Wan VACE ComfyUI video-to-video

WAN 2.1 VACE (Video All-in-One Creation and Editing) is a video generation and editing AI model that you can run locally on your computer. It unifies text-to-video, reference-to-video (reference-guided generation), video-to-video (pose and depth control), inpainting, and outpainting under a single framework.

VACE supports the following core functions:

Reference-to-Video (R2V): Generate a video sequence from reference images.
Video-to-Video (V2V): Apply style transfer to an existing video.
Masked Video Editing (MV2V): Inpaint or outpaint specific regions within each frame.

This tutorial covers the Wan Vace Video-to-Video (V2V) workflow on ComfyUI, which:

Copy the movement of a person in the reference video. (via OpenPose control)
Copy the face and clothing of a person in the reference image.

Here’s the reference video and reference image.

Table of Contents

Software
Generation time
Google Colab notebook
Other Wan 2.1 workflows
Wan 2.1 VACE video-to-video
Tips for using the Wan VACE V2V model

Software

We will use ComfyUI, a free AI image and video generator. You can use it on Windows, Mac, or Google Colab.

Think Diffusion provides an online ComfyUI service. They offer an extra 20% credit to our readers.

Read the ComfyUI beginner’s guide if you are new to ComfyUI. See the Quick Start Guide if you are new to AI images and videos.

Take the ComfyUI course to learn how to use ComfyUI step by step.

Generation time

This workflow takes 50 minutes to generate a 3.3-second 608 x 1088 clip on my RTX4090. Reducing the resolution to 720 x 720 reduces the generation time to 23 minutes.

Google Colab notebook

My ComfyUI Google Colab notebook supports running this workflow. It comes in handy if you don’t have a fast GPU card.

If you use it, you can select L4 or A100 (fast) GPU to run this workflow. Select Wan 2.1 under Video models and skip the model download step below.

Other Wan 2.1 workflows

Wan VACE Reference-to-video
Wan 2.1 Text-to-Video: Generate a video based on the text prompt.
Wan 2.1 Image-to-Video: Generate a video with the initial frame’s image.
Speeding up Wan 2.1 with Teacache and Sage Attention
Flux-Wan 2.1 video workflow (ComfyUI)
Flux-Wan 2.1 four-clip movie (ComfyUI)

Wan 2.1 VACE video-to-video

Step 1: Update ComfyUI

Before loading the workflow, make sure your ComfyUI is up-to-date. The easiest way to do this is to use ComfyUI Manager.

Click the Manager button on the top toolbar.

Select Update ComfyUI.

Restart ComfyUI.

Step 2: Download model files

Download the diffusion model wan2.1_vace_14B_fp16.safetensors and put it in ComfyUI > models > diffusion_models.

Download the text encoder model umt5_xxl_fp8_e4m3fn_scaled.safetensors and put it in ComfyUI > models > text_encoders.

Download the Wan VAE model wan_2.1_vae.safetensors and put it in ComfyUI > models > vae.

Step 3: Load the workflow

Download the workflow JSON file below and drop it into ComfyUI to load.

Download

Step 4: Install missing nodes

If you see red blocks, you don’t have the custom node that this workflow needs.

Click Manager > Install missing custom nodes, and install the missing nodes.

Restart ComfyUI.

Step 5: Set the input video

Upload a reference video to the Load Video node.

I used this video on TikTok. You can download it using online tools like this one.

Step 6: Set the input reference image

This Wan VACE workflow requires an input reference image. Like the reference-to-video workflow, it copies the likeness of the image.

Upload the reference image to the Load Image node.

The image was generated using the Flux.1 Dev model with the following prompt.

close up portriat of a stunning, ethereal woman elf with flowing hair stands in an enchanted forest at twilight. Her beautiful eyes and face is clearly visible. Blonde, Danish. smile.

Below is the input reference image.

Step 7: Revise the prompt

Revise the prompt to describe the video you want to generate. In the workflow, I have:

a stunning, ethereal woman elf with flowing hair stands in an enchanted forest at twilight. Her beautiful eyes and face is clearly visible. Blonde, Danish. smile. dancing,

Some tips:

Describe what the subject is doing.
Add action words, e.g., laugh, run, fight, etc.

Step 8: Generate the video

Click the Run button to run the workflow.

Tips for using the Wan VACE V2V model

Out-of-memory

High-resolution and long video lengths can cause an out-of-memory error during generation. If you see an “allocation on device” error, reduce the width, height, or length parameter in the WanVaceToVideo node.