Unlock the Power of Image-to-Video: HunyuanVideo I2V Now Available in ComfyUI

We're excited to announce that HunyuanVideo now supports Image-to-Video with native integration in ComfyUI! Building on our previous Text-to-Video implementation, this powerful new feature allows you to transform still images into fluid, high-quality videos.

Now this 13B model is available on your local GPUs.

Highlights of HunyuanVideo I2V

HunyuanVideo I2V extends the capabilities of 13B open-source video foundation model by adding image conditioning support.

The new modal maintains the success of quality comparable to or exceeding top closed-source models, bridging the gap between industry capabilities and publicly available resources.

Lora training: Hunyuan also released the LoRA training code for customizable special effects, which can be used to create more interesting video effects.

Getting Started with HunyuanVideo I2V in ComfyUI

1. Update ComfyUI or ComfyUI Desktop to the latest version

2. Download the example workflow: Click the button, download the image and drag into ComfyUI. (The workflow will guide you to download the required models to the right folders)

   Hunyuan I2V Workflow

Tip: Select a fp8 weight_dtype in “Load Diffusion Model” node if you are running out of memory.

Here are some of the examples:

Check our documentation page for other setting instructions: https://docs.comfy.org/advanced/hunyuan-video

Enjoy creating with HunyuanVideo I2V in ComfyUI!