handdrawn-live-video-generator

Provide a scene idea, a contact object or hand action, and a mood. The Skill designs the contact moment, continuous morphing chain, escape route, and delayed camera chase, then outputs a complete 15-second 16:9 prompt segmented by time intervals in your input language.

After receiving the prompt, explicitly confirm that you want H3 generation. The Skill will not generate any video, image, or storyboard until you confirm, and then it produces the 15-second 16:9 video with MiniMax H3 and checks contact realism and texture.

Yes, the final prompt follows the dominant language of your input, including Chinese, English, and Japanese. For mixed-language input it uses the dominant language, and only proper nouns or model names you request remain unchanged.

The prompts ban 3DCG, plush toy looks, uniform vector lines, smooth neon, horror monsters, giant eyes, teeth, threatening motions, sudden black screens, and jump scares. The tone stays cute, nostalgic, and gentle with rough crayon or chalk textures.

Avoid it for polished CG production, horror content, plush character videos, or multi-scene edited narratives. It is designed for single-scene or adjacent-space clips where one entity continuously morphs and a handheld camera chases it.