Skip to main content
The Kling Image to Video Node generates a video from a starting reference image using text prompts. It takes an image as the first frame and creates a video sequence based on positive and negative text descriptions, with configurable options for model, duration, aspect ratio, and generation mode.

Inputs

ParameterDescriptionData TypeRequiredRange
start_frameThe reference image used to generate the video. The image must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1.IMAGEYes-
promptPositive text prompt. Maximum 500 characters.STRINGYes-
negative_promptNegative text prompt. Maximum 500 characters.STRINGYes-
model_nameThe model used for video generation (default: "kling-v2-master").COMBOYes"kling-v2-master"
"kling-v2-1-master"
"kling-v2-5-turbo"
"kling-v2-1"
"kling-v1-6"
"kling-v1-5"
"kling-v1-4"
"kling-v1-0"
cfg_scaleControls how closely the video follows the prompt. Higher values mean stronger adherence (default: 0.8).FLOATYes0.0 to 1.0
modeThe generation mode. "std" is standard quality, "pro" is higher quality (default: "std"). Note: When using the kling-v2-5-turbo model, "std" mode is not supported and will be automatically switched to "pro".COMBOYes"std"
"pro"
aspect_ratioThe aspect ratio of the generated video (default: "16:9").COMBOYes"16:9"
"9:16"
"1:1"
durationThe duration of the generated video in seconds (default: "5").COMBOYes"5"
"10"

Outputs

Output NameDescriptionData Type
outputThe generated video output.VIDEO
video_idUnique identifier for the generated video.STRING
durationDuration information for the generated video.STRING
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): 2845117c840372d457c58bfb8da077ccac32a9398e5679120104d8ee597d4855