Guanlong Jiao1,3, Biqing Huang1, Kuan-Chieh Wang2, Renjie Liao3
1Tsinghua University, 2Snap Inc., 3The University of British Columbia
TL;DR: A highly accurate and efficient, model-agnostic, training and tuning-free sampling strategy for inversion and editing tasks. Support text-driven image 🎨 (FLUX, Stable Diffusion 3, Stable Diffusion XL, etc.) and video 🎥 (Wan, flow-based video generation model) editing.
In this work, we introduce a predictor-corrector-based framework for inversion and editing in flow models. First, we propose Uni-Inv, an effective inversion method designed for accurate reconstruction. Building on this, we extend the concept of delayed injection to flow models and introduce Uni-Edit, a region-aware, robust image editing approach. Our methodology is tuning-free, model-agnostic, efficient, and effective, enabling diverse edits while ensuring strong preservation of edit-irrelevant regions.
More results can be found in our project page.
| Editing Prompt | Source Image | FLUX | Stable Diffusion 3 | Stable Diffusion XL |
| A |
 |
 |
 |
 |
| Two origami birds sitting on a branch. |  |
 |
 |
 |
| A clown in pixel art style with colorful hair. |  |
 |
 |
 |
| Editing Prompt | Source Video | Wan + Uni-Edit |
| A young rider wearing full protective gear, including a black helmet and motocross-style outfit, is navigating a |
 |
 |
| A |
 |
 |
Here we provide two implementation options:
- Implementation by diffusers: Support FLUX (e.g.,
black-forest-labs/FLUX.1-dev), Stable Diffusion 3 (e.g.,stabilityai/stable-diffusion-3-medium), Stable Diffusion XL (e.g.,SG161222/RealVisXL_V4.0), etc., for text-driven image editing tasks. As well, support Wan (e.g.,Wan-AI/Wan2.1-T2V-1.3B-Diffusers) for text-driven video editing tasks. - Implementation on official FLUX repository: Implementation based on original FLUX. The performance is slightly better than the diffusers-based FLUX pipeline.
We sincerely thank FireFlow, RF-Solver, and FLUX for their awesome work! Additionally, we would also like to thank PnpInversion for providing comprehensive baseline survey and implementations, as well as their great benchmark.
If you like our work, you can cite our paper through the bibtex below. Thank for your attention!
@misc{jiao2025unieditflowunleashinginversionediting,
title={UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models},
author={Guanlong Jiao and Biqing Huang and Kuan-Chieh Wang and Renjie Liao},
year={2025},
eprint={2504.13109},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2504.13109},
}