Modelpublic

bytedance-research/UNO

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

182likes

Model Card

<h3 align="center"> Less-to-More Generalization: Unlocking More Controllability by In-Context Generation </h3>

Shaojin Wu,</a> Mengqi Huang*,</a> Wenxu Wu,</a> Yufeng Cheng, </a> Fei Ding+,</a> Qian He</a> Intelligent Creation Team, ByteDance

[image]

🔥 News

—[04/2025] 🔥 The training code, inference code, and model of UNO are released. The demo will coming soon.
—[04/2025] 🔥 The project page of UNO is created.
—[04/2025] 🔥 The arXiv paper of UNO is released.

📖 Introduction

In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic in-context generation capabilities of diffusion transformers and generates high-consistency multi-subject paired data. Additionally, we introduce UNO, which consists of progressive cross-modal alignment and universal rotary position embedding. It is a multi-image conditioned subject-to-image model iteratively trained from a text-to-image model. Extensive experiments show that our method can achieve high consistency while ensuring controllability in both single-subject and multi-subject driven generation.

⚡️ Quick Start

🔧 Requirements and Installation

Clone our Github repo

Install the requirements

bash

## create a virtual environment with python >= 3.10 <= 3.12, like
# python -m venv uno_env
# source uno_env/bin/activate
# then install
pip install -r requirements.txt

then download checkpoints in one of the three ways:

1.Directly run the inference scripts, the checkpoints will be downloaded automatically by the hf_hub_download function in the code to your $HF_HOME(the default value is ~/.cache/huggingface).
2.use huggingface-cli download <repo name> to download black-forest-labs/FLUX.1-dev, xlabs-ai/xflux_text_encoders, openai/clip-vit-large-patch14, TODO UNO hf model, then run the inference scripts.
3.use huggingface-cli download <repo name> --local-dir <LOCAL_DIR> to download all the checkpoints menthioned in 2. to the directories your want. Then set the environment variable TODO. Finally, run the inference scripts.

🌟 Gradio Demo

bash

python app.py

✍️ Inference

—Optional prepreration: If you want to test the inference on dreambench at the first time, you should clone the submodule dreambench to download the dataset.

bash

git submodule update --init

bash

python inference.py

🚄 Training

bash

accelerate launch train.py

🎨 Application Scenarios

[image]

📄 Disclaimer

We open-source this project for academic research. The vast majority of images used in this project are either generated or licensed. If you have any concerns, please contact us, and we will promptly remove any inappropriate content. Our code is released under the Apache 2.0 License,, while our models are under the CC BY-NC 4.0 License. Any models related to <a href="https://huggingface.co/black-forest-labs/FLUX.1-dev" target="_blank">FLUX.1-dev</a> base model must adhere to the original licensing terms. This research aims to advance the field of generative AI. Users are free to create images using this tool, provided they comply with local laws and exercise responsible usage. The developers are not liable for any misuse of the tool by users.

🚀 Updates

For the purpose of fostering research and the open-source community, we plan to open-source the entire project, encompassing training, inference, weights, etc. Thank you for your patience and support! 🌟

—[x] Release github repo.
—[x] Release inference code.
—[x] Release training code.
—[x] Release model checkpoints.
—[x] Release arXiv paper.
—[] Release in-context data generation pipelines.

Citation

If UNO is helpful, please help to ⭐ the repo.

If you find this project useful for your research, please consider citing our paper:

bibtex

@article{wu2025less,
  title={Less-to-More Generalization: Unlocking More Controllability by In-Context Generation},
  author={Wu, Shaojin and Huang, Mengqi and Wu, Wenxu and Cheng, Yufeng and Ding, Fei and He, Qian},
  journal={arXiv preprint arXiv:2504.02160},
  year={2025}
}