Wan2.1 Video series is a video generation model open-sourced by Alibaba in February 2025 under the Apache 2.0 license. It offers two versions:

  • 14B (14 billion parameters)
  • 1.3B (1.3 billion parameters) Covering multiple tasks including text-to-video (T2V) and image-to-video (I2V). The model not only outperforms existing open-source models in performance but more importantly, its lightweight version requires only 8GB of VRAM to run, significantly lowering the barrier to entry.

If you find missing nodes when loading the workflow file below, it may be due to the following situations:

  1. You are not using the latest Development (Nightly) version of ComfyUI.
  2. You are using the Stable (Release) version or Desktop version of ComfyUI (which does not include the latest feature updates).
  3. You are using the latest Commit version of ComfyUI, but some nodes failed to import during startup.

Please make sure you have successfully updated ComfyUI to the latest Development (Nightly) version. See: How to Update ComfyUI section to learn how to update ComfyUI.

​
Wan2.1 ComfyUI Native Workflow Examples

Please update ComfyUI to the latest version before starting the examples to make sure you have native Wan Video support.

​
Model Installation

All models mentioned in this guide can be found here. Below are the common models you’ll need for the examples in this guide, which you can download in advance:

Choose one version from Text encoders to download:

VAE

CLIP Vision

File storage locations:

ComfyUI/
├── models/
│   ├── diffusion_models/
│   ├── ...                  # Let's download the models in the corresponding workflow
│   ├── text_encoders/
│   │   └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors
│   └── vae/
│   │   └──  wan_2.1_vae.safetensors
│   └── clip_vision/
│       └──  clip_vision_h.safetensors

For diffusion models, we’ll use the fp16 precision models in this guide because we’ve found that they perform better than the bf16 versions. If you need other precision versions, please visit here to download them.

​
Wan2.1 Text-to-Video Workflow

Before starting the workflow, please download wan2.1_t2v_1.3B_fp16.safetensors and save it to the ComfyUI/models/diffusion_models/ directory.

If you need other t2v precision versions, please visit here to download them.

​
1. Workflow File Download

Download the file below and drag it into ComfyUI to load the corresponding workflow:

​
2. Complete the Workflow Step by Step

  1. Make sure the Load Diffusion Model node has loaded the wan2.1_t2v_1.3B_fp16.safetensors model
  2. Make sure the Load CLIP node has loaded the umt5_xxl_fp8_e4m3fn_scaled.safetensors model
  3. Make sure the Load VAE node has loaded the wan_2.1_vae.safetensors model
  4. (Optional) You can modify the video dimensions in the EmptyHunyuanLatentVideo node if needed
  5. (Optional) If you need to modify the prompts (positive and negative), make changes in the CLIP Text Encoder node at number 5
  6. Click the Run button or use the shortcut Ctrl(cmd) + Enter to execute the video generation

​
Wan2.1 Image-to-Video Workflow

Since Wan Video separates the 480P and 720P models, we’ll need to provide examples for both resolutions in this guide. In addition to using different models, they also have slight parameter differences.

​
480P Version

​
1. Workflow and Input Image

Download the image below and drag it into ComfyUI to load the corresponding workflow:

We’ll use the following image as input:

​
2. Model Download

Please download wan2.1_i2v_480p_14B_fp16.safetensors and save it to the ComfyUI/models/diffusion_models/ directory.

​
3. Complete the Workflow Step by Step

  1. Make sure the Load Diffusion Model node has loaded the wan2.1_i2v_480p_14B_fp16.safetensors model
  2. Make sure the Load CLIP node has loaded the umt5_xxl_fp8_e4m3fn_scaled.safetensors model
  3. Make sure the Load VAE node has loaded the wan_2.1_vae.safetensors model
  4. Make sure the Load CLIP Vision node has loaded the clip_vision_h.safetensors model
  5. Upload the provided input image in the Load Image node
  6. (Optional) Enter the video description content you want to generate in the CLIP Text Encoder node
  7. (Optional) You can modify the video dimensions in the WanImageToVideo node if needed
  8. Click the Run button or use the shortcut Ctrl(cmd) + Enter to execute the video generation

​
720P Version

​
1. Workflow and Input Image

Download the image below and drag it into ComfyUI to load the corresponding workflow:

We’ll use the following image as input:

​
2. Model Download

Please download wan2.1_i2v_720p_14B_fp16.safetensors and save it to the ComfyUI/models/diffusion_models/ directory.

​
3. Complete the Workflow Step by Step

  1. Make sure the Load Diffusion Model node has loaded the wan2.1_i2v_720p_14B_fp16.safetensors model
  2. Make sure the Load CLIP node has loaded the umt5_xxl_fp8_e4m3fn_scaled.safetensors model
  3. Make sure the Load VAE node has loaded the wan_2.1_vae.safetensors model
  4. Make sure the Load CLIP Vision node has loaded the clip_vision_h.safetensors model
  5. Upload the provided input image in the Load Image node
  6. (Optional) Enter the video description content you want to generate in the CLIP Text Encoder node
  7. (Optional) You can modify the video dimensions in the WanImageToVideo node if needed
  8. Click the Run button or use the shortcut Ctrl(cmd) + Enter to execute the video generation