Yunlong Lin1*,
Zixu Lin1*,
Kunjie Lin1*,
Jinbin Bai5,
Panwang Pan4,
Chenxin Li3,
Haoyu Chen2,
Zhongdao Wang6,
Xinghao Ding1†,
Wenbo Li3♣,
Shuicheng Yan5†
1Xiamen University, 2The Hong Kong University of Science and Technology (Guangzhou), 3 The Chinese University of Hong Kong, 4Bytedance, 5National University of Singapore, 6Tsinghua University
💡 Our new work that may interest you ✨.
[CVPR’ 2026] JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization
Yunlong Lin, Lingqing Wang, Zixu Lin and Kunjie Lin, etc.
📮 Updates
🧭 Navigation
📝 Overview
JarvisArt workflow and results showcase
JarvisArt is a multi-modal large language model (MLLM)-driven agent for intelligent photo retouching. It is designed to liberate human creativity by understanding user intent, mimicking the reasoning of professional artists, and coordinating over 200 tools in Adobe Lightroom. JarvisArt utilizes a novel two-stage training framework, starting with Chain-of-Thought supervised fine-tuning for foundational reasoning, followed by Group Relative Policy Optimization for Retouching (GRPO-R) to enhance its decision-making and tool proficiency. Supported by the newly created MMArt dataset (55K samples) and MMArt-Bench, JarvisArt demonstrates superior performance, outperforming GPT-4o with a 60% improvement in pixel-level metrics for content fidelity while maintaining comparable instruction-following capabilities.
📦 Dataset Source FAQ
To clarify data provenance for MMArt (including the distribution summary shown in the paper):
- As described in the paper, MMArt is constructed from PPR10K and other licensed open-source collections.
- In this repository, the currently public dataset releases are:
- A full per-source breakdown list for every subset in Figure 9 is not yet published in this repository.
🎬 Demo Videos
Global Retouching Case
Local Retouching Case
JarvisArt supports multi-granularity retouching goals, ranging from scene-level adjustments to region-specific refinements. Users can perform intuitive, free-form edits through natural inputs such as text prompts and bounding boxes
💻 Getting Started
For gradio demo running, please follow:
For batch inference, please follow the instructions below:
For Agent-to-Lightroom Protocol, please follow:
For training (SFT & GRPO-R), please follow:
For data construction pipeline (image pairs, instructions, CoT generation & format conversion), please follow:
For evaluation, please follow:
🎪 Checklist
🔍 Jarvis Family
JarvisIR: An intelligent image restoration agent for diverse and complex degradations in real-world scenarios.
We are excited to expand the Jarvis family with more intelligent agents in the future. Stay tuned for upcoming releases!
🙏 Acknowledgements
We would like to express our gratitude to LLaMA-Factory, gradio_image_annotator and VLM-R1 for their valuable open-source contributions which have provided important technical references for our work.
🌤️ Discussion Group
If you have any questions during the trial, running or deployment, feel free to join our WeChat group discussion!
WeChat Group 1
|
WeChat Group 2
|
Scan QR code to join WeChat group discussion
For any questions or inquiries, please reach out to us:
📚 Citation
If you find JarvisArt useful in your research, please consider citing:
@article{jarvisart2025,
title={JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent},
author={Yunlong Lin and Zixu Lin and Kunjie Lin and Jinbin Bai and Panwang Pan and Chenxin Li and Haoyu Chen and Zhongdao Wang and Xinghao Ding and Wenbo Li and Shuicheng Yan},
year={2025},
journal={arXiv preprint arXiv:2506.17612}
}
📜 License
The JarvisArt model weights, inference code, and associated materials are made freely available by Yunlong Lin for academic research, personal study, and other non-commercial uses under the JarvisArt Non-Commercial License.
By downloading, accessing, or using the JarvisArt model, you agree to the terms of this license. Please refer to the JarvisArt Non-Commercial License v1.0 file in this repository for the full terms and conditions.
Commercial Use: If you wish to use the JarvisArt model or its derivatives for commercial purposes, please contact me at [[email protected]] to request a commercial license.
评论