KlingImageGenerationNode - ComfyUI Built-in Node Documentation

Kling Image Generation Node generates images from text prompts with the option to use a reference image for guidance.

Kling Image Generation Node generates images from text prompts with the option to use a reference image for guidance. It creates one or more images based on your text description and reference settings, then returns the generated images as output.

Inputs

Parameter	Description	Data Type	Required	Range
prompt	Positive text prompt	STRING	Yes	Maximum 500 characters
negative_prompt	Negative text prompt	STRING	Yes	Maximum 500 characters
image_type	Image reference type selection (advanced). Required when a reference image is provided.	COMBO	Yes	"subject_reference" "style_reference"
image_fidelity	Reference intensity for user-uploaded images (default: 0.5, advanced)	FLOAT	Yes	0.0 - 1.0
human_fidelity	Subject reference similarity (default: 0.45, advanced)	FLOAT	Yes	0.0 - 1.0
model_name	Model selection for image generation (default: “kling-v3”)	COMBO	Yes	"kling-v3"
aspect_ratio	Aspect ratio for generated images (default: “16:9”)	COMBO	Yes	"16:9" "9:16" "1:1" "4:3" "3:4" "21:9" "9:21"
n	Number of generated images (default: 1)	INT	Yes	1 - 9
image	Optional reference image	IMAGE	No	-
seed	Seed controls whether the node should re-run; results are non-deterministic regardless of seed (default: 0)	INT	No	0 - 2147483647

Parameter Constraints:

• The image parameter is optional. When a reference image is provided, the image_type parameter determines whether the reference is used as a subject reference or a style reference.
• When no reference image is provided, the reference-related settings (image_type, image_fidelity, human_fidelity) have no effect on the result.
• prompt and negative_prompt have a maximum length of 500 characters.
• The seed parameter is optional and does not guarantee deterministic results.

Outputs

Output Name	Description	Data Type
output	Generated image(s) based on the input parameters. When n is greater than 1, multiple images are returned as a batch.	IMAGE

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): fd344519346f63ac03975b93f03725749ed9697245d6dfa2378884c59a5325cd