HeyGenReferenceToVideoNode - ComfyUI Built-in Node Documentation

Generate a video with synchronized dialogue and sound from a text prompt using HeyGen Video 1.0, optionally guided by connected reference material. Images of people, products or places, videos to reuse and audio clips that provide a voice can all be used as references. Mention each reference in the prompt as @Image1, @Video1 or @Audio1, numbered per type in the order the inputs are connected: these tags are rewritten into the labels HeyGen expects, and a tag that points to a reference which is not connected raises an error. Without any reference image or video the node runs as text-to-video generation.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	Model version used for generation. (default: `"heygen-video-1"`)	DYNAMIC_COMBO	Yes	`"heygen-video-1"`
`prompt`	Description of the video, including any dialogue. Refer to connected references as @Image1, @Video1, @Audio1, numbered per type in input order. (default: empty string)	STRING	Yes	1 to 32000 characters
`duration`	Duration of the output video in seconds. (default: 5)	INT	Yes	5 to 15
`resolution`	Output resolution. 2k requires the 16:9 or 9:16 aspect ratio; ‘auto’ works at 2k only without references. (default: `"768p"`)	COMBO	Yes	`"768p"` `"480p"` `"2k"`
`aspect_ratio`	Output aspect ratio. `"auto"` is 16:9 when no references are connected, otherwise it follows the first reference image, or the first reference video when no images are connected. (default: `"auto"`)	COMBO	Yes	`"auto"` `"16:9"` `"9:16"` `"1:1"` `"4:3"` `"3:4"` `"21:9"`
`seed`	Seed for the generation. Results can still vary between runs with the same seed. (default: 42)	INT	Yes	0 to 4294967295
`reference_images`	Growable slot: images of people, products or places to use in the video (`image_1` … `image_9`); refer to them as @Image1, @Image2, … Each input must contain exactly one image, and each image must have an aspect ratio between 1:4 and 4:1.	IMAGE	No	0 to 9 images
`reference_videos`	Growable slot: videos to use as references (`video_1` … `video_3`); refer to them as @Video1, @Video2, …	VIDEO	No	0 to 3 videos
`reference_audios`	Growable slot: audio clips such as a voice for a speaker (`audio_1` … `audio_3`); refer to them as @Audio1, @Audio2, … Requires at least one reference image or video. A voice reference needs a few seconds of clean speech, and clips shorter than about 2 seconds are usually ignored.	AUDIO	No	0 to 3 audio clips

Parameter Constraints

Reference limit: at most 12 references in total across reference_images, reference_videos and reference_audios; connecting more raises an error.
Audio needs image or video: reference audio is rejected when no reference image and no reference video is connected.
Reference image rules: each reference_images input must hold exactly one image (a batch is rejected), and each image must be between 1:4 and 4:1 in aspect ratio.
Prompt tags: @ImageN, @VideoN and @AudioN are matched case-insensitively. The number must not exceed the count of connected references of that type, and the prompt must be non-empty after trimming whitespace.
Mode: with at least one reference image or video the request is a reference-to-video run; with none it is a plain text-to-video run.
2k resolution: resolution "2k" requires aspect_ratio "16:9" or "9:16"; "auto" is accepted at 2k only when no reference image and no reference video are connected.
Seed: the seed only decides whether the node re-runs; results are not reproducible with the same seed.

Outputs

Output Name	Description	Data Type
`VIDEO`	The generated video with synchronized dialogue and sound.	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): f3fae5dce59c90d65ad8eff2c992819f29a71e3a3e13fa91c1e7479a9cd6fcdc

​Inputs

​Parameter Constraints

​Outputs

Inputs

Parameter Constraints

Outputs