ComfyUI_KV_Edit

KV_Edit: Training-Free Image Editing for Precise Background Preservation, re-implemented on ComfyUI's own FLUX DiT stack.

update

• 改成comfyUI的内核封装 /changed to ComfyUI's own FLUX DiT stack

1. Installation

In the ./ComfyUI/custom_nodes directory, run the following:

git clone https://github.com/smthemex/ComfyUI_KV_Edit

2.Model

• 2.1 download 'ae.safetensor' and 'flux1-dev.safetensors' from here 下载ae和flux单体模型模型,文件结构如下图
• 2.2 download 'clip_l.safetensors' and 't5xxl_fp8_e4m3fn.safetensors' from here下载T5和clip l单体模型模型,文件结构如下图

--   ComfyUI/models/diffusion_models  # or unet
    ├── flux1-dev.safetensors #23.8G 全量
    ├── flux1-kj-dev-fp8.safetensors #11G 名字中有fp8自动开启量化，注意不支持comfy量化的版本
--   ComfyUI/models/clip
    ├── clip_l.safetensors
    ├── t5xxl_fp8_e4m3fn.safetensorsvae
--   ComfyUI/models/vae
    ├── ae.safetensor

3 Example

• new

4 Citation

@article{zhu2025kv,
  title={KV-Edit: Training-Free Image Editing for Precise Background Preservation},
  author={Zhu, Tianrui and Zhang, Shiyi and Shao, Jiawei and Tang, Yansong},
  journal={arXiv preprint arXiv:2502.17363},
  year={2025}
}