🌌 Skywork-UniPic-1.5B

👁 GitHub Repo
👁 GitHub Stars
👁 GitHub Forks

📖 Introduction

Skywork-UniPic is a unified autoregressive multimodal model with 1.5 billion parameters, capable of handling three key vision-language tasks within a single architecture:

🖼️ Image Understanding
🎨 Text-to-Image Generation
✏️ Image Editing

Trained from scratch on a large-scale multimodal corpus, UniPic is designed to support a wide range of unified image-text tasks efficiently.

👁 Model Teaser

📊 Benchmarks

Skywork-UniPic achieves competitive results across a variety of vision-language tasks:

Task	Score
🧠 GenEval	0.86
🖼️ DPG-Bench	85.5
✂️ GEditBench-EN	5.83
🧪 ImgEdit-Bench	3.49

👁 Benchmark Results

🧠 Usage

1. Clone the Repository

git clone https://github.com/SkyworkAI/UniPic
cd UniPic-1

2. Set Up the Environment

conda create -n unipic python=3.10.14
conda activate unipic
pip install -r requirements.txt

3.Text-to-Image Generation

export PYTHONPATH=./:$PYTHONPATH

python scripts/text2image.py configs/models/qwen2_5_1_5b_kl16_mar_h.py \
 --checkpoint checkpoint/pytorch_model.bin \
 --image_size 1024 \
 --prompt "A glossy-coated golden retriever stands on the park lawn beside a life-sized penguin statue." \
 --output output.jpg

4. Image Editing

The image editing feature within this unified model is an exploratory module at the forefront of research. And it is not yet production-ready.

export PYTHONPATH=./:$PYTHONPATH

python scripts/image_edit.py configs/models/qwen2_5_1_5b_kl16_mar_h.py \
 --checkpoint checkpoint/pytorch_model.bin \
 --image_size 1024 \
 --image data/sample.png \
 --prompt "Replace the stars with the candle." \
 --output output.jpg

📄 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}, 
}