ComfyUI Hunyuan Video Examples

Hunyuan Video series is developed and open-sourced by Tencent, featuring a hybrid architecture that supports both Text-to-Video and Image-to-Video generation with a parameter scale of 13B. Technical features:

Core Architecture: Uses a DiT (Diffusion Transformer) architecture similar to Sora, effectively fusing text, image, and motion information to improve consistency, quality, and alignment between generated video frames. A unified full-attention mechanism enables multi-view camera transitions while ensuring subject consistency.
3D VAE: The custom 3D VAE compresses videos into a compact latent space, making image-to-video generation more efficient.
Superior Image-Video-Text Alignment: Utilizing MLLM text encoders that excel in both image and video generation, better following text instructions, capturing details, and performing complex reasoning.

You can learn more through the official repositories: Hunyuan Video and Hunyuan Video-I2V. This guide will walk you through setting up both Text-to-Video and Image-to-Video workflows in ComfyUI.

The workflow images in this tutorial contain metadata with model download information.Simply drag them into ComfyUI or use the menu Workflows -> Open (ctrl+o) to load the corresponding workflow, which will prompt you to download the required models.Alternatively, this guide provides direct model links if automatic downloads fail or you are not using the Desktop version. All models are available here for download.

Local users
Cloud users

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 If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:

You are not using the latest ComfyUI version (Nightly version)
Some nodes failed to import at startup

Common Models for All Workflows

The following models are used in both Text-to-Video and Image-to-Video workflows. Download and save them to the specified directories:

Text Encoder: clip_l.safetensors

Save to ComfyUI/models/text_encoders

Text Encoder: llava_llama3_fp8_scaled.safetensors

Save to ComfyUI/models/text_encoders

VAE: hunyuan_video_vae_bf16.safetensors

Save to ComfyUI/models/vae

Storage location:

ComfyUI/
├── models/
│   ├── text_encoders/
│   │   ├── clip_l.safetensors
│   │   └── llava_llama3_fp8_scaled.safetensors
│   └── vae/
│       └── hunyuan_video_vae_bf16.safetensors

Hunyuan Text-to-Video Workflow

Hunyuan Text-to-Video was open-sourced in December 2024, supporting 5-second short video generation through natural language descriptions in both Chinese and English.

1. Workflow

Download the workflow image below and drag it into ComfyUI to load the workflow: ComfyUI Workflow - Hunyuan Text-to-Video

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Hunyuan Video” in Template Library

2. Manual models installation

Diffusion Model: hunyuan_video_t2v_720p_bf16.safetensors

Save to ComfyUI/models/diffusion_models

Ensure you have all these model files in the correct locations:

ComfyUI/
├── models/
│   ├── text_encoders/
│   │   ├── clip_l.safetensors                       // Shared model
│   │   └── llava_llama3_fp8_scaled.safetensors      // Shared model
│   ├── vae/
│   │   └── hunyuan_video_vae_bf16.safetensors       // Shared model
│   └── diffusion_models/
│       └── hunyuan_video_t2v_720p_bf16.safetensors  // T2V model

3. Steps to run the workflow

Ensure the DualCLIPLoader node has loaded these models:
- clip_name1: clip_l.safetensors
- clip_name2: llava_llama3_fp8_scaled.safetensors
Ensure the Load Diffusion Model node has loaded hunyuan_video_t2v_720p_bf16.safetensors
Ensure the Load VAE node has loaded hunyuan_video_vae_bf16.safetensors
Click the Queue button or use the shortcut Ctrl(cmd) + Enter to run the workflow

When the length parameter in the EmptyHunyuanLatentVideo node is set to 1, the model can generate a static image.

Hunyuan Image-to-Video Workflow

Hunyuan Image-to-Video model was open-sourced on March 6, 2025, based on the HunyuanVideo framework. It transforms static images into smooth, high-quality videos and also provides LoRA training code to customize special video effects like hair growth, object transformation, and more. Currently, the Hunyuan Image-to-Video model has two versions:

v1 “concat”: Better motion fluidity but less adherence to the image guidance
v2 “replace”: Updated the day after v1, with better image guidance but seemingly less dynamic compared to v1

v1 “concat”

v2 “replace”

Shared Model for v1 and v2 Versions

CLIP Vision: llava_llama3_vision.safetensors

Save to ComfyUI/models/clip_vision

V1 “concat” Image-to-Video Workflow

1. Workflow and Asset

Download the workflow image below and drag it into ComfyUI to load the workflow: ComfyUI Workflow - Hunyuan Image-to-Video v1

Download Workflow

Download the workflow image and drag into ComfyUI

Download the image below and use it as the starting frame for the image-to-video generation:

Starting Frame: robot-ballet.png

Save and use as input image for I2V generation

Diffusion Model: hunyuan_video_image_to_video_720p_bf16.safetensors

Save to ComfyUI/models/diffusion_models

Ensure you have all these model files in the correct locations:

ComfyUI/
├── models/
│   ├── clip_vision/
│   │   └── llava_llama3_vision.safetensors                     // I2V shared model
│   ├── text_encoders/
│   │   ├── clip_l.safetensors                                  // Shared model
│   │   └── llava_llama3_fp8_scaled.safetensors                 // Shared model
│   ├── vae/
│   │   └── hunyuan_video_vae_bf16.safetensors                  // Shared model
│   └── diffusion_models/
│       └── hunyuan_video_image_to_video_720p_bf16.safetensors  // I2V v1 "concat" version model

3. Steps to run the workflow

Ensure that DualCLIPLoader has loaded these models:
- clip_name1: clip_l.safetensors
- clip_name2: llava_llama3_fp8_scaled.safetensors
Ensure that Load CLIP Vision has loaded llava_llama3_vision.safetensors
Ensure that Load Image Model has loaded hunyuan_video_image_to_video_720p_bf16.safetensors
Ensure that Load VAE has loaded vae_name: hunyuan_video_vae_bf16.safetensors
Ensure that Load Diffusion Model has loaded hunyuan_video_image_to_video_720p_bf16.safetensors
Click the Queue button or use the shortcut Ctrl(cmd) + Enter to run the workflow

v2 “replace” Image-to-Video Workflow

The v2 workflow is essentially the same as the v1 workflow. You just need to download the replace model and use it in the Load Diffusion Model node.

