Skip to main content
This node generates a video featuring a person or object from reference images using the HappyHorse model. It supports creating videos with single-character performances and multi-character interactions.

Inputs

ParameterDescriptionData TypeRequiredRange
modelThe HappyHorse model to use for video generation.COMBOYes"happyhorse-1.0-r2v"
promptPrompt describing the video. Use identifiers such as ‘character1’ and ‘character2’ to refer to the reference characters.STRINGYesN/A
resolutionThe resolution of the generated video.COMBOYes"720P"
"1080P"
ratioThe aspect ratio of the generated video.COMBOYes"16:9"
"9:16"
"1:1"
"4:3"
"3:4"
durationThe duration of the generated video in seconds (default: 5).INTYes3 to 15
reference_imagesOne or more reference images of the person or object to feature in the video. At least one image must be provided.IMAGEYes1 to 9
seedSeed to use for generation (default: 0). Can be set to automatically change after each generation.INTNo0 to 2147483647
watermarkWhether to add an AI-generated watermark to the result (default: False).BOOLEANNoTrue or False

Outputs

Output NameDescriptionData Type
VIDEOThe generated video file.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): 61e22c2424191b59b3c6f6be1917e47d26436eba5360c1e173b59b4de40216f2