Qo-qiao
Community@Qo-qiao
Qo-qiao publishes 13 generative-media skills for AI video, music, image prompt engineering, and stop-motion explainer production on MiniMax Hub.
Agent Skills by Qo-qiao
Showing 13 vetted skills indexed across 1 GitHub repositories.
Image Prompt Reverse
Analyze uploaded images and generate prompts for 19+ AI drawing models.
minimalist-product-ad-generator
Generate minimalist Apple-style product ad videos from product images using anchor photos and beat storyboards.
Portrait Photography
Generates professional portrait photography prompts with lighting design, lens language, and realism techniques for Z-Image and Krea 2.
music-video-subtitle-generator
Generates beat-synced multi-shot MV prompts and lyric typography plans from music and lyrics.
3d-animation-short-generator
Generates stylized 3D animated shorts from story ideas through a gated production workflow.
music-caption-rewriter
Convert music descriptions and tagged lyrics into structured MiniMax Music 3 generation captions.
handdrawn-live-video-generator
Generates 15-second 16:9 video prompts blending hand-drawn animation with live-action footage for MiniMax H3.
paper-collage-explainer-generator
Generate stop-motion paper-collage explainer animations from narration lines or abstract concepts.
h3-prompt-writing
Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA modes.
brand-promo-video-generator
Generate short brand promotional videos from verified assets using Hub-native image, video, and audio tools.
co-op-game-intro-generator
Generates two-player co-op game intro videos via confirmation image and Minimax H3 prompts.
yue2-music
Generate, cover, transcribe, and edit songs with YuE2 and SheetSage2 via ABC scores.
papercraft-stop-motion-explainer
Generate production-ready papercraft stop-motion explainer video packages from knowledge topics.
Frequently Asked Questions About Qo-qiao
FAQPage SchemaWhat tasks can I accomplish with Qo-qiao's skills?▼
You can reverse-engineer image prompts for 19+ models, generate MiniMax H3 videos (product ads, brand promos, hand-drawn/live-action hybrids, 3D animated shorts, co-op game intros), create lyric-typography music videos, write structured MiniMax Music 3 captions, and produce paper-collage or papercraft stop-motion explainers.
Who are these skills designed for?▼
They target video creators, musicians, social-media editors, e-commerce marketers, educators, and prompt engineers. Personas include MV producers needing beat-reactive typography, marketers launching product promos, and educators building tactile paper-art explainers for science and knowledge content.
What runtime or platform do these skills require?▼
Eleven of the thirteen skills require the MiniMax Hub agent with its canvas workspace and hub_generate_image/video/audio tools, and are not portable to generic agent harnesses. Only h3-prompt-writing is portable to any agent that reads local files, requiring no external API calls.
Which AI models do the skills support?▼
Image prompt reversal covers SD1.5, SDXL, Flux1, Flux2-Klein, Midjourney, Pony Diffusion, GPT-Image2, and HunyuanImage_2.1. Video skills target MiniMax H3 across T2VA, I2VA, FL2VA, L2VA, and Ref2VA modes. Music skills use YuE2 with SheetSage2/MERT2 and MiniMax Music 3.
What inputs do I need to provide to use these skills?▼
Inputs vary per skill: source images for prompt reversal, product images and ad requirements for commercials, music and lyrics for MVs, story ideas for 3D animation, topics or source copy for explainers, and logos or verified brand assets for promotional videos. Each skill confirms format and direction before generating.