1. Workflow and Asset

Download the workflow image below and drag it into ComfyUI to load the workflow: ComfyUI Workflow - Hunyuan Image-to-Video v2

Download Workflow

Download the workflow image and drag into ComfyUI

Download the image below and use it as the starting frame for the image-to-video generation:

Starting Frame: flux_dev_example.png

Save and use as input image for I2V generation

Diffusion Model: hunyuan_video_v2_replace_image_to_video_720p_bf16.safetensors

Save to ComfyUI/models/diffusion_models

Ensure you have all these model files in the correct locations:

ComfyUI/
├── models/
│   ├── clip_vision/
│   │   └── llava_llama3_vision.safetensors                                // I2V shared model
│   ├── text_encoders/
│   │   ├── clip_l.safetensors                                             // Shared model
│   │   └── llava_llama3_fp8_scaled.safetensors                            // Shared model
│   ├── vae/
│   │   └── hunyuan_video_vae_bf16.safetensors                             // Shared model
│   └── diffusion_models/
│       └── hunyuan_video_v2_replace_image_to_video_720p_bf16.safetensors  // V2 "replace" version model

3. Steps to run the workflow

Ensure the DualCLIPLoader node has loaded these models:
- clip_name1: clip_l.safetensors
- clip_name2: llava_llama3_fp8_scaled.safetensors
Ensure the Load CLIP Vision node has loaded llava_llama3_vision.safetensors
Ensure the Load Image Model node has loaded hunyuan_video_image_to_video_720p_bf16.safetensors
Ensure the Load VAE node has loaded hunyuan_video_vae_bf16.safetensors
Ensure the Load Diffusion Model node has loaded hunyuan_video_v2_replace_image_to_video_720p_bf16.safetensors
Click the Queue button or use the shortcut Ctrl(cmd) + Enter to run the workflow

Try It Yourself

Here are some images and prompts we provide. Use them as-is or adjust to create your own video.

Futuristic robot dancing ballet, dynamic motion, fast motion, fast shot, moving scene

Samurai waving sword and hitting the camera. camera angle movement, zoom in, fast scene, super fast, dynamic

flying car fastly moving and flying through the city

cyberpunk car race in night city, dynamic, super fast, fast shot

Get Started

Agent Tools

Basic Concepts

Interface Guide

Tutorials

Partner Nodes

ComfyUI Hunyuan Video Examples

Common Models for All Workflows

Text Encoder: clip_l.safetensors

Text Encoder: llava_llama3_fp8_scaled.safetensors

VAE: hunyuan_video_vae_bf16.safetensors

Hunyuan Text-to-Video Workflow

1. Workflow

Run on Comfy Cloud

Download Workflow

2. Manual models installation

Diffusion Model: hunyuan_video_t2v_720p_bf16.safetensors

3. Steps to run the workflow

Hunyuan Image-to-Video Workflow

Shared Model for v1 and v2 Versions

CLIP Vision: llava_llama3_vision.safetensors

V1 “concat” Image-to-Video Workflow

1. Workflow and Asset

Download Workflow

Starting Frame: robot-ballet.png

Diffusion Model: hunyuan_video_image_to_video_720p_bf16.safetensors

3. Steps to run the workflow

v2 “replace” Image-to-Video Workflow

1. Workflow and Asset

Download Workflow

Starting Frame: flux_dev_example.png

Diffusion Model: hunyuan_video_v2_replace_image_to_video_720p_bf16.safetensors

3. Steps to run the workflow

Try It Yourself

​Common Models for All Workflows

Text Encoder: clip_l.safetensors

Text Encoder: llava_llama3_fp8_scaled.safetensors

VAE: hunyuan_video_vae_bf16.safetensors

​Hunyuan Text-to-Video Workflow

​1. Workflow

Run on Comfy Cloud

Download Workflow

​2. Manual models installation

Diffusion Model: hunyuan_video_t2v_720p_bf16.safetensors

​3. Steps to run the workflow

​Hunyuan Image-to-Video Workflow

​Shared Model for v1 and v2 Versions

CLIP Vision: llava_llama3_vision.safetensors

​V1 “concat” Image-to-Video Workflow

​1. Workflow and Asset

Download Workflow

Starting Frame: robot-ballet.png

​2. Related models manual installation

Diffusion Model: hunyuan_video_image_to_video_720p_bf16.safetensors

​3. Steps to run the workflow

​v2 “replace” Image-to-Video Workflow

​1. Workflow and Asset

Download Workflow

Starting Frame: flux_dev_example.png

​2. Related models manual installation

Diffusion Model: hunyuan_video_v2_replace_image_to_video_720p_bf16.safetensors

​3. Steps to run the workflow

​Try It Yourself

Common Models for All Workflows

Hunyuan Text-to-Video Workflow

1. Workflow

2. Manual models installation

3. Steps to run the workflow

Hunyuan Image-to-Video Workflow

Shared Model for v1 and v2 Versions

V1 “concat” Image-to-Video Workflow

1. Workflow and Asset

2. Related models manual installation

3. Steps to run the workflow

v2 “replace” Image-to-Video Workflow

1. Workflow and Asset

2. Related models manual installation

3. Steps to run the workflow

Try It Yourself