Back to Nodes
Kling O1

Kling O1

Official

Instruction-driven Kling model for transforming existing video content or generating new clips with optional multimodal references.

Nodespell AI
AI / Video / Kwaivgi

Instruction-driven Kling model for transforming existing video content or generating new clips with optional multimodal references.

Model Overview

Kling O1 focuses on natural-language video transformation and controlled generation. It can operate with prompt-only generation, image guidance, or reference-video workflows.

Best At

  • Rewriting scene style and content from natural-language instructions.
  • Video variation workflows with optional reference images and video.
  • Maintaining motion continuity while changing visual context.

Limitations / Not Good At

  • Strong edits can drift from original composition intent.
  • Reference-heavy runs require careful prompt and asset alignment.
  • Results can vary when prompts are underspecified.

Ideal Use Cases

  • Iterative video editing with text-driven direction.
  • Creative adaptation of existing clips into new visual styles.
  • Prompt-led generation workflows with optional reference assets.

Input & Output Format

  • Input: required prompt; optional start_image, end_image, reference_images, reference_video, mode, video_reference_type, aspect_ratio, duration, and keep_original_sound.
  • Output: generated video URI returned on response.

Performance Notes

  • mode changes quality/cost behavior (std vs pro).
  • Video-reference usage can improve continuity for edit-style tasks.
Inputs (5)

Prompt

String

Text instructions describing desired visual transformation or generation.

RequiredMulti InputMin: 0Max: 100

Start Image

String

Optional first frame reference image.

Min: 0Max: 100

End Image

String

Optional final frame reference image. Requires start image.

Min: 0Max: 100

Reference Images

String

Optional one-to-many image references for scene, style, or subject guidance.

Multi InputMin: 0Max: 100

Reference Video

String

Optional reference video for style/camera guidance or base-video editing.

Min: 0Max: 100
Parameters (6)

Prompt

String

Text instructions describing desired visual transformation or generation.

Required
Default:

Mode

String

Generation quality mode.

Default: pro

Video Reference Type

String

Controls whether reference video is used as guidance or as base footage for editing.

Default: feature

Aspect Ratio

String

Output aspect ratio when reference framing does not override it.

Default: 16:9

Duration

Number

Target output duration in seconds.

Default: 5

Keep Original Sound

Boolean

Keep original audio from reference video when available.

Default: true
Outputs (1)

Output

Inferred

Output

Nodespell Team

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Video / Kwaivgi

Input

TextImageVideo

Output

Video

Keywords

Video EditVideo GenerationMultimodal GenerationPrompt ConditioningStyle ControlLength Control
Use in Workflow