FlowInOne

<div align="center"> <h2 align="center" style="margin-top: 0; margin-bottom: 15px;"> <span style="color:#0052CC">F</span><span style="color:#135FD0">l</span><span style="color:#266CD4">o</span><span style="color:#3979D7">w</span><span style="color:#4C86DB">I</span><span style="color:#6093DF">n</span><span style="color:#73A0E3">O</span><span style="color:#86ADE7">n</span><span style="color:#99BAEB">e</span>: Unifying Multimodal Generation as <span style="color:#0052CC">I</span><span style="color:#0958CE">m</span><span style="color:#125ED0">a</span><span style="color:#1B64D2">g</span><span style="color:#246AD4">e</span><span style="color:#2D70D6">-</span><span style="color:#3676D8">i</span><span style="color:#3F7CDA">n</span><span style="color:#4882DC">,</span>&nbsp;<span style="color:#5188DE">I</span><span style="color:#5A8EE0">m</span><span style="color:#6394E2">a</span><span style="color:#6C9AE4">g</span><span style="color:#75A0E6">e</span><span style="color:#7EA6E8">-</span><span style="color:#87ACEA">o</span><span style="color:#90B2EC">u</span><span style="color:#99B8EE">t</span> Flow Matching </h2> <p align="center" style="font-size: 15px;"> <span style="color:#E74C3C; font-weight: bold;">TL;DR:</span> <strong>The first vision-centric image-in, image-out image generation model.</strong> </p> <p align="center" style="font-size: 16px;"> <a href="https://csu-jpg.github.io/FlowInOne.github.io/" style="text-decoration: none;">🌐 Homepage</a> | <a href="https://github.com/CSU-JPG/FlowInOne" style="text-decoration: none;">💻 Code</a> | <a href="https://arxiv.org/pdf/2604.06757" style="text-decoration: none;">📄 Paper</a> | <a href="https://huggingface.co/datasets/CSU-JPG/VisPrompt5M" style="text-decoration: none;">📁 Dataset</a> | <a href="https://huggingface.co/datasets/CSU-JPG/VPBench" style="text-decoration: none;">🌏 Benchmark</a> | <a href="https://huggingface.co/CSU-JPG/FlowInOne" style="text-decoration: none;">🤗 Model</a> </p> </div>

About

We present FlowInOne, a framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean image-in, image-out pipeline governed by a single flow matching model. This vision-centric formulation naturally eliminates cross-modal alignment bottlenecks, noise scheduling, and task-specific architectural branches, unifying text-to-image generation, layout-guided editing, and visual instruction following under one coherent paradigm. Extensive experiments demonstrate that FlowInOne achieves state-of-the-art performance across all unified generation tasks, surpassing both open-source models and competitive commercial systems, establishing a new foundation for fully vision-centric generative modeling where perception and creation coexist within a single continuous visual space.

🧪 Usage

you can download the model weights and model preparation

# model weights
wget -O /path/to/download https://huggingface.co/CSU-JPG/FlowInOne/resolve/main/flowinone_256px.pth
# model preparation
wget -O /path/to/download https://huggingface.co/CSU-JPG/FlowInOne/resolve/main/preparation.tar.gz
# unzip
tar -xzvf "preparation.tar.gz" -C "/path/to/preparation"

you can download the dataset examples

wget -O /path/to/download https://huggingface.co/CSU-JPG/FlowInOne/resolve/main/flowinone_demo_dataset.tar.gz
# unzip
tar -xzvf "flowinone_demo_dataset.tar.gz" -C "/path/to/flowinone_demo_dataset"

Our training and inference scripts are now available on GitHub!

Citation

If you found our work useful, please consider citing:

@article{yi2026flowinoneunifyingmultimodalgenerationimagein,
      title={FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching}, 
      author={Junchao Yi and Rui Zhao and Jiahao Tang and Weixian Lei and Linjie Li and Qisheng Su and Zhengyuan Yang and Lijuan Wang and Xiaofeng Zhu and Alex Jinpeng Wang},    
      journal={arXiv preprint arXiv:2604.06757},
      year={2026}
}