> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-chore-sync-comfy-api-v2-spec-b886298.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# HunyuanVideo 1.5

> Learn how to use HunyuanVideo 1.5, a lightweight 8.3B parameter model for high-quality video generation on consumer GPUs

[HunyuanVideo 1.5](https://github.com/Tencent/HunyuanVideo) is a lightweight 8.3B parameter model developed by Tencent's Hunyuan team. It delivers flagship-quality video generation on consumer GPUs (24GB VRAM), dramatically lowering the barrier to entry without compromising on quality.

<Tip>
  <Tabs>
    <Tab title="Local users">
      Make sure your ComfyUI is updated.

      * [Download ComfyUI](https://www.comfy.org/download)
      * [Update Guide](/installation/update_comfyui)

      Workflows in this guide can be found in the [Workflow Templates](/interface/features/template).
      If you can't find them in the template, your ComfyUI may be outdated.

      If nodes are missing when loading a workflow, possible reasons:

      1. You are not using the latest ComfyUI version (Nightly version)
      2. Some nodes failed to import at startup
    </Tab>

    <Tab title="Cloud users">
      * [Cloud](https://cloud.comfy.org) will update after ComfyUI stable release.

      So, if you find any core node missing in this document, it might be because the new core nodes have not yet been released in the latest stable version. Please wait for the next stable release.
    </Tab>
  </Tabs>
</Tip>

## Model highlights

* **Compact powerhouse**: Delivers SOTA performance comparable to larger models while running on consumer hardware.
* **Versatile generation**: Supports high-quality Text-to-Video and Image-to-Video (5-10s) with exceptional consistency.
* **Precise control**: Strong instruction following for camera movements, physics, and emotional expressions.
* **Cinematic quality**: Native 720p output (upscalable to 1080p) with professional aesthetics.
* **Rich features**: Supports diverse styles (realistic, anime, 3D) and in-video text rendering (Chinese/English).

## 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:

<CardGroup cols={2}>
  <Card title="Download Qwen2.5 VL 7B" icon="download" href="https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/blob/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors?download=true">
    qwen\_2.5\_vl\_7b\_fp8\_scaled.safetensors — save to <code>ComfyUI/models/text\_encoders/</code>
  </Card>

  <Card title="Download ByT5 Small" icon="download" href="https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/blob/main/split_files/text_encoders/byt5_small_glyphxl_fp16.safetensors?download=true">
    byt5\_small\_glyphxl\_fp16.safetensors — save to <code>ComfyUI/models/text\_encoders/</code>
  </Card>

  <Card title="Download HunyuanVideo 1.5 VAE" icon="download" href="https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/blob/main/split_files/vae/hunyuanvideo15_vae_fp16.safetensors?download=true">
    hunyuanvideo15\_vae\_fp16.safetensors — save to <code>ComfyUI/models/vae/</code>
  </Card>
</CardGroup>

#### Storage

```
ComfyUI/
├── 📂 models/
│   ├── 📂 text_encoders/
│   │   ├── qwen_2.5_vl_7b_fp8_scaled.safetensors
│   │   └── byt5_small_glyphxl_fp16.safetensors
│   └── 📂 vae/
│       └── hunyuanvideo15_vae_fp16.safetensors
```

## Hunyuan Video 1.5 Text-to-Video Workflow

HunyuanVideo 1.5 Text-to-Video generates 5-10 second videos from natural language descriptions with enhanced quality and reduced VRAM requirements.

![ComfyUI Workflow - Hunyuan Video 1.5 T2V](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/templates/video_hunyuan_video_1.5_720p_t2v-1.webp)

<CardGroup cols={2}>
  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=video_hunyuan_video_1.5_720p_t2v&utm_source=docs&utm_medium=referral&utm_campaign=hunyuan-video-1-5">
    Open in Comfy Cloud
  </Card>

  <Card title="Download Workflow" icon="download" href="https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_hunyuan_video_1.5_720p_t2v.json">
    Download JSON or search "Hunyuan Video 1.5 T2V" in Template Library
  </Card>
</CardGroup>

### Model downloads

<CardGroup cols={2}>
  <Card title="Download T2V Diffusion Model" icon="download" href="https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/blob/main/split_files/diffusion_models/hunyuanvideo1.5_720p_t2v_fp16.safetensors?download=true">
    hunyuanvideo1.5\_720p\_t2v\_fp16.safetensors — save to <code>ComfyUI/models/diffusion\_models/</code>
  </Card>
</CardGroup>

#### Model storage

```
ComfyUI/
├── 📂 models/
│   ├── 📂 text_encoders/
│   │   ├── qwen_2.5_vl_7b_fp8_scaled.safetensors       // Shared model
│   │   └── byt5_small_glyphxl_fp16.safetensors           // Shared model
│   ├── 📂 vae/
│   │   └── hunyuanvideo15_vae_fp16.safetensors           // Shared model
│   └── 📂 diffusion_models/
│       └── hunyuanvideo1.5_720p_t2v_fp16.safetensors     // T2V model
```

