FLUX.1-dev-CMO

🤗 Hugging Face | 📄 arXiv

🌟 Official LoRA Adapter for Correlation-Weighted Multi-Reward Optimization for Compositional Generation

This repository contains the official LoRA adapter for 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.

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

ConceptMix (Link)

GenEval 2 (Link)

T2I-CompBench (Link)

🛠️ 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:

@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}
}