What problem does it solve? Producing cinematic AI video with consistent characters, native audio, and the right quality tier requires knowing which Kling 3.0 endpoint to call, how to structure prompts, and how to control cost. This Skill routes requests to the correct RunComfy endpoint and handles CLI invocation, polling, and result download. ## Core Features & Use Cases - Six endpoint coverage: Routes across three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video) with per-tier pricing guidance. - Multi-shot prompting: Supports numbered shot sequences in one generation with character identity preservation, plus tail-image control for i2v transitions. - Native audio generation: Enables synchronized dialogue, ambience, and music in a single pass via the generate_audio flag. - Use Case: A marketing team needs a 10-second 4K brand film with voiceover. The Skill selects the kling/kling-3.0/4k/text-to-video endpoint, submits a multi-shot prompt with audio enabled, and downloads the finished 3840x2160 clip. ## Quick Start Ask the AI to generate a 5-second Kling 3.0 video of a barista pulling an espresso shot in 9:16 vertical format using the Standard tier.
