Skywork / Unipic3-DMD

🌌 Unipic3-DMD-Model(Distribution Matching Distillation)

📖 Introduction

UniPic3-DMD-Model is a few-step image editing and multi-image composition model trained using Distribution Matching Distillation (DMD) . The model directly matches the output distribution of a high-quality teacher model , enabling sharp, visually detailed generations in very few inference steps.
It is designed to maximize perceptual quality and realism , closely imitating strong proprietary or large teacher models. This model is initialized from a consistency-trained checkpoint and further refined via distribution-level distillation.

📊 Benchmarks

🧠 Usage

1. Clone the Repository

git clone https://github.com/SkyworkAI/UniPic
cd UniPic-3

2. Set Up the Environment

conda create -n unipic python=3.10
conda activate unipic3
pip install -r requirements.txt

3.Batch Inference

transformer_path = "Skywork/Unipic3-DMD/ema_transformer"

python -m torch.distributed.launch --nproc_per_node=1 --master_port 29501 --use_env \
    qwen_image_edit_fast/batch_inference.py \
    --jsonl_path data/val.jsonl \
    --output_dir work_dirs/output \
    --distributed \
    --num_inference_steps 4 \
    --true_cfg_scale 4.0 \
    --transformer transformer_path \
    --skip_existing

📄 License

This model is released under the MIT License.

Citation

If you use Skywork-UniPic in your research, please cite:

@misc{wang2025skyworkunipicunifiedautoregressive,
      title={Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation}, 
      author={Peiyu Wang and Yi Peng and Yimeng Gan and Liang Hu and Tianyidan Xie and Xiaokun Wang and Yichen Wei and Chuanxin Tang and Bo Zhu and Changshi Li and Hongyang Wei and Eric Li and Xuchen Song and Yang Liu and Yahui Zhou},
      year={2025},
      eprint={2508.03320},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2508.03320}, 
}

@misc{wei2025skyworkunipic20building,
      title={Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model}, 
      author={Hongyang Wei and Baixin Xu and Hongbo Liu and Cyrus Wu and Jie Liu and Yi Peng and Peiyu Wang and Zexiang Liu and Jingwen He and Yidan Xietian and Chuanxin Tang and Zidong Wang and Yichen Wei and Liang Hu and Boyi Jiang and William Li and Ying He and Yang Liu and Xuchen Song and Eric Li and Yahui Zhou},
      year={2025},
      eprint={2509.04548},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2509.04548}, 
}