KlingStartEndFrameNode - ComfyUI Built-in Node Documentation

This node creates a video sequence that transitions between your provided start and end images. It generates all the frames in between to produce a smooth transformation from the first frame to the last frame. This node calls the image-to-video API but only supports the input options that work with the image_tail request field.

Inputs

Parameter	Description	Data Type	Required	Range
`start_frame`	Reference Image - URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300*300px, aspect ratio between 1:2.5 ~ 2.5:1. Base64 should not include data:image prefix.	IMAGE	Yes	-
`end_frame`	Reference Image - End frame control. URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300*300px. Base64 should not include data:image prefix.	IMAGE	Yes	-
`prompt`	Positive text prompt. Must not be empty and cannot exceed 500 characters.	STRING	Yes	-
`negative_prompt`	Negative text prompt. Cannot exceed 500 characters. If left empty, it is omitted from the request.	STRING	Yes	-
`cfg_scale`	Controls the strength of the prompt guidance (default: 0.5)	FLOAT	Yes	0.0-1.0
`aspect_ratio`	The aspect ratio for the generated video (default: “16:9”)	COMBO	Yes	”16:9" "9:16" "1:1”
`mode`	The configuration to use for the video generation following the format: mode / duration / model_name. (default: “pro mode / 5s duration / kling-v2-5-turbo”)	COMBO	Yes	”pro mode / 5s duration / kling-v2-5-turbo" "pro mode / 10s duration / kling-v2-5-turbo”

Image Constraints:

Both start_frame and end_frame are required and cannot exceed 10MB in file size.
Minimum resolution: 300×300 pixels for both images.
start_frame aspect ratio must be between 1:2.5 and 2.5:1.
Base64 encoded images should not include the “data:image” prefix.

Prompt Constraints:

prompt must not be empty and cannot exceed 500 characters.
negative_prompt cannot exceed 500 characters; when empty, it is not sent with the request.

Mode Notes:

Both mode options use pro mode with the kling-v2-5-turbo model and differ only in duration (5 seconds or 10 seconds).
Pricing per generation, as shown in the node’s price badge: 5s mode costs $0.35 USD and 10s mode costs$ 0.70 USD.

Outputs

Output Name	Description	Data Type
`output`	The generated video sequence	VIDEO
`video_id`	Unique identifier for the generated video	STRING
`duration`	Duration of 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): a27977226360a425614255f8330ce7fd8ba94b8c3020eb8fdddc01eb74f035c1

​Inputs

​Outputs

Inputs

Outputs