detail-page-image

Detail Page Image Composer

Overview

This is a skill that generates 13-section emotional journey detail page images and creates them into a vertically composited PNG. Using moai-media:higgsfield-image as the backend, it creates 13 section images with a consistent visual tone per category, and produces a single 1080×12720 composite image with Pillow as the sole dependency.

Trigger Keywords

detail page image, sangpye image, 13-section image, 1080 12720, detail page composite, product detail image, combined.png, sangpye composite, e-commerce image composite

Prerequisites

1. Pillow installation: pip install Pillow or uv pip install Pillow
   • Python 3.10+ environment
   • No other dependencies (NumPy not required)

1. moai-media plugin enabled: use higgsfield-image for 13-section image generation

   • Or the user separately prepares 13 section images and provides the folder path

2. 1-14 product photos: actual product reference (optional but recommended)

Workflow

Step 1: Collect Input

Secure the following:

• 13-section copy JSON (detail-page-copy skill output)
• Paths to 1-14 product photos
• Category (electronics/fashion/food/beauty/home/supplement/pet/kids/handmade/general)
• ProductDNA (optional, product-photo-brief skill output)
• Output directory (default: ./commerce-output/{job_id}/)

Step 2: Generate 13-Section Image Prompts

Combine each section's copy and the category visual brief to write higgsfield-image prompts. references/image-prompts.md reference (per-section visual language, composite guide).

Each section has a unique visual language:

• Hero: cinematic_product_portrait — full-bleed + dramatic rim light
• Pain: emotional_photography_no_product — dark tone, no product shown
• Problem: clinical_infographic — clean infographic
• Story: editorial_split_before_after — Before/After left-right split
• Solution: product_beauty_shot — studio beauty shot
• How: illustrated_step_sequence — 3-step illustration
• Proof: magazine_spread — magazine spread
• Authority: portrait_with_quote — portrait + quote
• Benefits: icon_grid_with_lifestyle — icon grid + lifestyle
• Risk: document_with_seal — document·certification style
• Compare: split_screen_vs — 50/50 split comparison
• Filter: checklist_visual — checklist visualization
• CTA: urgent_product_reveal — urgency + price emphasis

Step 3: Image Generation (moai-media:higgsfield-image)

Generation strategy:

• Width of each section: 1080px
• Height per section: references/sections-spec.md See table (Hero 1600-Filter 700)
• Inject category visual brief (electronics/fashion/...) into all prompts
• Pass product reference photos to higgsfield-image's image-to-image mode

Save generation results from output_dir/{job_id}/sections/01_hero.png to 13_cta.png .

On generation failure: the corresponding section is filled with a dark placeholder (40,40,40) and compositing proceeds.

Step 4: 1080×12720 compositing (scripts/compose.py)

python scripts/compose.py \
  --sections-dir ./commerce-output/{job_id}/sections/ \
  --output ./commerce-output/{job_id}/combined.png

Script behavior:

1. Load the 13 section PNGs in order
2. Resize each section to the standard width of 1080 (preserve aspect ratio + center crop)
3. Adjust to the standard height per section
4. Stitch vertically to create a single 1080×12720 PNG
5. Missing sections are replaced with a (40,40,40) dark placeholder

For the detailed algorithm, see scripts/compose.py와 scripts/README.md .

Step 5: Output report

{
  "job_id": "a1b2c3d4",
  "output_dir": "/abs/.../commerce-output/a1b2c3d4",
  "combined": "/abs/.../combined.png",
  "sections": [
    "/abs/.../sections/01_hero.png",
    "...",
    "/abs/.../sections/13_cta.png"
  ],
  "failed_sections": [],
  "elapsed_sec": 0,
  "size": "1080x12720"
}

failed_sectionsIf is not empty, guide the user on the following:

• Which sections failed
• Whether it automatically resumes when rerun with the same --output --job-id(resume is done by the user manually regenerating only that section)

Output file structure

./commerce-output/{job_id}/
├── analysis.json              # 13섹션 카피 + 프롬프트 + ProductDNA
├── sections/                   # 13장 섹션 (1080×가변)
│   ├── 01_hero.png            (1080×1600)
│   ├── 02_pain.png            (1080×800)
│   ├── ...
│   └── 13_cta.png             (1080×900)
└── combined.png                # 1080×12720 세로 합성본

scripts/compose.py usage

For detailed usage, see scripts/README.md . Key commands:

# 13장이 sections/ 폴더에 01_hero.png ~ 13_cta.png로 있을 때
python scripts/compose.py \
  --sections-dir ./commerce-output/abc12345/sections/ \
  --output ./commerce-output/abc12345/combined.png

Options:

• --width INT: Output width (default 1080)
• --placeholder-color "R,G,B": Missing section placeholder color (default "40,40,40")
• --quiet: Suppress progress logs

Usage examples

• "Composite a 13-section image with this copy result"
• "Create a 1080 12720 detail page with 5 product photos"
• "electronics category, wireless earbuds detail page image full set"

Related skills

• moai-commerce:detail-page-copy — 13-section copy generation (input to this skill)
• moai-commerce:product-photo-brief — Product photo pre-analysis
• 13-section image generation — Higgsfield MCP(Soul·Cinematic Image·Character) direct call
• moai-commerce:marketplace-coupang — Image spec guide per channel

When not to use this skill

• When only copy is needed: detail-page-copy use standalone
• When only a single product shot is needed: Higgsfield MCP direct call
• Video generation: Higgsfield MCP(DOP·Soul) direct call
• shadcn/ui-based web detail page: moai-content:product-detail

License

MIT.