https://github.com/ant-research/edicho
[ICCV 2025] Edicho: Consistent Image Editing in the Wild
https://github.com/ant-research/edicho
diffusion-models image-editing
Last synced: 6 months ago
JSON representation
[ICCV 2025] Edicho: Consistent Image Editing in the Wild
- Host: GitHub
- URL: https://github.com/ant-research/edicho
- Owner: ant-research
- Created: 2024-12-30T15:45:12.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-10-22T17:12:19.000Z (10 months ago)
- Last Synced: 2026-02-09T02:23:38.402Z (6 months ago)
- Topics: diffusion-models, image-editing
- Language: Python
- Homepage: https://ant-research.github.io/edicho/
- Size: 22.4 MB
- Stars: 124
- Watchers: 13
- Forks: 1
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Edicho: Consistent Image Editing in the Wild
> **Edicho: Consistent Image Editing in the Wild**
> Qingyan Bai, Hao Ouyang, Yinghao Xu, Qiuyu Wang, Ceyuan Yang, Ka Leong Cheng, Yujun Shen, Qifeng Chen
**Figure:** Given two images in the wild, Edicho generates consistent editing versions of them in a zero-shot manner. Our approach
achieves precise consistency for editing parts (left), objects (middle), and the entire images (right) by leveraging explicit correspondence.
**[**[**Paper**](https://arxiv.org/abs/2412.21079)**]**
**[**[**Project Page**](https://ant-research.github.io/edicho/)**]**
As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments.
Edicho, embodying "echoing the editing effect", steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing.
Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence.
Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet.
Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings.
**Figure:** Method overview. To achieve consistent editing, we propose a training-free and plug-and-play method that injects the pre-computed correspondence into the pre-trained diffusion models and guides the denoising in the two levels of (a) attention features and (b) noisy latents in classifier-free guidance (CFG).
## How to Run
### 1) Environment setup
- Main dependencies (pip install -e .) | [BrushNet extras](examples/brushnet/requirements.txt) | [DIFT env](https://github.com/Tsingularity/dift/blob/main/environment.yml)
### 2) Prepare pretrained model weights
- The editing model: [Sanster/brushnet_segmentation_mask](https://huggingface.co/Sanster/brushnet_segmentation_mask/tree/main)
- The base diffusion model: `realisticVision_diffusers` (for instance, [this model](https://huggingface.co/emilianJR/RealisticVision_V2)). Set `--base_model_path` to the local path of this model checkpoint directory.
### 3) Run inference
Organize your inputs under one folder (e.g., `./images/toy`) with images and masks:
- Images named like `input_*.png` or `input_*.jpg`
- Masks named like `mask_*.jpg`
Then run:
```bash
python infer.py \
--base_model_path /path/to/checkpoints \
--brushnet_path Sanster/brushnet_segmentation_mask \
--in_dir ./images/toy \
--save_dir_root ./results \
--prompt_main "Your prompt" \
--prompt_add "Prompt suffix" \
--num_inference_steps 50 \
--seed 42
```
Outputs will be saved under `./results//` as a concatenated image.
## BibTeX
If you find our work helpful for your research, please consider to cite:
```bibtex
@inproceedings{bai2024edicho,
title = {Edicho: Consistent Image Editing in the Wild},
author = {Bai, Qingyan and Ouyang, Hao and Xu, Yinghao and Wang, Qiuyu and Yang, Ceyuan and Cheng, Ka Leong and Shen, Yujun and Chen, Qifeng},
booktitle = {arXiv preprint arXiv:2412.21079},
year = {2024}
}
```