{
  "schemaVersion": "1.0",
  "item": {
    "slug": "morpheus-fashion-design",
    "name": "Morpheus Fashion Design",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/PauldeLavallaz/morpheus-fashion-design",
    "canonicalUrl": "https://clawhub.ai/PauldeLavallaz/morpheus-fashion-design",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/morpheus-fashion-design",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=morpheus-fashion-design",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/generate.py"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/morpheus-fashion-design"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/morpheus-fashion-design",
    "agentPageUrl": "https://openagent3.xyz/skills/morpheus-fashion-design/agent",
    "manifestUrl": "https://openagent3.xyz/skills/morpheus-fashion-design/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/morpheus-fashion-design/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Morpheus Fashion Design",
        "body": "Generate professional fashion/product advertising images using ComfyDeploy's Morpheus Fashion Design workflow."
      },
      {
        "title": "1. NO logo field — EVER",
        "body": "The logo input has been removed from the API. Do NOT pass it.\nOnly two image inputs exist:\n\nproduct → the product being advertised\nmodel → frontal face photo of the model"
      },
      {
        "title": "2. NEVER USE AUTO VALUES for packs",
        "body": "Configuration packs MUST NEVER be left on auto or AUTO.\n\nauto = empty values = neutral, boring images with no creative direction.\n\nAlways select deliberately based on the brief. Custom string values are allowed and encouraged."
      },
      {
        "title": "Pack Selection Guidelines",
        "body": "PackHow to Choosestyle_packBrand personality: luxury→premium_restraint, sports→cinematic_realism, street→street_authenticcamera_packSports→sony_a1, editorial→hasselblad_x2d, street→leica_m6lens_packPortrait compression? Wide? Match shot type and moodlighting_packGolden hour? Studio? Natural window? Match briefpose_discipline_packSport action→sport_in_motion, commercial→commercial_front_facing, UGC→street_style_candid_walkfilm_texture_packWarm editorial→kodak_portra_400, cinematic→kodak_vision3_500t, clean→digital_clean_no_emulationenvironment_packbeach_minimal, urban_glass_steel, street_crosswalk — or custom stringcolor_science_packwarm_golden_editorial, neutral_premium_clean, cinematic_low_contrasttime_weather_packgolden_hour_clear, bright_midday_sun, overcast_winter_daylight"
      },
      {
        "title": "API Details",
        "body": "Endpoint: https://api.comfydeploy.com/api/run/deployment/queue\nDeployment ID: 1e16994d-da67-4f30-9ade-250f964b2abc"
      },
      {
        "title": "Canonical API Call",
        "body": "const response = await fetch(\"https://api.comfydeploy.com/api/run/deployment/queue\", {\n  method: \"POST\",\n  headers: {\n    \"Content-Type\": \"application/json\",\n    \"Authorization\": \"Bearer YOUR_API_KEY\"\n  },\n  body: JSON.stringify({\n    \"deployment_id\": \"1e16994d-da67-4f30-9ade-250f964b2abc\",\n    \"inputs\": {\n      \"product\": \"/* product image URL */\",\n      \"model\":   \"/* model face URL */\",\n      \"brief\":   \"Detailed scene, pose, lighting, mood, product placement...\",\n      \"target\":  \"Target audience: demographics, psychographics, lifestyle...\",\n      \"input_seed\": -1,\n      \"branding_pack\": \"logo_none\",\n      \"aspect_ratio\": \"9:16\",\n      \"style_pack\": \"street_authentic\",\n      \"camera_pack\": \"sony_a1\",\n      \"lens_pack\": \"zeiss_otus_55\",\n      \"film_texture_pack\": \"kodak_portra_400\",\n      \"color_science_pack\": \"warm_golden_editorial\",\n      \"shot_pack\": \"medium_shot\",\n      \"pose_discipline_pack\": \"street_style_candid_walk\",\n      \"lighting_pack\": \"natural_window\",\n      \"time_weather_pack\": \"golden_hour_clear\",\n      \"environment_pack\": \"urban_glass_steel\",\n      \"intent\": \"awareness\"\n    }\n  })\n});"
      },
      {
        "title": "🎭 Model Catalog",
        "body": "GitHub: https://github.com/PauldeLavallaz/model_management\nLocal path: ~/clawd/models-catalog/catalog/images/"
