Back to Nodes
Kling V3 Video

Kling V3 Video

Official

Generate cinematic Kling V3 videos from text with optional start/end frames, multi-shot JSON control, and native audio toggle.

Nodespell AI
AI / Video / Kwaivgi

Generate cinematic Kling V3 videos from text with optional start/end frames, multi-shot JSON control, and native audio toggle.

Model Overview

Kling V3 Video is a text-to-video model with optional image framing controls. It supports standard/pro modes, shot sequencing via multi-shot JSON, and optional native audio generation.

Best At

  • Prompt-driven short cinematic clip generation.
  • Controlled framing with optional first/last frame images.
  • Multi-shot scene sequencing in one generation run.

Limitations / Not Good At

  • Complex multi-shot JSON can require validation and retries.
  • Start/end frame constraints can limit aspect ratio flexibility.
  • Detailed scene choreography may still need iterative prompting.

Ideal Use Cases

  • Storyboard and campaign concept video generation.
  • Fast creative branching with optional audio-enabled previews.
  • Controlled text-to-video drafts with guided framing.

Input & Output Format

  • Input: required prompt; optional start_image, end_image, mode, aspect_ratio, duration, generate_audio, negative_prompt, and multi_prompt.
  • Output: generated video URI returned on response.

Performance Notes

  • pro mode targets higher quality and higher cost than standard.
  • Multi-shot JSON should keep shot durations aligned with total duration.
Inputs (4)

Prompt

String

Text prompt describing scene, style, camera, and motion.

RequiredMulti InputMin: 0Max: 100

Multi-Shot Prompt (JSON)

String

Optional JSON shot array, for example [{"prompt":"...", "duration":3}].

Min: 0Max: 100

Start Image

String

Optional first frame reference image.

Min: 0Max: 100

End Image

String

Optional last frame reference image. Requires a start image.

Min: 0Max: 100
Parameters (7)

Prompt

String

Text prompt describing scene, style, camera, and motion.

Required
Default:

Mode

String

Generation quality mode.

Default: pro

Aspect Ratio

String

Aspect ratio for generation when start image is not provided.

Default: 16:9

Duration

Number

Target video duration in seconds.

Default: 5

Generate Audio

Boolean

Generate native audio with the video output.

Default: false

Negative Prompt

String

Describe elements you want to avoid in the output.

Default:

Multi-Shot Prompt (JSON)

String

Optional JSON shot array, for example [{"prompt":"...", "duration":3}].

Default:
Outputs (1)

Output

Inferred

Output

Nodespell Team

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Video / Kwaivgi

Input

TextImage

Output

Video

Keywords

Video GenerationPrompt ConditioningAspect ControlLength ControlResolution Control
Use in Workflow