kling-3-0

Generate cinematic videos via RunComfy CLI using Standard, Pro, or 4K tiers and text/image inputs.

5|2|Updated May 18, 2026
One-click install
npx skills add https://github.com/doany-ai/skills --skill kling-3-0-doany-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kling-3-0
Source: https://github.com/doany-ai/skills/tree/main/kling-3-0
Command: npx skills add https://github.com/doany-ai/skills --skill kling-3-0-doany-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Kling 3.0 provides a scalable way to produce cinematic multi-shot videos with synchronized audio while preserving character identity across scenes, reducing manual video production time.

Core Features & Use Cases

  • Supports six endpoints across three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video).
  • Enables end-to-end video generation from prompts or source images with in-pass audio, multi-shot prompts, and identity preservation for branding, marketing, and storytelling.
  • Triggers and routing via runcomfy run kling/kling-3.0/<tier>/<mode> for predictable deployments in automated pipelines.

Quick Start

Use Kling 3.0 to generate a video by calling the RunComfy Kling endpoint with your desired tier, mode, and prompt.

Frequently Asked Questions about kling-3-0

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate cinematic videos with synchronized audio from text prompts?

You generate cinematic AI videos with synchronized audio from text prompts using Kling 3.0 on RunComfy, requiring the CLI, a login token, and your prompt to produce multi-shot sequences.

Can I use a source image to create a 4K video with character identity preservation?

Image-to-video generation supports character identity preservation by providing a publicly accessible image URL along with your prompt, allowing you to render output across Standard, Pro, and 4K tiers.

What are the duration limits for AI video generation using image-to-video or text-to-video?

AI video generation duration is limited to 3 to 15 seconds per clip, applicable to both text-to-video and image-to-video modes across all rendering tiers including Standard, Pro, and 4K.

Do I need the RunComfy CLI to automate multi-shot video generation in pipelines?

Automated multi-shot video generation requires the RunComfy CLI and login token to trigger endpoints via runcomfy run kling/kling-3.0/<tier>/<mode>, ensuring predictable deployments in your pipelines.

How does in-pass audio generation work for product showcase videos?

In-pass audio generation for product showcase videos is enabled via the optional generate_audio parameter, adding synchronized sound directly during the video generation process without separate post-production steps.