What problem does it solve? Creating AI-generated video with synchronized audio and consistent characters across shots requires knowing the right model, prompt structure, and API parameters, which this Skill packages into a single documented workflow on RunComfy. ## Core Features & Use Cases - Text-to-Video Generation: Calls the happyhorse/happyhorse-1-0/text-to-video endpoint via the RunComfy CLI with control over prompt, aspect ratio, resolution (720P/1080P), duration (3-15s), seed, and watermark. - Prompting Guidance: Documents motion-over-time prompting, camera directives, multi-shot character anchoring, and audio direction for in-pass synchronized sound. - Model Routing: Compares HappyHorse 1.0 against Wan 2.7, Seedance 2.0 Pro, LTX 2, and Kling Video O1 so requests land on the right model. - Use Case: A marketer needs a 9:16 vertical ad with a consistent character across two shots and ambient audio; the Skill supplies the exact CLI command and prompt pattern to produce it. ## Quick Start Ask the AI to generate a video with HappyHorse describing your scene, for example: generate a 10-second 1080p HappyHorse video of a barista pulling an espresso shot in a sunlit cafe.
