ComfyUI > Nodes > ComfyUI > Wan Reference to Video

ComfyUI Node: Wan Reference to Video

Class Name

WanReferenceVideoApi

Category
api node/video/Wan
Author
ComfyAnonymous (Account age: 763days)
Extension
ComfyUI
Latest Updated
2026-05-13
Github Stars
112.77K

How to Install ComfyUI

Install this extension via the ComfyUI Manager by searching for ComfyUI
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Wan Reference to Video Description

Generate new videos using existing character and voice data with user prompts for consistent content creation.

Wan Reference to Video:

The WanReferenceVideoApi node is designed to generate new videos by leveraging existing character and voice data from input videos, combined with a user-defined prompt. This node is particularly useful for maintaining character consistency across different video outputs, ensuring that the generated content aligns closely with the reference materials provided. By utilizing this node, you can create videos that not only preserve the visual and auditory characteristics of the original content but also incorporate new narrative elements as specified in the prompt. This capability is especially beneficial for projects that require a seamless integration of new ideas with established character traits, making it a powerful tool for creative video production.

Wan Reference to Video Input Parameters:

reference_videos

This parameter accepts a list of video files that serve as the reference material for generating the new video. Each video in the list is validated to ensure it meets the required duration constraints, with a minimum duration of 2 seconds and a maximum of 30 seconds. The reference videos are crucial as they provide the character and voice data that the node uses to maintain consistency in the generated output.

prompt

The prompt is a textual input that guides the narrative or thematic direction of the generated video. It allows you to specify the storyline or context you wish to incorporate into the video, ensuring that the output aligns with your creative vision.

negative_prompt

This parameter allows you to specify elements or themes that should be avoided in the generated video. By providing a negative prompt, you can steer the video generation process away from unwanted content, ensuring that the final output remains true to your intended narrative.

size

The size parameter defines the resolution of the generated video, specified in the format width*height. This allows you to control the visual quality and aspect ratio of the output, ensuring it meets your project requirements.

duration

This parameter sets the length of the generated video in seconds. It allows you to define how long the final video should be, providing control over the pacing and completeness of the narrative.

shot_type

The shot_type parameter influences the style or composition of the video shots. It allows you to specify the type of shots you want in the video, such as close-ups or wide angles, enhancing the visual storytelling.

watermark

This boolean parameter determines whether a watermark should be included in the generated video. It provides an option to protect your content by adding a visible mark that identifies the video as your creation.

seed

The seed parameter is used to initialize the random number generator for the video synthesis process. By setting a specific seed value, you can ensure that the video generation process is repeatable, producing the same output for the same input parameters.

Wan Reference to Video Output Parameters:

output_video

The output_video parameter represents the final video generated by the node. This video incorporates the character and voice data from the reference videos, along with the narrative elements specified in the prompt. The output is a cohesive video that maintains character consistency while introducing new thematic content.

Wan Reference to Video Usage Tips:

  • Ensure that your reference videos are clear and of good quality to achieve the best results in character consistency.
  • Use a well-defined prompt to guide the video generation process effectively, ensuring that the output aligns with your creative vision.
  • Experiment with different seed values to explore variations in the generated video while maintaining the same input parameters.

Wan Reference to Video Common Errors and Solutions:

An unknown error occurred: <code> - <message>

  • Explanation: This error indicates that the video generation process encountered an unexpected issue, which could be due to invalid input parameters or a problem with the API service.
  • Solution: Verify that all input parameters are correctly specified and within the allowed ranges. Ensure that the reference videos meet the duration requirements and that the API service is operational. If the problem persists, consider reaching out to support for further assistance.

Wan Reference to Video Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Wan Reference to Video