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
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

ParameterData TypeRequiredRangeDescription
start_frameIMAGEYes-The 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.
promptSTRINGYes-Positive text prompt. Maximum 500 characters.
negative_promptSTRINGYes-Negative text prompt. Maximum 500 characters.
model_nameCOMBOYes"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"
The model used for video generation (default: "kling-v2-master").
cfg_scaleFLOATYes0.0 to 1.0Controls how closely the video follows the prompt. Higher values mean stronger adherence (default: 0.8).
modeCOMBOYes"std"
"pro"
The 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".
aspect_ratioCOMBOYes"16:9"
"9:16"
"1:1"
The aspect ratio of the generated video (default: "16:9").
durationCOMBOYes"5"
"10"
The duration of the generated video in seconds (default: "5").

Outputs

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

Source fingerprint (SHA-256): 2845117c840372d457c58bfb8da077ccac32a9398e5679120104d8ee597d4855