Model Highlights
- Cinematic-level Aesthetic Control: Professional camera language, supports multi-dimensional visual control such as lighting, color, and composition
- Large-scale Complex Motion: Smoothly restores various complex motions, enhances motion controllability and naturalness
- Precise Semantic Compliance: Complex scene understanding, multi-object generation, better restoring creative intentions
- Efficient Compression Technology: 5B version with high compression ratio VAE, memory optimization, supports mixed training
Wan2.2 Open Source Model Versions
The Wan2.2 series models are based on the Apache 2.0 open source license and support commercial use. The Apache 2.0 license allows you to freely use, modify, and distribute these models, including for commercial purposes, as long as you retain the original copyright notice and license text.Model Type | Model Name | Parameters | Main Function | Model Repository |
---|---|---|---|---|
Hybrid Model | Wan2.2-TI2V-5B | 5B | Hybrid version supporting both text-to-video and image-to-video, a single model meets two core task requirements | 🤗 Wan2.2-TI2V-5B |
Image-to-Video | Wan2.2-I2V-A14B | 14B | Converts static images into dynamic videos, maintaining content consistency and smooth dynamic process | 🤗 Wan2.2-I2V-A14B |
Text-to-Video | Wan2.2-T2V-A14B | 14B | Generates high-quality videos from text descriptions, with cinematic-level aesthetic control and precise semantic compliance | 🤗 Wan2.2-T2V-A14B |
ComfyOrg Wan2.2 Live Streams
For ComfyUI Wan2.2 usage, we have conducted live streams, which you can view to learn how to use them. This tutorial will use the 🤗 Comfy-Org/Wan_2.2_ComfyUI_Repackaged version.Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates.
If you can’t find them in the template, your ComfyUI may be outdated.(Desktop version’s update will delay sometime)If nodes are missing when loading a workflow, possible reasons:
- You are not using the latest ComfyUI version(Nightly version)
- You are using Stable or Desktop version (Latest changes may not be included)
- Some nodes failed to import at startup

Wan2.2 TI2V 5B Hybrid Version Workflow Example
The Wan2.2 5B version should fit well on 8GB vram with the ComfyUI native offloading.
1. Download Workflow File
Please update your ComfyUI to the latest version, and through the menuWorkflow
-> Browse Templates
-> Video
, find “Wan2.2 5B video generation” to load the workflow.
Download JSON Workflow File
2. Manually Download Models
Diffusion Model VAE Text Encoder3. Follow the Steps

- Ensure the
Load Diffusion Model
node loads thewan2.2_ti2v_5B_fp16.safetensors
model. - Ensure the
Load CLIP
node loads theumt5_xxl_fp8_e4m3fn_scaled.safetensors
model. - Ensure the
Load VAE
node loads thewan2.2_vae.safetensors
model. - (Optional) If you need to perform image-to-video generation, you can use the shortcut Ctrl+B to enable the
Load image
node to upload an image. - (Optional) In the
Wan22ImageToVideoLatent
node, you can adjust the size settings and the total number of video frames (length
). - (Optional) If you need to modify the prompts (positive and negative), please do so in the
CLIP Text Encoder
node at step 5. - Click the
Run
button, or use the shortcutCtrl(cmd) + Enter
to execute video generation.
Wan2.2 14B T2V Text-to-Video Workflow Example
1. Workflow File
Please update your ComfyUI to the latest version, and through the menuWorkflow
-> Browse Templates
-> Video
, find “Wan2.2 14B T2V” to load the workflow.
Or update your ComfyUI to the latest version, then download the following video and drag it into ComfyUI to load the workflow.
Download JSON Workflow File
2. Manually Download Models
Diffusion Model VAE Text Encoder3. Follow the Steps

- Ensure the first
Load Diffusion Model
node loads thewan2.2_t2v_high_noise_14B_fp8_scaled.safetensors
model. - Ensure the second
Load Diffusion Model
node loads thewan2.2_t2v_low_noise_14B_fp8_scaled.safetensors
model. - Ensure the
Load CLIP
node loads theumt5_xxl_fp8_e4m3fn_scaled.safetensors
model. - Ensure the
Load VAE
node loads thewan_2.1_vae.safetensors
model. - (Optional) In the
EmptyHunyuanLatentVideo
node, you can adjust the size settings and the total number of video frames (length
). - (Optional) If you need to modify the prompts (positive and negative), please do so in the
CLIP Text Encoder
node at step 5. - Click the
Run
button, or use the shortcutCtrl(cmd) + Enter
to execute video generation.
Wan2.2 14B I2V Image-to-Video Workflow Example
1. Workflow File
Please update your ComfyUI to the latest version, and through the menuWorkflow
-> Browse Templates
-> Video
, find “Wan2.2 14B I2V” to load the workflow.
Or update your ComfyUI to the latest version, then download the following video and drag it into ComfyUI to load the workflow.
Download JSON Workflow File
You can use the following image as input:
2. Manually Download Models
Diffusion Model VAE Text Encoder3. Follow the Steps

- Make sure the first
Load Diffusion Model
node loads thewan2.2_t2v_high_noise_14B_fp8_scaled.safetensors
model. - Make sure the second
Load Diffusion Model
node loads thewan2.2_t2v_low_noise_14B_fp8_scaled.safetensors
model. - Make sure the
Load CLIP
node loads theumt5_xxl_fp8_e4m3fn_scaled.safetensors
model. - Make sure the
Load VAE
node loads thewan_2.1_vae.safetensors
model. - In the
Load Image
node, upload the image to be used as the initial frame. - If you need to modify the prompts (positive and negative), do so in the
CLIP Text Encoder
node at step 6. - (Optional) In
EmptyHunyuanLatentVideo
, you can adjust the size settings and the total number of video frames (length
). - Click the
Run
button, or use the shortcutCtrl(cmd) + Enter
to execute video generation.
Wan2.2 14B FLF2V Workflow Example
The first and last frame workflow uses the same model locations as the I2V section.1. Workflow and Input Material Preparation
Download the video or the JSON workflow below and open it in ComfyUI.Download JSON Workflow
Download the following images as input materials:

2. Follow the Steps

- Upload the image to be used as the starting frame in the first
Load Image
node. - Upload the image to be used as the ending frame in the second
Load Image
node. - Adjust the size settings in the
WanFirstLastFrameToVideo
node.- By default, a relatively small size is set to prevent low VRAM users from consuming too many resources.
- If you have enough VRAM, you can try a resolution around 720P.
- Write appropriate prompts according to your first and last frames.
- Click the
Run
button, or use the shortcutCtrl(cmd) + Enter
to execute video generation.