https://github.com/smthemex/ComfyUI_PhotoDoodle

PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data，you can use it in comfyUI
https://github.com/smthemex/ComfyUI_PhotoDoodle

Last synced: about 2 months ago
JSON representation

PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data，you can use it in comfyUI

• Host: GitHub
• URL: https://github.com/smthemex/ComfyUI_PhotoDoodle
• Owner: smthemex
• License: mit
• Created: 2025-02-27T05:45:15.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2025-02-27T05:50:02.000Z (about 2 months ago)
• Last Synced: 2025-02-27T06:48:37.366Z (about 2 months ago)
• Size: 273 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-comfyui - **ComfyUI_PhotoDoodle** - Shot Pairwise Data，you can use it in comfyUI (All Workflows Sorted by GitHub Stars)

README

        
# PhotoDoodle

[PhotoDoodle](https://github.com/showlab/PhotoDoodle) it a method about 'Learning Artistic Image Editing from Few-Shot Pairwise Data'，you can use it in comfyUI

# 1.Installation  

-----

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

```

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

```

# 2.requirements  

----

```

pip install -r requirements.txt

```

* If Vram <=24G  pip install mmgp ，这个方法适配的显存是40G，所以4090及以下显卡都要按照mmpg，这样才能跑得快，4090模型加载菜单，可以选0，或者1或者2

# 3.checkpoints 

* 3.1 mode use flux dev single checkpoints（fp8 or fp16） or repo or unet+ae+comfyui T5XXX ，三种选择，使用flux dev的fp8或fp16单体模型 或者使用repo，或者使用flux unet+ae+comfy的T5双clip

```

├── ComfyUI/models/diffusion_models/

|     ├── flux1-kj-dev-fp8.safetensors  # if use fp8 unet  11G  unet+vae+clip方法不推荐，因为更容易爆显存

|     ├── flux1-dev-fp8.safetensors  # if use fp8 single 16G  comfy官方单体模型或者flux官方单体模型，推荐，开启mmgp不会爆显存，虽然慢

```

* 3.2 more lora download from [here](https://huggingface.co/nicolaus-huang/PhotoDoodle/tree/main)

```

├── ComfyUI/models/loras/

|     ├── pretrain.safetensors  # 必须要

|     ├── skscloudsketch.safetensors  # 选你喜欢的lora

```

# 4 Example

* if use single files，vae must choice "none"  #flux1-dev-fp8.safetensors 16G 单体16G模型，内置clip和vae那种，vae必须选择"none"

![](https://github.com/smthemex/ComfyUI_PhotoDoodle/blob/main/assets/example.png)

* if use unet #11G 单体unet模型，没有内置clip和vae的，所以必须要连双clip和选vae

![](https://github.com/smthemex/ComfyUI_PhotoDoodle/blob/main/assets/example_c.png)

* if use repo 'black-forest-labs/FLUX.1-dev' or C:/youpath/black-forest-labs/FLUX.1-dev  如果使用repo可以用自动下载或本地

![](https://github.com/smthemex/ComfyUI_PhotoDoodle/blob/main/assets/example_b.png)

# 5. Acknowledgments  

1. Thanks to **[Yuxuan Zhang](https://xiaojiu-z.github.io/YuxuanZhang.github.io/)** and **[Hailong Guo](mailto:[email protected])** for providing the code base.  

2. Thanks to **[Diffusers](https://github.com/huggingface/diffusers)** for the open-source project.

# Citation

```

@misc{huang2025photodoodlelearningartisticimage,

      title={PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data}, 

      author={Shijie Huang and Yiren Song and Yuxuan Zhang and Hailong Guo and Xueyin Wang and Mike Zheng Shou and Jiaming Liu},

      year={2025},

      eprint={2502.14397},

      archivePrefix={arXiv},

      primaryClass={cs.CV},

      url={https://arxiv.org/abs/2502.14397}, 

}

```