KlingVideoNode - ComfyUI Built-in Node Documentation

This node generates videos using the Kling V3 model. It supports text-to-video mode, where a video is created from a text description, and image-to-video mode, where an existing image is animated. It also offers advanced features like creating multi-segment videos with individual prompts for each part (storyboards) and optionally generating accompanying audio.

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
`multi_shot`	Generate a series of video segments with individual prompts and durations. When set to a storyboard option, additional inputs for each storyboard’s prompt and duration appear.	DYNAMIC_COMBO	Yes	`"disabled"` `"1 storyboard"` `"2 storyboards"` `"3 storyboards"` `"4 storyboards"` `"5 storyboards"` `"6 storyboards"`
`model`	Model and generation settings. Selecting a model reveals its resolution and aspect ratio sub-parameters.	DYNAMIC_COMBO	Yes	`"kling-v3"` `"kling-3.0-turbo"`
`generate_audio`	When enabled, the node generates audio for the video. Note: `"kling-3.0-turbo"` always generates native audio, so this toggle is ignored for that model. Default is True.	BOOLEAN	Yes	True False
`seed`	Seed controls whether the node should re-run; results are non-deterministic regardless of seed. Default is 0.	INT	Yes	0 to 2147483647
`start_frame`	Optional start frame image. When connected, switches to image-to-video mode.	IMAGE	No	-

kling-v3 Inputs

Parameter	Description	Data Type	Required	Range
`model.resolution`	The resolution for the generated video. Default is `"1080p"`.	COMBO	Yes	`"4k"` `"1080p"` `"720p"`
`model.aspect_ratio`	The aspect ratio for the generated video. Ignored in image-to-video mode.	COMBO	Yes	`"16:9"` `"9:16"` `"1:1"`

kling-3.0-turbo Inputs

Parameter	Description	Data Type	Required	Range
`model.resolution`	The resolution for the generated video. Default is `"720p"`.	COMBO	Yes	`"1080p"` `"720p"`
`model.aspect_ratio`	The aspect ratio for the generated video. Ignored in image-to-video mode.	COMBO	Yes	`"16:9"` `"9:16"` `"1:1"`

Multi-shot Inputs

When multi_shot is set to "disabled":

Parameter	Description	Data Type	Required	Range
`prompt`	The main text description for the video. Must be between 1 and 2500 characters.	STRING	Yes	1 to 2500 characters
`negative_prompt`	Text describing what should not appear in the video. Can be left empty.	STRING	No	-
`duration`	The length of the video in seconds. Default is 5.	INT	Yes	3 to 15

When multi_shot is set to a storyboard option (e.g., "3 storyboards"): For each storyboard segment N (from 1 up to the selected storyboard count), the following inputs appear:

Parameter	Description	Data Type	Required	Range
`storyboard_N_prompt`	Prompt for storyboard segment N. Max 512 characters.	STRING	Yes	1 to 512 characters
`storyboard_N_duration`	Duration for storyboard segment N in seconds. Default is 4.	INT	Yes	1 to 15

Constraints and behavior:

Text-to-video mode is used when start_frame is not connected; image-to-video mode is used when start_frame is connected. In image-to-video mode, model.aspect_ratio is ignored and the input image must be at least 300x300 pixels with an aspect ratio between 1:2.5 and 2.5:1.
In storyboard mode, the main prompt and negative_prompt are not used. The total sum of all storyboard durations must be between 3 and 15 seconds.
negative_prompt is only used with kling-v3; it is ignored when kling-3.0-turbo is selected.
For kling-v3, each storyboard is sent to the API as a separate segment. For kling-3.0-turbo, the storyboard prompts and durations are combined into a single multi-shot prompt.
For kling-3.0-turbo, generate_audio is ignored because this model always generates native audio.

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): 2863d7a971a1978b6009e5321ed2112a9c04809281acd5f65d85ab72c4b49f08

​Inputs

​Common Inputs

​kling-v3 Inputs

​kling-3.0-turbo Inputs

​Multi-shot Inputs

​Outputs