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

Inputs

ParameterDescriptionData TypeRequiredRange
modelModel configuration containing the model selection, prompt, resolution, aspect ratio, and optional reference images.DICTYesSee below
videoThe video to edit.VIDEOYes-
seedSeed to use for generation (default: 0).INTYes0 to 2147483647
watermarkWhether to add an AI-generated watermark to the result (default: False).BOOLEANNoTrue
False

model Parameter Details

The model parameter is a dictionary with the following fields:
FieldDescriptionData TypeRequiredRange
modelThe HappyHorse video editing model to use.STRINGYes"happyhorse-1.0-video-edit"
promptEditing instructions or style transfer requirements. Must be at least 1 character long.STRINGYes-
resolutionThe output resolution.STRINGYes"720P"
"1080P"
ratioAspect ratio. If not changed, approximates the input video ratio.STRINGYes"16:9"
"9:16"
"1:1"
"4:3"
"3:4"
reference_imagesOptional reference images (image1, image2, image3, image4, image5) to guide the edit.DICTNo0 to 5 images

Outputs

Output NameDescriptionData Type
videoThe edited video output.VIDEO
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 396cad4b5a06d457746a421050df98c892fa9db6019e3de983b4d0c417842b57