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

Edit a video using text instructions or reference images with the HappyHorse model. The output duration is 3-15 seconds and matches the input video; inputs longer than 15 seconds are truncated.

Inputs

ParameterData TypeRequiredRangeDescription
modelDICTYesSee belowModel configuration containing the model selection, prompt, resolution, aspect ratio, and optional reference images.
videoVIDEOYes-The video to edit.
seedINTYes0 to 2147483647Seed to use for generation (default: 0).
watermarkBOOLEANNoTrue / FalseWhether to add an AI-generated watermark to the result (default: False).

model Parameter Details

The model parameter is a dictionary with the following fields:
FieldData TypeRequiredRangeDescription
modelSTRINGYes"happyhorse-1.0-video-edit"The HappyHorse video editing model to use.
promptSTRINGYes-Editing instructions or style transfer requirements. Must be at least 1 character long.
resolutionSTRINGYes"720P"
"1080P"
The output resolution.
ratioSTRINGYes"16:9"
"9:16"
"1:1"
"4:3"
"3:4"
Aspect ratio. If not changed, approximates the input video ratio.
reference_imagesDICTNo0 to 5 imagesOptional reference images (image1, image2, image3, image4, image5) to guide the edit.

Outputs

Output NameData TypeDescription
videoVIDEOThe edited video output.

Source fingerprint (SHA-256): eadb446a8dbcc524a8bb6a2ee48941136f8c1ec2cb64aa9061fb1fa22e1b683d