ai-video-generation

AI Video Generation is a RunComfy-powered skill that simplifies the process of creating AI-generated videos from text prompts, images, and existing video content. It acts as an intelligent routing layer over a broad catalog of video generation models, helping users select the most appropriate model for their goals without needing deep knowledge of each provider. The skill supports text-to-video (t2v), image-to-video (i2v), and video extension workflows, while providing the exact RunComfy CLI commands needed to generate content. This reduces the complexity of evaluating models, endpoints, and invocation patterns across multiple video-generation platforms.

The skill includes access to a diverse set of video models such as HappyHorse 1.0, Wan 2-7, Seedance, Kling, Veo, Hailuo, and Dreamina. It can recommend models based on specific creative requirements including high-quality output, multi-shot character consistency, native audio generation, audio-driven lip-sync, cinematic motion, faster generation speed, shorter clips, or longer-duration content. In addition to model selection, the skill provides documented prompting patterns and standardized RunComfy CLI usage, making it easier to generate videos consistently across different models.

This skill is designed for creators, marketers, content producers, developers, and AI enthusiasts who need a streamlined workflow for video generation. Common use cases include creating social-media clips, advertising content, cinematic scenes, animated image sequences, narrative video concepts, and extended video segments. It is particularly valuable for users who want to leverage multiple AI video models through a single command-line interface while minimizing the effort required to choose and configure the right model.