HappyHorseReferenceVideoApi - ComfyUI Built-in Node Documentation - ComfyUI

This node generates a video featuring a person or object from reference images using the HappyHorse model. It supports single-character performances and multi-character interactions. The reference images are uploaded and used to represent the characters in the generated video.

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
`model`	The HappyHorse reference-to-video model to use for generation.	DYNAMIC_COMBO	Yes	`"happyhorse-1.1-r2v"` `"happyhorse-1.0-r2v"`
`seed`	Seed to use for generation (default: 0). Can be set to automatically change after each generation.	INT	Yes	0 to 2147483647
`watermark`	Whether to add an AI-generated watermark to the result (default: False).	BOOLEAN	Yes	True or False

HappyHorse 1.1 Inputs (happyhorse-1.1-r2v)

Parameter	Description	Data Type	Required	Range
`prompt`	Prompt describing the video. Use identifiers such as ‘character1’ and ‘character2’ to refer to the reference characters.	STRING	Yes	N/A
`resolution`	The resolution of the generated video.	COMBO	Yes	`"720P"` `"1080P"`
`ratio`	The aspect ratio of the generated video.	COMBO	Yes	`"16:9"` `"9:16"` `"1:1"` `"4:3"` `"3:4"` `"21:9"` `"9:21"` `"5:4"` `"4:5"`
`duration`	The duration of the generated video in seconds (default: 5).	INT	Yes	3 to 15

HappyHorse 1.0 Inputs (happyhorse-1.0-r2v)

Parameter	Description	Data Type	Required	Range
`prompt`	Prompt describing the video. Use identifiers such as ‘character1’ and ‘character2’ to refer to the reference characters.	STRING	Yes	N/A
`resolution`	The resolution of the generated video.	COMBO	Yes	`"720P"` `"1080P"`
`ratio`	The aspect ratio of the generated video.	COMBO	Yes	`"16:9"` `"9:16"` `"1:1"` `"4:3"` `"3:4"`
`duration`	The duration of the generated video in seconds (default: 5).	INT	Yes	3 to 15

Reference Inputs

Parameter	Description	Data Type	Required	Range
`reference_images`	Growable slot: connect 1 to 9 reference images of the person or object to feature in the video. At least one reference image must be provided.	IMAGE	Yes	1 to 9 (per model)

Note: At least one reference image must be provided, otherwise the node raises an error. Each reference image must be at least 400 x 400 pixels and have an aspect ratio between 1:2.5 and 2.5:1. The prompt must not be empty.

Outputs

Output Name	Description	Data Type
`VIDEO`	The 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): 252c918afc4cf38be9c7d09b7112075b9adb23490ec9fed1717a8548519d2554