Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
This node uses the Kling AI model to generate a video based on a text prompt and up to seven reference images. It allows you to control the video’s aspect ratio, duration, resolution, and optionally use storyboards or generate audio. The node sends the request to an external API and returns the generated video.

Inputs

ParameterData TypeRequiredRangeDescription
model_nameCOMBOYes"kling-v3-omni"
"kling-video-o1"
The specific Kling model to use for video generation (default: “kling-v3-omni”).
promptSTRINGYes-A text prompt describing the video content. This can include both positive and negative descriptions. The text is automatically normalized and must be between 1 and 2500 characters. Ignored when storyboards are enabled.
aspect_ratioCOMBOYes"16:9"
"9:16"
"1:1"
The desired aspect ratio for the generated video.
durationINTYes3 to 15The length of the video in seconds. The value can be adjusted with a slider (default: 5).
reference_imagesIMAGEYes-Up to 7 reference images. Each image must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1.
resolutionCOMBONo"4k"
"1080p"
"720p"
The output resolution of the video. This parameter is optional (default: “1080p”).
storyboardsDYNAMIC_COMBONo"disabled"
"1 storyboard"
"2 storyboards"
"3 storyboards"
"4 storyboards"
"5 storyboards"
"6 storyboards"
Generate a series of video segments with individual prompts and durations. Only supported for kling-v3-omni. When enabled, the global prompt is ignored, and the total duration of all storyboard segments must equal the global duration.
generate_audioBOOLEANNotrue
false
Generate audio for the video. Only supported for kling-v3-omni (default: false).
seedINTNo0 to 2147483647Seed controls whether the node should re-run; results are non-deterministic regardless of seed (default: 0).
Note: The reference_images input accepts a maximum of 7 images. If more are provided, the node will raise an error. Each image is validated for minimum dimensions and aspect ratio. Model-specific constraints:
  • kling-video-o1 does not support durations greater than 10 seconds.
  • kling-video-o1 does not support audio generation.
  • kling-video-o1 does not support 4k resolution.
  • kling-video-o1 does not support storyboards.

Outputs

Output NameData TypeDescription
outputVIDEOThe generated video file.

Source fingerprint (SHA-256): e1fe0433a604fbc071fdd426121a1f4ff10bb0aa6d3eb2d702306b7206dae4c0