KlingCameraControlI2VNode - ComfyUI Built-in Node Documentation

Complete documentation for the KlingCameraControlI2VNode node in ComfyUI. Learn its inputs, outputs, parameters and usage.

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 Camera Control Node transforms still images into cinematic videos with professional camera movements. This specialized image-to-video node allows you to control virtual camera actions including zoom, rotation, pan, tilt, and first-person view while maintaining focus on your original image. Camera control is currently only supported in pro mode with the kling-v1-5 model at 5-second duration.

Inputs

Parameter	Data Type	Required	Range	Description
start_frame	IMAGE	Yes	-	Reference Image - URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300x300px, aspect ratio between 1:2.5 and 2.5:1. Base64 should not include data:image prefix.
prompt	STRING	Yes	-	Positive text prompt describing the desired video content. Maximum length is 500 characters.
negative_prompt	STRING	Yes	-	Negative text prompt describing what to avoid in the generated video. Maximum length is 500 characters.
cfg_scale	FLOAT	No	0.0 to 1.0	Controls the strength of text guidance. Higher values make the output more closely follow the prompt (default: 0.75)
aspect_ratio	COMBO	No	"16:9" "9:16" "1:1"	The aspect ratio of the generated video (default: “16:9”)
camera_control	CAMERA_CONTROL	Yes	-	Can be created using the Kling Camera Controls node. Controls the camera movement and motion during the video generation.

Outputs

Output Name	Data Type	Description
output	VIDEO	The generated video output
video_id	STRING	Unique identifier for the generated video
duration	STRING	Duration of the generated video

---

Source fingerprint (SHA-256): c7c0ef732a97d60b03c6942a9f026a23982ea5d86746520772cc6bf2f450865c