Skip to main content
This node uses the Kling AI model to generate a new video based on an input video and optional reference images. You provide a text prompt describing the desired content, and the node transforms the reference video accordingly. It can also incorporate up to four additional reference images to guide the style and content of the output.

Inputs

ParameterDescriptionData TypeRequiredRange
model_nameThe specific Kling model to use for video generation (default: “kling-v3-omni”).COMBOYes"kling-v3-omni"
"kling-video-o1"
promptA text prompt describing the video content. This can include both positive and negative descriptions.STRINGYesN/A
aspect_ratioThe desired aspect ratio for the generated video.COMBOYes"16:9"
"9:16"
"1:1"
durationThe length of the generated video in seconds (default: 3).INTYes3 to 10
reference_videoVideo to use as a reference.VIDEOYesN/A
keep_original_soundDetermines if the audio from the reference video is kept in the output (default: True).BOOLEANYesN/A
reference_imagesUp to 4 additional reference images.IMAGENoN/A
resolutionThe resolution for the generated video (default: “1080p”).COMBONo"1080p"
"720p"
seedSeed controls whether the node should re-run; results are non-deterministic regardless of seed (default: 0).INTNo0 to 2147483647
Parameter Constraints:
  • The prompt must be between 1 and 2500 characters long.
  • The reference_video must be between 3.0 and 10.05 seconds in duration.
  • The reference_video must have dimensions between 720x720 and 2160x2160 pixels.
  • A maximum of 4 reference_images can be provided. Each image must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1.

Outputs

Output NameDescriptionData Type
outputThe newly generated video.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): aa99b865ca96ec5c2d5535d3392e8dc94dd5e56ebf624f8fdff09302767ab300