Skip to content

Wan 2.2 VACE Video Editing

Video Lecture

Section Video Links
Wan 2.2 VACE Video Editing Wan 2.2 VACE Video Editing Wan 2.2 VACE Video Editing

Description

VACE : All-in-One Video Creation and Editing

Think of it like inpainting, but for video.

Install ComfyUI-segment-anything-2

Install the custom node ComfyUI-segment-anything-2 using the manager, or you can use your command/terminal prompt.

  1. Navigate to your ComfyUI/custom_nodes folder.
  2. Run, 
    git clone https://github.com/kijai/ComfyUI-segment-anything-2.git
  3. Restart ComfyUI

Download Models

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 clip/
│   │   └── umt5-xxl-encoder-Q8_0.gguf
│   ├── 📂 loras/
│   │   ├── Wan2.2-I2V-A14B-lora-high_noise.safetensors
│   │   └── Wan2.2-I2V-A14B-lora-low_noise.safetensors
│   ├── 📂 unet/
│   │   ├── Wan2.2-VACE-Fun-A14B-high-noise-Q8_0.gguf
│   │   └── Wan2.2-VACE-Fun-A14B-low-noise-Q8_0.gguf
│   └── 📂 vae/
│       └── wan2.1_vae.safetensors

Workflows

For VACE workflow use the WanVaceToVideo node.

Initial Workflow

Guiding Videos

Movement Only Movement Only With Speech

wan2.2-I2V-1.webm
wan2.2-I2V-2.webm
wan2.2-S2V-1.webm

Initial Images

WGET Commands

If you are using Runpod, or a similar hosted GPU service, then you can access your running pod/instance using a terminal.

#
#
# CD into ./ComfyUI/models/clip/ folder
wget https://huggingface.co/city96/umt5-xxl-encoder-gguf/resolve/main/umt5-xxl-encoder-Q8_0.gguf

#
#
#
# CD into ./ComfyUI/models/loras/ folder
wget https://huggingface.co/lightx2v/Wan2.2-Lightning/resolve/main/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1/high_noise_model.safetensors -O Wan2.2-I2V-A14B-lora-high_noise.safetensors
wget https://huggingface.co/lightx2v/Wan2.2-Lightning/resolve/main/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1/low_noise_model.safetensors -O Wan2.2-I2V-A14B-lora-low_noise.safetensors

#
#
#
# CD into ./ComfyUI/models/unet/ folder
wget https://huggingface.co/QuantStack/Wan2.2-VACE-Fun-A14B-GGUF/resolve/main/HighNoise/Wan2.2-VACE-Fun-A14B-high-noise-Q8_0.gguf
wget https://huggingface.co/QuantStack/Wan2.2-VACE-Fun-A14B-GGUF/resolve/main/LowNoise/Wan2.2-VACE-Fun-A14B-low-noise-Q8_0.gguf

#
#
# CD into ./ComfyUI/models/vae/ folder
wget https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors

Wait for files to download fully before running your workflows.

https://github.com/ali-vilab/VACE

https://ali-vilab.github.io/VACE-Page/