Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Overview

This node generates a video featuring a person or object based on reference images using the HappyHorse model. It supports creating videos with a single character or multiple characters interacting with each other.

Inputs

ParameterData TypeRequiredRangeDescription
modelCOMBOYes"happyhorse-1.0-r2v"The HappyHorse model to use for video generation.
promptSTRINGYesN/AA text description of the video you want to generate. Use identifiers like ‘character1’ and ‘character2’ to refer to the reference characters.
resolutionCOMBOYes"720P"
"1080P"
The resolution of the generated video.
ratioCOMBOYes"16:9"
"9:16"
"1:1"
"4:3"
"3:4"
The aspect ratio of the generated video.
durationINTYes3 to 15The duration of the generated video in seconds (default: 5).
reference_imagesIMAGEYes1 to 9One or more reference images of the person or object to feature in the video. You must provide at least one image.
seedINTNo0 to 2147483647A seed value for reproducible generation (default: 0). The seed can be set to automatically change after each generation.
watermarkBOOLEANNoTrue or FalseWhether to add an AI-generated watermark to the resulting video (default: False).

Outputs

Output NameData TypeDescription
VIDEOVIDEOThe generated video file.

Source fingerprint (SHA-256): 42c844db22ed2284bd16bd28fe0060652248ada0d5d31003134768ed5e44356c