      },
      {
        "title": "Priority order",
        "body": "User provides model image → use directly\nUser describes model → search catalog, select best match\nNo specification → choose based on brief context"
      },
      {
        "title": "Searching",
        "body": "# By body type\ncat models-catalog/catalog/catalog.json | python3 -c \"\nimport json,sys; data=json.load(sys.stdin)\nfor t in data['talents']:\n    if t.get('body_type') in ['curvy','plus_size']:\n        print(t['id'], t['name'], t['ethnicity'])\n\"\n# By ethnicity + gender\ncat models-catalog/catalog/catalog.json | jq '[.talents[] | select(.ethnicity == \"hispanic\" and .gender == \"female\") | {id, name, body_type}]'"
      },
      {
        "title": "Creative Brief — How to Write It",
        "body": "Write it as a real photography director's brief — specific, physical, cinematic:"
      },
      {
        "title": "Example: CasanCrem Light (ironic/viral UGC angle)",
        "body": "Campaña UGC TikTok para CasanCrem Light La Serenísima.\nJoven de contextura robusta sostiene el pote con sonrisa cómplice en cocina hogareña argentina.\nPose relajada, apoyada en la mesada, mirando directo a cámara con energía y complicidad.\nEl pote visible y protagonista en la mano. Luz de ventana natural, cálida de tarde.\nEstilo UGC auténtico, no publicitario clásico. Cuerpo real, relatable, no atlético."
      },
      {
        "title": "Example: Oakley Snowboarding",
        "body": "Oakley snowboarding campaign. Rider on metal rail in snowpark, body slightly rotated,\narms open for balance, eyes on the line. Technical authentic freestyle pose.\nAlpine snowpark, full midday daylight, compacted snow, metal structures.\nNatural sun bouncing off snow — saturated colors, strong contrast.\nDocumentary approach — freeze rider on rail, sharp body and board.\nReal session frame: balance, concentration, style merged."
      },
      {
        "title": "Configuration Packs Reference",
        "body": "PackOptionsstyle_packpremium_restraint, editorial_precision, cinematic_realism, cinematic_memory, campaign_hero, product_truth, clean_commercial, street_authentic, archive_fashion, experimental_authorialshot_packfull_body_wide, medium_shot, close_up, low_angle_hero, three_quarter, waist_upcamera_packarri_alexa35, canon_r5, hasselblad_x2d, leica_m6, sony_a1lens_packcooke_anamorphic_i_50, leica_noctilux_50, zeiss_otus_55, wide_distortion_controlledlighting_packgolden_hour_backlit, natural_window, studio_three_point, bright_midday_sunpose_discipline_packcommercial_front_facing, street_style_candid_walk, sport_in_motionfilm_texture_packkodak_portra_400, fujifilm_velvia_50, kodak_vision3_500t, digital_clean_no_emulationcolor_science_packneutral_premium_clean, warm_golden_editorial, cinematic_low_contrastenvironment_packbeach_minimal, urban_glass_steel, street_crosswalk — or custom descriptive stringtime_weather_packgolden_hour_clear, bright_midday_sun, overcast_winter_daylightbranding_packlogo_none ← always unless logo explicitly requestedintentawareness, consideration, conversion, retentionaspect_ratio9:16, 16:9, 1:1, 4:5, 3:4"
      },
      {
        "title": "Python Upload Helper",
        "body": "def comfy_upload(filepath: str, api_key: str) -> str:\n    from pathlib import Path\n    import requests\n    p = Path(filepath)\n    mime = \"image/png\" if p.suffix == \".png\" else \"image/jpeg\"\n    with open(p, \"rb\") as f:\n        r = requests.post(\n            \"https://api.comfydeploy.com/api/file/upload\",\n            headers={\"Authorization\": f\"Bearer {api_key}\"},\n            files={\"file\": (p.name, f, mime)},\n            timeout=60\n        )\n    r.raise_for_status()\n    return r.json()[\"file_url\"]"
      },
      {
        "title": "Priority Hierarchy",
        "body": "Talent (identity) > Product fidelity > Fit > Pose > Style > Location > Branding"
      },
      {
        "title": "Troubleshooting",
        "body": "Imagen negra/vacía = filtro de moderación de Google/Gemini activado.\n\nNo usar personas famosas o celebridades\nModificar el brief eliminando referencias problemáticas\n\nAPI Key: NO pasar como parámetro. Ya está configurado en ComfyDeploy."
