Generate Kling 3.0 multi-shot videos from text or images via RunComfy endpoints.
npx skills add https://github.com/runcomfy-com/skills --skill kling-3-0
Please help me install this Agent Skill. Skill: kling-3-0 Source: https://github.com/runcomfy-com/skills/tree/main/kling-3-0 Command: npx skills add https://github.com/runcomfy-com/skills --skill kling-3-0
This Skill solves the problem of producing high-quality Kling 3.0 multi-shot videos with consistent character identity, synchronized audio, and correct tier/mode routing without manually orchestrating multiple API calls.
generate_audio for Standard and Pro with higher cost and flat-rate audio behavior on the 4K tier.tail_image_url for controlled endings.Use the Kling 3.0 skill to generate a 10-second 16:9 text-to-video by describing your cinematic multi-shot prompt and choosing the appropriate tier (Standard, Pro, or 4K).
High-intent search queries and answers about installing and using this skill.
Multi-shot videos with consistent character identity are generated using Kling 3.0 by submitting a single-call, numbered shot sequence prompt to preserve character features across multiple cinematic shots.
You can animate a subject from a publicly fetchable HTTPS image URL into a 4K video by selecting the image-to-video mode and the 4K rendering tier in the Kling 3.0 endpoint.
Synchronized audio generation is supported for image-to-video using Kling 3.0 by enabling the generate_audio option, which is available for Standard and Pro tiers with flat-rate behavior on 4K.
To control the ending frame of an image-to-video animation, provide an optional tail_image_url alongside the starting image_url in your JSON input to define the final visual state.
To generate native 4K brand films, route your cinematic text prompt to the Kling 3.0 text-to-video endpoint configured for the 4K tier to achieve 3840x2160 resolution rendering.
agentspace-soGenerate cinematic Kling 3.0 videos on RunComfy from text prompts or reference images.
doany-aiGenerate cinematic videos via RunComfy CLI using Standard, Pro, or 4K tiers and text/image inputs.
runcomfy-comRoute still images to RunComfy image-to-video models for animated video output.
video-production-buddyGenerate cinematic video clips with synchronized audio and multi-shot cuts.