HiAPIAI

Turn a brief, link, or research topic into a controlled, source-grounded video prompt that runs on HiAPI Seedance 2.0 or HappyHorse 1.0. Use when a user asks to direct, plan, or storyboard a video before generation.

Design production-ready prompts and second-by-second storyboards for Jimeng Seedance 2.0 using text, image, video, and audio references. Use for Seedance or Jimeng video ideation, prompt writing, asset analysis and @reference mapping, shot planning, dialogue…

给视频生成模型（Sora/Veo/可灵/即梦/Hailuo 等）写「人物情绪特写」表演 prompt 时用——哭戏、强忍、破防、微表情、喜极而泣、愤怒克制、强忍笑意等真实感情绪表演。触发词：「情绪特写」「人物表演 prompt」「哭戏」「破防」「微表情」「情绪弧线」「emotional close-up」「facial performance」。核心方法：六阶段情绪弧线 + 肌肉级解剖描写 + 泪水/呼吸/声音物理因果 + 混合情绪裂缝 + 反表演指令 + 技术尾巴模板。

Use when planning, creating, reviewing, or researching AI product videos from product images, ecommerce listings, or product briefs. Routes ecommerce sellers, ad teams, and AI creators through product-image preparation, hero visuals, storyboards,…

Generate videos with HiAPI's seedance-2.0 model via the HiAPI unified async task API. Use when a user asks to create a video with Seedance 2.0, HiAPI Seedance 2.0, or this specific skill.

Turn one reference image into a text prompt that makes an image model regenerate a similar image — subject, layout, dominant shapes, light, color grade, and verbatim text — for general use, GPT Image, Midjourney, FLUX, or Stable Diffusion, in English or…

Build a complete brand identity from a one-line business idea — strategy, name check, a vector logo system (mark, horizontal, stacked) drawn as SVG, colour and type, voice — then put the real logo onto photorealistic mockups (storefront, packaging, cups,…

Make a complete, consistent game asset pack from one game idea through one HiAPI key — key art, character sprites and poses with transparent backgrounds, enemies, items, tilesets and UI icon sheets cut into game-ready PNGs, parallax backgrounds, title logo,…

Use only for HiAPI GPT Image 2.5 image generation and editing with Flare or Sunburst — the mode model IDs gpt-image-2.5-flare/text-to-image, gpt-image-2.5-flare/image-to-image, gpt-image-2.5-sunburst/text-to-image, gpt-image-2.5-sunburst/image-to-image…

Generate images with HiAPI's GPT Image 2 family (default, beta, and ext multi-ratio 4K routes) via the HiAPI unified async task API, with non-billing dry-run/estimate, idempotent task creation, and create-free recovery. Use when a user asks to create or edit…

Use when a user asks to create text-to-video with HappyHorse 1.0, HiAPI HappyHorse 1.0, or this specific skill.

Create source-grounded, real-person or consented synthetic-actor UGC product ads with HiAPI Seedance 2.0 for TikTok and Instagram Reels. Use for ecommerce product trials, unboxings, direct-to-camera demos, creator-style scripts, paid-social variants, 9:16…

Design and review model-agnostic video prompts that should resemble captured real-world footage, including phone clips, consumer camcorder recordings, analog tape, small-gauge film, action cameras, security cameras, webcams, observational documentary, and…