To use Wan 2.2 through ComfyUI, the following steps are required:
- Clone ComfyUI-WanVideoWrapper repository:
git clone https://github.com/kijai/ComfyUI-WanVideoWrapper.git - Install the dependencies:
pip install -r requirements.txt - Place the model files in the corresponding ComfyUI directory (diffusion model, VAE, CLIP, etc.)
- Load workflow in ComfyUI, import Wan2.2 model and set parameters
The ComfyUI interface offers the following advantages over the command line approach:
- visualization: No need to memorize complex commands, set parameters via graphical interface
- Workflow management: Complex workflows can be saved and reused
- Real-time preview: Facilitate the adjustment and optimization of the generated results
- nodal editor: Flexible combination of different processing steps
Particularly suitable for non-technical people or creative scenarios that require frequent parameter adjustments. It also retains the ability to control advanced parameters, balancing ease of use and professionalism.
This answer comes from the articleWan2.2: Open Source Video Generation Model with Efficient Text and Image to Video SupportThe
May not be reproduced without permission:AI productivity tools " How to use Wan 2.2 via ComfyUI and what are the advantages over command line?
