Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The Kling Image to Video Node generates video content from a starting image using text prompts. It takes a reference image and creates a video sequence based on the provided positive and negative text descriptions, with various configuration options for model selection, duration, and aspect ratio.

Inputs

ParameterData TypeRequiredRangeDescription
start_frameIMAGEYes-The reference image used to generate the video.
promptSTRINGYes-Positive text prompt.
negative_promptSTRINGYes-Negative text prompt.
model_nameCOMBOYesMultiple options availableModel selection for video generation (default: “kling-v2-master”).
cfg_scaleFLOATYes0.0-1.0Configuration scale parameter (default: 0.8).
modeCOMBOYesMultiple options availableVideo generation mode selection (default: std).
aspect_ratioCOMBOYesMultiple options availableAspect ratio for the generated video (default: field_16_9).
durationCOMBOYesMultiple options availableDuration of the generated video (default: field_5).

Outputs

Output NameData TypeDescription
outputVIDEOThe generated video output.
video_idSTRINGUnique identifier for the generated video.
durationSTRINGDuration information for the generated video.