X-GenGroup/PaCo-Qwen-Image-Edit-Lora

PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling

       

The model presented in PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling.

🌟 Overview

PaCo-RL is a comprehensive framework for consistent image generation through reinforcement learning, addressing challenges in preserving identities, styles, and logical coherence across multiple images for storytelling and character design applications.

Key Components

• PaCo-Reward: A pairwise consistency evaluator with task-aware instruction and CoT reasoning.
• PaCo-GRPO: Efficient RL optimization with resolution-decoupled training and log-tamed multi-reward aggregation

Example Usage

import os
from PIL import Image
import torch
from diffusers import QwenImageEditPipeline
from peft import PeftModel
from diffusers.utils import load_image

pipeline = QwenImageEditPipeline.from_pretrained(
    "Qwen/Qwen-Image-Edit",
    torch_dtype=torch.bfloat16,
    device_map="balanced"
)

pipeline.transformer = PeftModel.from_pretrained(
    pipeline.transformer,
    'X-GenGroup/PaCo-Qwen-Image-Edit-Lora'
)

pipeline.set_progress_bar_config(disable=None)

input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")

prompt = "Add a blue hat to the cat."
inputs = {
    "image": input_image,
    "prompt": prompt,
    "generator": torch.manual_seed(0),
    "true_cfg_scale": 4.0,
    "negative_prompt": " ",
    "num_inference_steps": 50,
}

with torch.inference_mode():
    output = pipeline(**inputs)
    output_image = output.images[0]

🎁 Model Zoo

Model	Type	HuggingFace
PaCo-Reward-7B	Reward Model	🤗 Link
PaCo-Reward-7B-Lora	Reward Model (LoRA)	🤗 Link
PaCo-FLUX.1-dev	T2I Model (LoRA)	🤗 Link
PaCo-FLUX.1-Kontext-dev	Image Editing Model (LoRA)	🤗 Link
PaCo-QwenImage-Edit	Image Editing Model (LoRA)	🤗 Link

⭐ Citation

@misc{ping2025pacorladvancingreinforcementlearning,
      title={PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling}, 
      author={Bowen Ping and Chengyou Jia and Minnan Luo and Changliang Xia and Xin Shen and Zhuohang Dang and Hangwei Qian},
      year={2025},
      eprint={2512.04784},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.04784}, 
}

_{⭐ Star us on GitHub if you find PaCo-RL helpful!}