ByteDanceImageReferenceNode - ComfyUI Built-in Node Documentation

The ByteDance Image Reference Node generates videos using a text prompt and one to four reference images. It sends the images and prompt to an external API service that creates a video matching your description while incorporating the visual style and content from your reference images. The node provides various controls for video resolution, aspect ratio, duration, and other generation parameters.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The AI model to use for video generation (default: `"seedance-1-0-lite-i2v-250428"`).	STRING	Yes	`"seedance-1-0-pro-250528"` `"seedance-1-0-lite-i2v-250428"`
`prompt`	The text prompt used to generate the video.	STRING	Yes	-
`images`	One to four images. Each image must be between 300x300 and 6000x6000 pixels, with an aspect ratio between 0.4 and 2.5.	IMAGE	Yes	-
`resolution`	The resolution of the output video.	STRING	Yes	`"480p"` `"720p"`
`aspect_ratio`	The aspect ratio of the output video (default: `"adaptive"`).	STRING	Yes	`"adaptive"` `"16:9"` `"4:3"` `"1:1"` `"3:4"` `"9:16"` `"21:9"`
`duration`	The duration of the output video in seconds (default: 5).	INT	Yes	3 - 12
`seed`	Seed to use for generation (default: 0).	INT	No	0 - 2147483647
`watermark`	Whether to add an “AI generated” watermark to the video (default: False).	BOOLEAN	No	-

Note: The prompt text must not contain the following parameter strings: --resolution, --ratio, --duration, --seed, or --watermark. These values are controlled exclusively through their dedicated input widgets.

Outputs

Output Name	Description	Data Type
`output`	The generated video file based on the input prompt and reference images.	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): 77a0f9aee920d07a1374eaec8489eed494a4505369246c16007765d67e52ef99

​Inputs

​Outputs

Inputs

Outputs