      },
      {
        "title": "Flujo de selección de modelo (actualizado)",
        "body": "El campo model puede venir de dos fuentes:\n\nOpción A — Catálogo (default):\n\n~/clawd/models-catalog/catalog/images/model_XX.jpg\n\nUsar cuando el guión no requiere rasgos muy específicos.\n\nOpción B — Portrait Generator (cuando el guión lo requiere):\n\nportrait-generator → imagen_1 (vista frontal) → model en Morpheus\n\nUsar cuando necesitás: etnia muy específica, edad exacta, rasgos únicos, personaje\nque no existe en el catálogo de 114 modelos.\n\nRegla: imagen_1 del Portrait Generator = siempre la vista frontal = la correcta para model."
      },
      {
        "title": "Cuándo usar Portrait Generator",
        "body": "Personaje mayor de 60 años\nEtnia muy específica no disponible en catálogo\nRasgos físicos únicos (cicatrices, vitiligo, asimetría facial)\nCualquier personaje que el guión describa con detalle"
      },
      {
        "title": "Cuándo usar el catálogo",
        "body": "Personaje genérico / sin especificaciones\nCualquier modelo joven-adulto estándar\nCuando la velocidad importa más que la precisión"
      }
    ],
    "body": "Morpheus Fashion Design\n\nGenerate professional fashion/product advertising images using ComfyDeploy's Morpheus Fashion Design workflow.\n\n⚠️ CRITICAL RULES\n1. NO logo field — EVER\n\nThe logo input has been removed from the API. Do NOT pass it. Only two image inputs exist:\n\nproduct → the product being advertised\nmodel → frontal face photo of the model\n2. NEVER USE AUTO VALUES for packs\n\nConfiguration packs MUST NEVER be left on auto or AUTO.\n\nauto = empty values = neutral, boring images with no creative direction.\n\nAlways select deliberately based on the brief. Custom string values are allowed and encouraged.\n\nPack Selection Guidelines\nPack\tHow to Choose\nstyle_pack\tBrand personality: luxury→premium_restraint, sports→cinematic_realism, street→street_authentic\ncamera_pack\tSports→sony_a1, editorial→hasselblad_x2d, street→leica_m6\nlens_pack\tPortrait compression? Wide? Match shot type and mood\nlighting_pack\tGolden hour? Studio? Natural window? Match brief\npose_discipline_pack\tSport action→sport_in_motion, commercial→commercial_front_facing, UGC→street_style_candid_walk\nfilm_texture_pack\tWarm editorial→kodak_portra_400, cinematic→kodak_vision3_500t, clean→digital_clean_no_emulation\nenvironment_pack\tbeach_minimal, urban_glass_steel, street_crosswalk — or custom string\ncolor_science_pack\twarm_golden_editorial, neutral_premium_clean, cinematic_low_contrast\ntime_weather_pack\tgolden_hour_clear, bright_midday_sun, overcast_winter_daylight\nAPI Details\n\nEndpoint: https://api.comfydeploy.com/api/run/deployment/queue Deployment ID: 1e16994d-da67-4f30-9ade-250f964b2abc\n\nCanonical API Call\nconst response = await fetch(\"https://api.comfydeploy.com/api/run/deployment/queue\", {\n  method: \"POST\",\n  headers: {\n    \"Content-Type\": \"application/json\",\n    \"Authorization\": \"Bearer YOUR_API_KEY\"\n  },\n  body: JSON.stringify({\n    \"deployment_id\": \"1e16994d-da67-4f30-9ade-250f964b2abc\",\n    \"inputs\": {\n      \"product\": \"/* product image URL */\",\n      \"model\":   \"/* model face URL */\",\n      \"brief\":   \"Detailed scene, pose, lighting, mood, product placement...