Skip to content

ComfyUI-HunyuanVideoWrapper-IP2V

Use an image as a video generation condition

Visit official site

What ComfyUI-HunyuanVideoWrapper-IP2V is

The wrapper is described as a HunyuanVideo-based tool that generates video from image prompts, pulling the concept and style of an image into the generation process. It is stated to be experimental but usable.

What you can do with it

  • Generate video from a landscape image
  • Generate video from a product image
  • Extract style and concept from an image prompt

Getting started

  • Select the vision language model and set its type
  • Load an image with ComfyUI native nodes
  • Connect it to the encode node and add the image tag

Pros & cons

✓ What we like

  • The image contributes style and content beyond the first frame
  • ComfyUI native nodes handle image loading

! What to watch out for

  • The wrapper is described as being in an experimental stage
  • At least 20GB of VRAM is stated as required

FAQ

How is the image used?

The material states the image acts as a generation condition, not just the first frame.

How many images can be connected?

Up to two images can be connected to the Hunyuan TextImageEncode node.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review