ComfyUI_CatVTON_Wrapper

ComfyUI_CatVTON_Wrapper
★ 375

虚拟试衣服装换装图像合成ComfyUI插件
为ComfyUI封装CatVTON虚拟试衣功能，解决不同长宽比图片裁剪问题，便于一键换装与图像合成，优化工作流。
💡 在ComfyUI中实现人体图片与服装的自动换装合成。
🍴 48 Forks💻 Jupyter Notebook🔄 2025-01-01
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/51137d50651f
📦 requirements.txt
opencv-python==4.4.0.46
image
image
📄 README

ComfyUI_CatVTON_Wrapper

CatVTON warpper for ComfyUI. fixed the cropping issue of images with different proportions input.

Original repo: https://github.com/Zheng-Chong/CatVTON

It is recommend use 6G or higher VRAM NVidia GPU device to run.

Install Plugin

Open the cmd window in the plugin directory of ComfyUI, like ComfyUI\custom_nodes，type:

git clone https://github.com/chflame163/ComfyUI_CatVTON_Wrapper.git

Install Dependency Packages

Open the cmd window in the ComfyUI_CatVTON_Wrapper plugin directory like ComfyUI\custom_ Nodes\ComfyUI_CatVTON_Wrapper and enter the following command,

For ComfyUI official portable package, type:

..\..\..\python_embeded\python.exe -s -m pip install -r requirements.txt

For Aki ComfyUI package, type:

..\..\python\python.exe -s -m pip install -r requirements.txt

Download Models

Download all model files from BaiduNetdisk or GoogleDrive and copy to “ComtyUI/models/CatVTON“ directory.

Example Workflow

The example workflow files is in the workflow directory.

Node Options

  • image: The input image.
  • mask: The mask of input image, clothing within the mask range will be repaint.
  • refer_image: The reference image of repaint clothing.
  • mask_grow: The size of the mask expansion. If the repaint clothing style is incorrect, try adjusting this value.
  • mixed_precision: fp32, fp16, bf16 can be selected, the model will run under the selected data type.
  • seed: The random seed of sampler.
  • steps: The number of steps of sampler.
  • cfg: The cfg strength of the diffusion model.

    • Statement

    Please refer to the original project license to authorization agreement.