### Steps to run the workflow

1. Ensure the `DualCLIPLoader` node has loaded these models:
   * clip\_name1: `qwen_2.5_vl_7b_fp8_scaled.safetensors`
   * clip\_name2: `byt5_small_glyphxl_fp16.safetensors`
2. Ensure the `Load Diffusion Model` node has loaded `hunyuanvideo1.5_720p_t2v_fp16.safetensors`
3. Ensure the `Load VAE` node has loaded `hunyuanvideo15_vae_fp16.safetensors`
4. Click the `Queue` button or use the shortcut `Ctrl(Cmd) + Enter` to run the workflow

<Tip>
  The workflow includes a super-resolution upscaler node. When enabled, it uses `hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors` to upscale the output to 1080p.
</Tip>

## Hunyuan Video 1.5 Image-to-Video Workflow

HunyuanVideo 1.5 Image-to-Video transforms static images into smooth, high-quality videos with improved consistency and motion dynamics.

![ComfyUI Workflow - Hunyuan Video 1.5 I2V](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/templates/video_hunyuan_video_1.5_720p_i2v-1.webp)

<CardGroup cols={2}>
  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=video_hunyuan_video_1.5_720p_i2v&utm_source=docs&utm_medium=referral&utm_campaign=hunyuan-video-1-5">
    Open in Comfy Cloud
  </Card>

  <Card title="Download Workflow" icon="download" href="https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_hunyuan_video_1.5_720p_i2v.json">
    Download JSON or search "Hunyuan Video 1.5 I2V" in Template Library
  </Card>
</CardGroup>

**Input materials**

<CardGroup cols={2}>
  <Card title="Input Image" icon="image" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/input/video_hunyuan_video_1.5_720p_i2v_input_image.png">
    Download the default input image, or use your own image as the starting frame.
  </Card>
</CardGroup>

### Model downloads

<CardGroup cols={2}>
  <Card title="Download CLIP Vision" icon="download" href="https://huggingface.co/Comfy-Org/sigclip_vision_384/blob/main/sigclip_vision_patch14_384.safetensors?download=true">
    sigclip\_vision\_patch14\_384.safetensors — save to <code>ComfyUI/models/clip\_vision/</code>
  </Card>

  <Card title="Download I2V Diffusion Model" icon="download" href="https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/blob/main/split_files/diffusion_models/hunyuanvideo1.5_720p_i2v_fp16.safetensors?download=true">
    hunyuanvideo1.5\_720p\_i2v\_fp16.safetensors — save to <code>ComfyUI/models/diffusion\_models/</code>
  </Card>
</CardGroup>

#### Model storage

```
ComfyUI/
├── 📂 models/
│   ├── 📂 clip_vision/
│   │   └── sigclip_vision_patch14_384.safetensors          // I2V vision encoder
│   ├── 📂 text_encoders/
│   │   ├── qwen_2.5_vl_7b_fp8_scaled.safetensors           // Shared model
│   │   └── byt5_small_glyphxl_fp16.safetensors             // Shared model
│   ├── 📂 vae/
│   │   └── hunyuanvideo15_vae_fp16.safetensors             // Shared model
│   └── 📂 diffusion_models/
│       └── hunyuanvideo1.5_720p_i2v_fp16.safetensors       // I2V model
```

### Steps to run the workflow

1. Ensure the `DualCLIPLoader` node has loaded these models:
   * clip\_name1: `qwen_2.5_vl_7b_fp8_scaled.safetensors`
   * clip\_name2: `byt5_small_glyphxl_fp16.safetensors`
2. Ensure the `CLIPVisionLoader` node has loaded `sigclip_vision_patch14_384.safetensors`
3. Ensure the `Load Diffusion Model` node has loaded `hunyuanvideo1.5_720p_i2v_fp16.safetensors`
4. Ensure the `Load VAE` node has loaded `hunyuanvideo15_vae_fp16.safetensors`
5. Click the `Queue` button or use the shortcut `Ctrl(Cmd) + Enter` to run the workflow

## Super-resolution upscaler

Both workflows include a super-resolution node that can upscale the output video from 720p to 1080p. This optional upscaler uses a distilled model for efficient high-resolution output.

<Card title="Download 1080p Upscaler" icon="download" href="https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/blob/main/split_files/diffusion_models/hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors?download=true">
  hunyuanvideo1.5\_1080p\_sr\_distilled\_fp16.safetensors — save to <code>ComfyUI/models/diffusion\_models/</code>
</Card>

All shared and workflow-specific models combined:

```
ComfyUI/
├── 📂 models/
│   ├── 📂 clip_vision/
│   │   └── sigclip_vision_patch14_384.safetensors
│   ├── 📂 text_encoders/
│   │   ├── qwen_2.5_vl_7b_fp8_scaled.safetensors
│   │   └── byt5_small_glyphxl_fp16.safetensors
│   ├── 📂 vae/
│   │   └── hunyuanvideo15_vae_fp16.safetensors
│   └── 📂 diffusion_models/
│       ├── hunyuanvideo1.5_720p_t2v_fp16.safetensors        // T2V model
│       ├── hunyuanvideo1.5_720p_i2v_fp16.safetensors        // I2V model
│       └── hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors  // Upscaler
```