\",\n      \"target\":  \"Target audience: demographics, psychographics, lifestyle...\",\n      \"input_seed\": -1,\n      \"branding_pack\": \"logo_none\",\n      \"aspect_ratio\": \"9:16\",\n      \"style_pack\": \"street_authentic\",\n      \"camera_pack\": \"sony_a1\",\n      \"lens_pack\": \"zeiss_otus_55\",\n      \"film_texture_pack\": \"kodak_portra_400\",\n      \"color_science_pack\": \"warm_golden_editorial\",\n      \"shot_pack\": \"medium_shot\",\n      \"pose_discipline_pack\": \"street_style_candid_walk\",\n      \"lighting_pack\": \"natural_window\",\n      \"time_weather_pack\": \"golden_hour_clear\",\n      \"environment_pack\": \"urban_glass_steel\",\n      \"intent\": \"awareness\"\n    }\n  })\n});\n\n🎭 Model Catalog\n\nGitHub: https://github.com/PauldeLavallaz/model_management Local path: ~/clawd/models-catalog/catalog/images/\n\nPriority order\nUser provides model image → use directly\nUser describes model → search catalog, select best match\nNo specification → choose based on brief context\nSearching\n# By body type\ncat models-catalog/catalog/catalog.json | python3 -c \"\nimport json,sys; data=json.load(sys.stdin)\nfor t in data['talents']:\n    if t.get('body_type') in ['curvy','plus_size']:\n        print(t['id'], t['name'], t['ethnicity'])\n\"\n# By ethnicity + gender\ncat models-catalog/catalog/catalog.json | jq '[.talents[] | select(.ethnicity == \"hispanic\" and .gender == \"female\") | {id, name, body_type}]'\n\nCreative Brief — How to Write It\n\nWrite it as a real photography director's brief — specific, physical, cinematic:\n\nExample: CasanCrem Light (ironic/viral UGC angle)\nCampaña UGC TikTok para CasanCrem Light La Serenísima.\nJoven de contextura robusta sostiene el pote con sonrisa cómplice en cocina hogareña argentina.\nPose relajada, apoyada en la mesada, mirando directo a cámara con energía y complicidad.\nEl pote visible y protagonista en la mano. Luz de ventana natural, cálida de tarde.\nEstilo UGC auténtico, no publicitario clásico. Cuerpo real, relatable, no atlético.\n\nExample: Oakley Snowboarding\nOakley snowboarding campaign. Rider on metal rail in snowpark, body slightly rotated,\narms open for balance, eyes on the line. Technical authentic freestyle pose.\nAlpine snowpark, full midday daylight, compacted snow, metal structures.\nNatural sun bouncing off snow — saturated colors, strong contrast.\nDocumentary approach — freeze rider on rail, sharp body and board.\nReal session frame: balance, concentration, style merged.\n\nConfiguration Packs Reference\nPack\tOptions\nstyle_pack\tpremium_restraint, editorial_precision, cinematic_realism, cinematic_memory, campaign_hero, product_truth, clean_commercial, street_authentic, archive_fashion, experimental_authorial\nshot_pack\tfull_body_wide, medium_shot, close_up, low_angle_hero, three_quarter, waist_up\ncamera_pack\tarri_alexa35, canon_r5, hasselblad_x2d, leica_m6, sony_a1\nlens_pack\tcooke_anamorphic_i_50, leica_noctilux_50, zeiss_otus_55, wide_distortion_controlled\nlighting_pack\tgolden_hour_backlit, natural_window, studio_three_point, bright_midday_sun\npose_discipline_pack\tcommercial_front_facing, street_style_candid_walk, sport_in_motion\nfilm_texture_pack\tkodak_portra_400, fujifilm_velvia_50, kodak_vision3_500t, digital_clean_no_emulation\ncolor_science_pack\tneutral_premium_clean, warm_golden_editorial, cinematic_low_contrast\nenvironment_pack\tbeach_minimal, urban_glass_steel, street_crosswalk — or custom descriptive string\ntime_weather_pack\tgolden_hour_clear, bright_midday_sun, overcast_winter_daylight\nbranding_pack\tlogo_none ← always unless logo explicitly requested\nintent\tawareness, consideration, conversion, retention\naspect_ratio\t9:16, 16:9, 1:1, 4:5, 3:4\nPython Upload Helper\ndef comfy_upload(filepath: str, api_key: str) -> str:\n    from pathlib import Path\n    import requests\n    p = Path(filepath)\n    mime = \"image/png\" if p.suffix == \".png\" else \"image/jpeg\"\n    with open(p, \"rb\") as f:\n        r = requests.post(\n            \"https://api.comfydeploy.com/api/file/upload\",\n            headers={\"Authorization\": f\"Bearer {api_key}\"},\n            files={\"file\": (p.name, f, mime)},\n            timeout=60\n        )\n    r.raise_for_status()\n    return r.json()[\"file_url\"]\n\nPriority Hierarchy\nTalent (identity) > Product fidelity > Fit > Pose > Style > Location > Branding\n\nTroubleshooting\n\nImagen negra/vacía = filtro de moderación de Google/Gemini activado.\n\nNo usar personas famosas o celebridades\nModificar el brief eliminando referencias problemáticas\n\nAPI Key: NO pasar como parámetro. Ya está configurado en ComfyDeploy.\n\nIntegración con Portrait Generator\nFlujo de selección de modelo (actualizado)\n\nEl campo model puede venir de dos fuentes:\n\nOpción A — Catálogo (default):\n\n~/clawd/models-catalog/catalog/images/model_XX.jpg\n\n\nUsar cuando el guión no requiere rasgos muy específicos.\n\nOpción B — Portrait Generator (cuando el guión lo requiere):\n\nportrait-generator → imagen_1 (vista frontal) → model en Morpheus\n\n\nUsar cuando necesitás: etnia muy específica, edad exacta, rasgos únicos, personaje que no existe en el catálogo de 114 modelos.\n\nRegla: imagen_1 del Portrait Generator = siempre la vista frontal = la correcta para model.\n\nCuándo usar Portrait Generator\nPersonaje mayor de 60 años\nEtnia muy específica no disponible en catálogo\nRasgos físicos únicos (cicatrices, vitiligo, asimetría facial)\nCualquier personaje que el guión describa con detalle\nCuándo usar el catálogo\nPersonaje genérico / sin especificaciones\nCualquier modelo joven-adulto estándar\nCuando la velocidad importa más que la precisión"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/PauldeLavallaz/morpheus-fashion-design",
    "publisherUrl": "https://clawhub.ai/PauldeLavallaz/morpheus-fashion-design",
    "owner": "PauldeLavallaz",
    "version": "1.4.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/morpheus-fashion-design",
    "downloadUrl": "https://openagent3.xyz/downloads/morpheus-fashion-design",
    "agentUrl": "https://openagent3.xyz/skills/morpheus-fashion-design/agent",
    "manifestUrl": "https://openagent3.xyz/skills/morpheus-fashion-design/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/morpheus-fashion-design/agent.md"
  }
}