Base Model:** FLUX.1-dev
- **Algorithm:** Correlation-Weighted Multi-Reward Optimization (CMO)
- **Precision:** bfloat16

## 📜 Citation

If you find this model useful for your research, please cite:

```bibtex
@article{wi2026correlation,
  title={Correlation-Weighted Multi-Reward Optimization for Compositional Generation},
  author={Wi, Jungmyung and Kim, Hyunsoo and Kim, Donghyun},
  journal={arXiv preprint arXiv:2603.18528},
  year={2026}
}
```