name: morpheus-fashion-design version: 1.2.0 description: | Generate professional advertising images with AI models holding/wearing products.

✅ USE WHEN: - Need a person/model in the image WITH a product - Creating fashion ads, product campaigns, commercial photography - Want consistent model face across multiple shots - Need professional lighting/camera simulation - Input: product image + model reference (or catalog)

❌ DON'T USE WHEN: - Just editing/modifying an existing image → use nano-banana-pro - Product-only shot without a person → use nano-banana-pro - Already have the hero image, need variations → use multishot-ugc - Need video, not image → use veed-ugc after generating image - URL-based product fetch with brand profile → use ad-ready instead

OUTPUT: Single high-quality PNG image (2K-4K resolution)

Morpheus Fashion Design

Generate professional fashion/product advertising images using ComfyDeploy's Morpheus Fashion Design workflow.

⚠️ CRITICAL RULES

1. NO logo field — EVER

The logo input has been removed from the API. Do NOT pass it. Only two image inputs exist: - product → the product being advertised - model → frontal face photo of the model

2. NEVER USE AUTO VALUES for packs

Configuration packs MUST NEVER be left on auto or AUTO.

auto = empty values = neutral, boring images with no creative direction.

Always select deliberately based on the brief. Custom string values are allowed and encouraged.

Pack Selection Guidelines

API Details

Endpoint: https://api.comfydeploy.com/api/run/deployment/queue Deployment ID: 1e16994d-da67-4f30-9ade-250f964b2abc

Canonical API Call

const response = await fetch("https://api.comfydeploy.com/api/run/deployment/queue", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "Bearer YOUR_API_KEY"
  },
  body: JSON.stringify({
    "deployment_id": "1e16994d-da67-4f30-9ade-250f964b2abc",
    "inputs": {
      "product": "/* product image URL */",
      "model":   "/* model face URL */",
      "brief":   "Detailed scene, pose, lighting, mood, product placement...",
      "target":  "Target audience: demographics, psychographics, lifestyle...",
      "input_seed": -1,
      "branding_pack": "logo_none",
      "aspect_ratio": "9:16",
      "style_pack": "street_authentic",
      "camera_pack": "sony_a1",
      "lens_pack": "zeiss_otus_55",
      "film_texture_pack": "kodak_portra_400",
      "color_science_pack": "warm_golden_editorial",
      "shot_pack": "medium_shot",
      "pose_discipline_pack": "street_style_candid_walk",
      "lighting_pack": "natural_window",
      "time_weather_pack": "golden_hour_clear",
      "environment_pack": "urban_glass_steel",
      "intent": "awareness"
    }
  })
});

🎭 Model Catalog

GitHub: https://github.com/PauldeLavallaz/model_management Local path: ~/clawd/models-catalog/catalog/images/

Priority order

1. User provides model image → use directly
2. User describes model → search catalog, select best match
3. No specification → choose based on brief context

Searching

# By body type
cat models-catalog/catalog/catalog.json | python3 -c "
import json,sys; data=json.load(sys.stdin)
for t in data['talents']:
    if t.get('body_type') in ['curvy','plus_size']:
        print(t['id'], t['name'], t['ethnicity'])
"
# By ethnicity + gender
cat models-catalog/catalog/catalog.json | jq '[.talents[] | select(.ethnicity == "hispanic" and .gender == "female") | {id, name, body_type}]'

Creative Brief — How to Write It

Write it as a real photography director's brief — specific, physical, cinematic:

Example: CasanCrem Light (ironic/viral UGC angle)

Campaña UGC TikTok para CasanCrem Light La Serenísima.
Joven de contextura robusta sostiene el pote con sonrisa cómplice en cocina hogareña argentina.
Pose relajada, apoyada en la mesada, mirando directo a cámara con energía y complicidad.
El pote visible y protagonista en la mano. Luz de ventana natural, cálida de tarde.
Estilo UGC auténtico, no publicitario clásico. Cuerpo real, relatable, no atlético.

Example: Oakley Snowboarding

7w4.net小蔥技能站收錄全網優質技能，值得收藏。

Oakley snowboarding campaign. Rider on metal rail in snowpark, body slightly rotated,
arms open for balance, eyes on the line. Technical authentic freestyle pose.
Alpine snowpark, full midday daylight, compacted snow, metal structures.
Natural sun bouncing off snow — saturated colors, strong contrast.
Documentary approach — freeze rider on rail, sharp body and board.
Real session frame: balance, concentration, style merged.

Configuration Packs Reference

Python Upload Helper

def comfy_upload(filepath: str, api_key: str) -> str:
    from pathlib import Path
    import requests
    p = Path(filepath)
    mime = "image/png" if p.suffix == ".png" else "image/jpeg"
    with open(p, "rb") as f:
        r = requests.post(
            "https://api.comfydeploy.com/api/file/upload",
            headers={"Authorization": f"Bearer {api_key}"},
            files={"file": (p.name, f, mime)},
            timeout=60
        )
    r.raise_for_status()
    return r.json()["file_url"]

Priority Hierarchy

Talent (identity) > Product fidelity > Fit > Pose > Style > Location > Branding

Troubleshooting

Imagen negra/vacía = filtro de moderación de Google/Gemini activado. - No usar personas famosas o celebridades - Modificar el brief eliminando referencias problemáticas

API Key: NO pasar como parámetro. Ya está configurado en ComfyDeploy.

Integración con Portrait Generator

Flujo de selección de modelo (actualizado)

El campo model puede venir de dos fuentes:

Opción A — Catálogo (default):

~/clawd/models-catalog/catalog/images/model_XX.jpg

Usar cuando el guión no requiere rasgos muy específicos.

Opción B — Portrait Generator (cuando el guión lo requiere):

portrait-generator → imagen_1 (vista frontal) → model en Morpheus

Usar cuando necesitás: etnia muy específica, edad exacta, rasgos únicos, personaje que no existe en el catálogo de 114 modelos.

Regla: imagen_1 del Portrait Generator = siempre la vista frontal = la correcta para model.

Cuándo usar Portrait Generator

• Personaje mayor de 60 años
• Etnia muy específica no disponible en catálogo
• Rasgos físicos únicos (cicatrices, vitiligo, asimetría facial)
• Cualquier personaje que el guión describa con detalle

Cuándo usar el catálogo

• Personaje genérico / sin especificaciones
• Cualquier modelo joven-adulto estándar
• Cuando la velocidad importa más que la precisión

這個 Skill 質量不錯，文件非常詳細，使用說明清晰，能幫助使用者生成專業的時尚廣告影像。主要優點是配置選項豐富、示例充分、錯誤處理完善。主要不足是部分說明與實際功能存在不一致，且缺少明確的使用條款。整體適合需要建立產品廣告圖片的使用者，但使用前需留意其資料上傳風險。