Nodes/ComfyUI-Kling-Direct/Kling Text to Video
ComfyUI Node

Kling Text to Video

A ComfyUI node in Kling AI/Video with 11 inputs and 5 outputs.

By IxMxAMAR·Created 5 months ago·Updated about a month ago· 4
Kling Text to Video
  • auth
  • camera_control
  • video
  • video_file
  • audio
  • url
  • task_id
prompt
negative_prompt
model_namekling-v3
aspect_ratio16:9
duration5
modepro
soundtrue
cfg_scale0.50
shot_typenatural
CategoryKling AI/Video

Inputs (11)

NameTypeDefaultDescription
authKLING_AUTH
promptSTRINGText description of the video to generate. Supports @image1 and @video1 references.
negative_promptSTRINGThings to avoid in the generated video.
model_nameCOMBOkling-v3Kling model version. v3 is latest, v2-master for cinematic quality.
aspect_ratioCOMBO16:9Output video aspect ratio.
durationCOMBO5Video duration in seconds.
modeCOMBOproGeneration mode: 'pro' for higher quality, 'std' for faster/cheaper.
soundBOOLEANtrueEnable AI-generated sound effects and ambient audio.
cfg_scaleFLOAT0.500–1Classifier-free guidance scale. Higher = more prompt adherence, lower = more creative.
shot_typeCOMBOnaturalCamera shot framing style.
camera_controloptKLING_CAMERA

Outputs (5)

NameTypeDescription
videoIMAGE
video_fileSTRING
audioAUDIO
urlSTRING
task_idSTRING