kling-3-0
🎯Skillfrom doany-ai/skills
|A Claude Code skill for generating video with Kuaishou Kling 3.0 on RunComfy, covering all six endpoints across three quality tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video) with native synchronized audio and character consistency.
Overview
Kling 3.0 is a Claude Code skill for generating cinematic video with Kuaishou Technology's third-generation video model on RunComfy. It covers all six Kling 3.0 rendering endpoints, spanning three quality tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video). Kling 3.0 produces multi-shot video with synchronized native audio, consistent character identity across shots, and physics-aware motion, with support for clips up to 15 seconds and native 4K output on the 4K tier.
Key Features
- Three quality tiers: Standard (cheapest, up to 1080p for fast iteration and social shorts), Pro (highest fidelity at 1080p for hero-quality clips), and 4K (native 3840x2160 for brand films and big-screen sequences)
- Dual input modes: Text-to-video generates from text prompts, while image-to-video animates a reference image into motion, both available across all three quality tiers
- Native synchronized audio: Generates dialogue, ambient sounds, and music in-pass, with optional audio generation that adds a per-second surcharge
- Multi-prompt segment system: A unified system that allows one generation to contain several distinct scenes with controlled transitions, enabling multi-shot narratives in a single call
- Physics-aware motion and character consistency: Maintains realistic motion physics and consistent character identity (face, wardrobe, build) across shots
Who is this for?
- Film and video production teams creating cinematic sequences, brand films, and big-screen content that requires up to native 4K resolution with synchronized audio
- Social media and advertising teams producing short-form video ads and social content across quality tiers, from rapid Standard-tier iteration to polished Pro-tier finals
- Creative directors and storyboard artists prototyping multi-shot narratives with consistent characters using the multi-prompt segment system
Same repository
doany-ai/skills(29 items)
Installation
npx vibeindex add doany-ai/skills --skill kling-3-0npx skills add doany-ai/skills --skill kling-3-0~/.claude/skills/kling-3-0/SKILL.mdSKILL.md
More from this repository10
A Claude Code skill for image outpainting on RunComfy that extends images beyond their original canvas, supporting aspect ratio changes, uncropping, and canvas expansion by routing across Nano Banana 2 Edit, GPT Image 2 Edit, and FLUX Kontext Pro.
A Claude Code skill for generating and editing images with OpenAI GPT Image 2 (ChatGPT Images 2.0) hosted on RunComfy, with strengths in embedded text, logos, multilingual typography, and precise multi-element prompt following.
A Claude Code skill that acts as a smart router for image editing on RunComfy, automatically selecting the best model (Nano Banana Edit, GPT Image 2 Edit, Flux Kontext Pro, or Z-Image Turbo Inpaint) based on the user's intent.
A Claude Code skill for generating images with Google Nano Banana 2, a Gemini-family flash-tier text-to-image model hosted on RunComfy, optimized for rapid iteration, social thumbnails, and in-image typography rendering.
A Claude Code skill for generating cinematic short-form video with ByteDance Seedance 2.0 Pro via RunComfy, supporting multi-modal references (images, videos, audio) with native lip-synced audio and cinematic motion refinement.
Edit images with Google Nano Banana 2 on RunComfy — preserve subject identity, swap backgrounds, localize edits with spatial language, and perform batch edits on up to 20 images in a single call. Best for identity-preserving edits and consistent multi-image processing.
A unified CLI for the RunComfy Model API that provides one binary and one authentication to access hundreds of model endpoints including image generation, video generation, lip-sync, face swap, inpainting, outpainting, ControlNet, relighting, upscaling, and LoRA training.
Generate images with Flux 2 Klein, Black Forest Labs' distilled fast variant of Flux 2, on RunComfy. Optimized for sub-second latency and rapid creative iteration with multi-reference brand styling and declarative prompts, available in 9B and 4B variants.
A Claude Code skill for generating text-to-video with HappyHorse 1.0 on RunComfy, currently ranked #1 on Artificial Analysis Video Arena, featuring native 1080p output with in-pass synchronized audio and multi-shot character consistency.
A Claude Code skill for face and character swapping in images and videos on RunComfy, routing across Wan 2-2 Animate, GPT Image 2 Edit, Nano Banana Edit, Flux Kontext, and Kling Motion Control based on the target medium and swap type.