Communitygithub.com

hiapi-fashion-lookbook-video

Plan, preview, price, and generate short single-shot fashion videos through HiAPI. Use for runway walks, one target-outfit transition, editorial lookbook poses, and non-speaking person showcases for clothing brands, fashion creators, and ecommerce sellers. Route text-only briefs to Kling 3.0 Omni text-to-video, one authorized person or complete-look image to Kling image-to-video, and person plus garment/style references to Seedance 2.0 Fast. Do not use for exact virtual try-on or fit guarantees, multi-outfit montages, deterministic motion transfer, talking presenters, captions, logos, CTA compositing, or multi-shot editing.

hiapi-fashion-lookbook-video란 무엇인가요?

hiapi-fashion-lookbook-video is a Claude Code agent skill that plan, preview, price, and generate short single-shot fashion videos through HiAPI. Use for runway walks, one target-outfit transition, editorial lookbook poses, and non-speaking person showcases for clothing brands, fashion creators, and ecommerce sellers. Route text-only briefs to Kling 3.0 Omni text-to-video, one authorized person or complete-look image to Kling image-to-video, and person plus garment/style references to Seedance 2.0 Fast. Do not use for exact virtual try-on or fit guarantees, multi-outfit montages, deterministic motion transfer, talking presenters, captions, logos, CTA compositing, or multi-shot editing.

지원 대상~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/HiAPIAI/hiapi-product-video-skills/tree/main/skills/fashion-lookbook

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

HiAPI Fashion Lookbook Video

Create one short fashion shot. Keep the person authorized, the garment recognizable, the reference roles explicit, and paid generation separately approved.

Route The Request

Choose one recipe:

RecipeBest for
runway-walkA full-body walk ending in one controlled pose
outfit-transitionExactly one initial-to-target outfit transformation
lookbook-poseA slow turn or pose that shows one complete look
person-showcaseA non-speaking fashion portrait with restrained motion

Choose the media route from the supplied assets:

Media inputRouteModel
No imageText-to-videokling-3.0-omni/text-to-video
Exactly one person or complete-look image, no other imageImage-to-videokling-3.0-omni/image-to-video
Any garment or style reference, up to 9 images totalMultireference generationseedance-2.0-fast

Use at most one person image, six garment images for one target look, and two style images. The combined limit is nine. Reference-driven outfit-transition requires one person image and at least one garment image. Text-only outfit-transition is fictional and cannot promise a specific garment or identity.

Delegate a speaking presenter to $hiapi-product-spokesperson-video. Delegate action or camera guidance from a video to $hiapi-reference-motion-transfer. Delegate multi-shot assembly, captions, music, logos, or CTA compositing to a video editing workflow.

Confirm Rights And Scope

Before using any image, confirm that the user owns it or is authorized to use it. Require --asset-rights-confirmed for every media request and additionally require --person-consent-confirmed when a person image is supplied. Do not infer consent, ownership, or a clean commercial license from the image itself.

Describe generated output as creative fashion visualization. Do not describe it as evidence of exact fit, size, tailoring, fabric performance, or how a garment will look on a buyer. Do not make body-shape, age, ethnicity, medical, or attractiveness claims.

Confirm the recipe, one primary action, one camera movement, duration, output ratio, target garment details, and whether audio is needed. Generated audio is off by default. Read references/prompting.md for recipe defaults, reference roles, timing, and fashion truth constraints.

Preview Before Spending

Preview the complete redacted payload offline:

node scripts/hiapi-fashion-lookbook-video.mjs `
  --recipe lookbook-pose `
  --prompt "An adult model presents one structured black evening look" `
  --duration 5 `
  --ratio 9:16 `
  --preview

For an authorized person and target garment:

node scripts/hiapi-fashion-lookbook-video.mjs `
  --recipe outfit-transition `
  --person-image-file "D:\media\person.jpg" `
  --garment-image-file "D:\media\dress-front.jpg" `
  --garment-image-file "D:\media\dress-back.jpg" `
  --person-consent-confirmed `
  --asset-rights-confirmed `
  --prompt "One clean change into the supplied evening dress" `
  --garment-details "Preserve the square neckline, fitted waist, ankle hem, and silver buttons" `
  --duration 5 `
  --ratio 9:16 `
  --preview

Run live checks only after telling the user that they contact HiAPI but create no paid task:

node scripts/hiapi-fashion-lookbook-video.mjs --check --env-file "D:\path\to\.env.local"

Then price the exact request with --dry-run. It reads the public live catalog and creates no task. The default local estimate limit is $1.00; override --max-cost-usd only within an approved budget. Public pricing is not a server-side final-charge cap because account group ratios may apply.

Use --spend --approved-request-hash HASH only after the user explicitly approves the matching live estimate, budget, and request hash. One invocation creates at most one paid task. Read the API key from HIAPI_API_KEY or --env-file; never print or persist it.

Resume Safely

The CLI binds its idempotency key to the approved request hash and prints the task ID immediately after creation. Reuse the exact printed --idempotency-key only if submission was interrupted before a task ID returned. After a task ID exists, resume without resubmitting:

node scripts/hiapi-fashion-lookbook-video.mjs --task-id TASK_ID --env-file "D:\path\to\.env.local"

Never automatically create a replacement task after polling, download, or quality-review failure.

Review The Package

Preserve final.mp4, brief.md, redacted prompt.json, manifest.json, and qc.json. Treat generated_unreviewed as the final automated status. Require human review before publication, ecommerce use, paid advertising, or making garment, identity, fit, size, material, origin, certification, or performance claims.

Read references/output.md for artifact semantics and the fashion QC checklist. Read references/api.md before changing models, routes, pricing, retries, or task handling.

Individual skills in this repo

This repo contains 3 individual skills — each has its own dedicated page.

hiapi-food-commercial-video

Plan, preview, price, and generate single-shot food and beverage commercial videos through HiAPI, with 3-15 second Kling output or 4-15 second Seedance Fast output. Use for coffee pours, beverage splashes, food macro shots, packaged-product hero ads, restaurant atmosphere spots, and ecommerce food promos. Route text-only requests to Kling 3.0 Omni text-to-video, one hero image to Kling image-to-video, and 1-9 reference images to Seedance 2.0 Fast. Do not use for human spokespersons, reference-motion transfer, editing, multi-shot assembly, captions, added logos, or CTA compositing.

hiapi-product-spokesperson-video

Generate product spokesperson, brand introduction, and on-camera advertising videos locally through HiAPI. Use for synthetic presenters, authorized talking-head videos from a person image, product introductions, or brand promotions from product and brand reference images. Route synthetic spokespersons to Kling 3.0 Omni text-to-video, talking heads to Kling 3.0 Omni image-to-video, and product or brand promos to Seedance 2.0 Fast. Do not use to edit or assemble existing footage.

hiapi-seedance-2-0-ugc-ad-video-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 video generation, or UGC campaign batches that need authentic phone-shot direction, native dialogue, claim controls, and final media QC.

관련 스킬