README.md

---
base_model: black-forest-labs/FLUX.1-Kontext-dev
base_model_relation: adapter
library_name: diffusers
license: apache-2.0
tags:
- lora
- flux
- flux-kontext
- image-to-image
- makeup-transfer
- makeup-removal
- safetensors
---

<div align='center'>
<h1 align="center">[ECCV 2026] Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer</h1>
    Bo Wei<sup> 1*</sup>&emsp;
    <a href='https://scholar.google.com/citations?user=wLTXeNwAAAAJ&hl=en&oi=ao' target='_blank'>Xianhui Lin</a><sup> 2†</sup>&emsp;
    Yi Dong<sup> 2</sup>&emsp;
    Zhongzhong Li<sup> 2</sup>&emsp;
    Zonghui Li<sup> 2</sup>&emsp;
    <a href='https://scholar.google.com/citations?hl=en&user=BhmLztgAAAAJ' target='_blank'>Zirui Wang</a><sup> 2</sup>&emsp;
</div>

<div align='center'>
    <a href='https://scholar.google.com/citations?hl=en&user=12MzNVkAAAAJ' target='_blank'>Jiachen Yang</a><sup> 2</sup>&emsp;
    Xing Liu<sup> 2</sup>&emsp;
    Hong Gu<sup> 2</sup>&emsp;
    <a href='https://scholar.google.com/citations?hl=en&user=tmT_voUAAAAJ' target='_blank'>Xiaoming Li</a><sup> 3✉</sup>&emsp;
    <a href='https://scholar.google.com/citations?hl=en&user=rUOpCEYAAAAJ' target='_blank'>Wangmeng Zuo</a><sup> 1✉</sup>
</div>

<div align='center'>
    <sup>1 </sup>Harbin Institute of Technology&emsp;
    <sup>2 </sup>vivo BlueImage Lab&emsp;
    <sup>3 </sup>Nanjing University
</div>

<div align='center'>
    <small><sup>*</sup> Work done during an internship at vivo.</small>&emsp;
    <small><sup>†</sup> Project lead</small>
</div>

<div align="center">
  <p>
    <a href="https://arxiv.org/abs/2606.31089" target="_blank"><img src="https://img.shields.io/badge/arXiv-ART-red" alt="arXiv link"></a>&nbsp;
    <a href="https://csbowei.github.io/ART/" target="_blank"><img src="https://img.shields.io/badge/Project-Homepage-green" alt="project homepage"></a>&nbsp;
    <a href="https://github.com/csbowei/ART" target="_blank"><img src="https://img.shields.io/badge/GitHub-Code-blue?logo=github" alt="GitHub code"></a>
    <a href="https://drive.google.com/drive/folders/1UfUUAk86fWWzYsZcGOzpTmAWa32IwK21?usp=drive_link" target="_blank"><img src="https://img.shields.io/badge/Dataset-MF2K-purple?logo=googledrive&logoColor=white" alt="MF2K Dataset"></a>
  </p>
</div>

This repository provides the model weights for **ART: Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer**.

ART is a makeup transfer framework that applies a reference cosmetic style to a source face while preserving identity, geometry, and fine-grained makeup details.

## Files

| File                                | Task            |
| ----------------------------------- | --------------- |
| `art_transfer_lora_512.safetensors` | Makeup transfer |
| `art_transfer_lora_1024.safetensors` | Makeup transfer |
| `art_demakeup_lora_512.safetensors` | Makeup removal  |
| `art_demakeup_lora_1024.safetensors` | Makeup removal  |

Higher-resolution checkpoints will be released in the future. Stay tuned.

## Usage

These LoRA adapters are for [`black-forest-labs/FLUX.1-Kontext-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev).

Refer to the project repository: https://github.com/csbowei/ART

Example:

```bash
# Makeup transfer: apply the reference's makeup onto the input face
python infer.py \
    --task        mt \
    --input       ./examples/source/src_001.jpg \
    --ref         ./examples/ref/ref_001.jpg \
    --lora_path   /path/to/art_transfer_lora_1024.safetensors \
    --resolution  1024
```

```bash
# Makeup removal: strip cosmetics from the input face
python infer.py \
    --task        demakeup \
    --input       ./examples/ref/ref_002.jpg \
    --lora_path   /path/to/art_demakeup_lora_1024.safetensors \
    --resolution  1024
```

## Citation

```bibtex
@article{wei2026art,
  title={Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer},
  author={Wei, Bo and Lin, Xianhui and Dong, Yi and Li, Zhongzhong and Li, Zonghui and Wang, Zirui and Yang, Jiachen and Liu, Xing and Gu, Hong and Li, Xiaoming and Zuo, Wangmeng},
  journal={arXiv preprint arXiv:2606.31089},
  year={2026}
}
```