ComfyUI-X-Portrait-Nodes

ComfyUI-X-Portrait-Nodes
★ 86

人像动画视频驱动参考图像ComfyUI节点
为ComfyUI提供X-Portrait节点，通过输入视频与参考人像驱动并生成可控的人像动画，便于风格保留与动作迁移。
💡 用视频和参考图驱动静态人像生成连贯动画
🍴 2 Forks💻 Python🔄 2025-04-20
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/e58c8376a81b
📦 requirements.txt
numpy
einops
opencv-python
matplotlib
imageio
omegaconf
scikit-image
face-alignment
torchvision
diffusers
pytorch-lightning
xformers
sageattention
transformers
open-clip-torch
imageio[ffmpeg]
triton
Example workflow 1
📄 README

X-Portrait Nodes

Animate portraits with an input video and a reference image using X-Portrait in ComfyUI.

Original X-Portrait Repo

  • source_image: the reference image for generation, should be square and max 512×512.
  • driving_video: the driving video containing a face, should match the resolution of the source_image and max 512×512.
  • seed: controls current generation seed
  • ddim_steps: how many samples (steps) for generating the output. Diminishing returns after 15.
  • best_frame: which frame of the driving_video most closely matches the source_image.

    • 🖥️ Custom Environment

    I created a custom ComfyUI environment for testing out X-Portrait nodes:

    akatzai/comfy-env-xportrait:latest

    Create a new environment and copy and paste the link above into the “Custom Image” field in my Environment Manager tool:

    https://github.com/akatz-ai/ComfyUI-Environment-Manager

    Make sure to select the Basic environment type to access the included workflow!

    ⭐ Example Workflow (in examples/)

    🔧 Installation and Usage

  • ComfyUI Manager:

  • This node pack is available to install via the ComfyUI Manager. You can find it in the Custom Nodes section by searching for “X-Portrait” and clicking on the entry called “X-Portrait Nodes”.

  • Clone the repository:
  • Navigate to ComfyUI/custom_nodes folder in terminal or command prompt.
  • Clone the repo using the following command:
    • git clone https://github.com/akatz-ai/ComfyUI-X-Portrait-Nodes.git
  • Restart ComfyUI