Light Silhouette

# Wiggly Light Silhouette Format

This runnable Repo preserves the exact gathered prompt, source guide, original
carousel cover, and seven native SKAI examples. It uses the shared Wiggly image
runner so validation, paid approval, retry caps, and visual finalization stay
explicit.

Run from `v3`:

```bash
npm install
npm run format:skai-image -- check --format=light-silhouette
npm run format:skai-image -- smoke --format=light-silhouette
npm run format:skai-image -- init --format=light-silhouette --run=my-photo --input=/absolute/path/to/photo.jpg
npm run format:skai-image -- validate --format=light-silhouette --run=my-photo
npm run format:skai-image -- estimate --format=light-silhouette --run=my-photo
```

Generation requires `REPLICATE_API_TOKEN` and explicit approval:

```bash
npm run format:skai-image -- render --format=light-silhouette --run=my-photo --approve-paid
```

No Replicate proof call was made while packaging this Repo.

Model routes:

- Economy: `google/nano-banana-2-lite`
- Default: `google/nano-banana-2`
- Premium: `google/nano-banana-pro`

The creator guide labels its examples as GPT Image 2. That remains source
provenance; the runnable kit uses Replicate-hosted Nano Banana 2 by default,
Lite for economy, and Pro for premium.

Every native example already contains the creator-published original photo in a
rounded top-right inset. Separate reference files are direct crops of those
insets for provenance and local smoke validation.

---
name: wiggly-light-silhouette
description: Apply the exact gathered SKAI Light Silhouette prompt to one photograph.
---

# Light Silhouette

Use the packaged runner and exact prompt. Do not call Replicate separately or
create another render path.

Ask one short question:

> Which photo should I turn into a Light Silhouette?

Then run:

```bash
npm run format:skai-image -- init --format=light-silhouette --run=<id> --input=<absolute-image-path>
npm run format:skai-image -- validate --format=light-silhouette --run=<id>
npm run format:skai-image -- estimate --format=light-silhouette --run=<id>
npm run format:skai-image -- render --format=light-silhouette --run=<id> --approve-paid
npm run format:skai-image -- inspect --format=light-silhouette --run=<id>
npm run format:skai-image -- inspect --format=light-silhouette --run=<id> --visual-pass --review-notes="<specific observations>"
npm run format:skai-image -- finalize --format=light-silhouette --run=<id> --approve-final
```

Hard rules:

- Keep the exact gathered prompt unless the user explicitly requests a change.
- Use Nano Banana 2 by default, Lite for economy, or Pro for premium.
- Treat GPT Image 2 as creator provenance, not as the packaged Replicate route.
- Validate before spending and never render without `--approve-paid`.
- Persist and resume the prediction ID.
- Never exceed three attempts.
- View the output and record specific visual-review notes before finalizing.
- Never print, store, or commit `REPLICATE_API_TOKEN`.

{
  "runtime": {
    "node": ">=22",
    "commands": ["npm"]
  },
  "providers": [
    {
      "name": "Replicate",
      "models": [
        "google/nano-banana-2-lite",
        "google/nano-banana-2",
        "google/nano-banana-pro"
      ]
    }
  ],
  "environment": [
    {
      "name": "REPLICATE_API_TOKEN",
      "secret": true,
      "requiredFor": ["render", "resume"]
    }
  ],
  "notes": [
    "All smoke and validation commands are local.",
    "The creator guide labels its examples GPT Image 2. That remains source provenance; the packaged Replicate runtime uses Nano Banana 2 by default, Lite for economy, and Pro for premium.",
    "No proof generation was purchased for this package.",
    "One render attempt is one paid prediction.",
    "Paid generation requires explicit approval and is capped at three attempts."
  ]
}

{
  "required": [
    {
      "id": "photo",
      "type": "image",
      "formats": ["jpg", "png", "webp"],
      "minimumWidth": 512,
      "minimumHeight": 512,
      "maximumBytes": 26214400
    }
  ],
  "question": "Which photo should I turn into a Light Silhouette?",
  "defaults": {
    "model": "nano-banana-2",
    "aspectRatio": "3:4",
    "outputCount": 1
  },
  "modelRoutes": {
    "economy": "google/nano-banana-2-lite",
    "default": "google/nano-banana-2",
    "premium": "google/nano-banana-pro",
    "creatorShown": "GPT Image 2"
  }
}

{
  "progress": "Prepare -> Validate -> Transform -> Inspect",
  "attemptCap": 3,
  "stages": [
    {
      "id": "prepare",
      "output": "One run pinned to the photo, exact gathered prompt, and selected model route.",
      "paid": false,
      "approvalRequired": false
    },
    {
      "id": "validate",
      "output": "The photo and prompt contract checked locally.",
      "paid": false,
      "approvalRequired": false
    },
    {
      "id": "transform",
      "output": "One Light Silhouette photograph from one approved prediction.",
      "paid": true,
      "approvalRequired": true
    },
    {
      "id": "inspect",
      "output": "Automatic file checks plus an actual visual review.",
      "paid": false,
      "approvalRequired": true
    }
  ]
}

{
  "sourceReference": {
    "creator": "@skaigenerated",
    "postUrl": "https://www.instagram.com/p/Daxp6JYCvuf/",
    "resourceTitle": "Light Silhouette Prompt",
    "resourceUrl": "https://docs.google.com/document/d/1fkCvR3TDStmfpjo6ULhGmw-A2V2It-bulTVFNv-cISs",
    "guide": "assets/source/guide.txt",
    "cover": "assets/source/cover.jpg",
    "referenceInset": "assets/source/coastal-cliff-reference.jpg",
    "verification": "The Instagram DM delivered the public Google Doc with the exact GPT Image 2 prompt. The ten-slide carousel supplied one cover and seven native output examples; two promotional slides were omitted. Clean 1080x1440 creator files were recovered from Instagram's public embed data.",
    "referenceNote": "Each creator example already includes its original input photo in a rounded top-right inset. The separate reference files are direct crops of those published insets and are retained for provenance and runner smoke inputs."
  },
  "examples": [
    {
      "id": "coastal-cliff",
      "path": "assets/source/coastal-cliff.jpg",
      "referencePath": "assets/source/coastal-cliff-reference.jpg",
      "referenceType": "creator-published-inset"
    },
    {
      "id": "desert-camel",
      "path": "assets/source/desert-camel.jpg",
      "referencePath": "assets/source/desert-camel-reference.jpg",
      "referenceType": "creator-published-inset"
    },
    {
      "id": "subway-platform",
      "path": "assets/source/subway-platform.jpg",
      "referencePath": "assets/source/subway-platform-reference.jpg",
      "referenceType": "creator-published-inset"
    },
    {
      "id": "misty-hills",
      "path": "assets/source/misty-hills.jpg",
      "referencePath": "assets/source/misty-hills-reference.jpg",
      "referenceType": "creator-published-inset"
    },
    {
      "id": "pyramid-dance",
      "path": "assets/source/pyramid-dance.jpg",
      "referencePath": "assets/source/pyramid-dance-reference.jpg",
      "referenceType": "creator-published-inset"
    },
    {
      "id": "mountain-meadow",
      "path": "assets/source/mountain-meadow.jpg",
      "referencePath": "assets/source/mountain-meadow-reference.jpg",
      "referenceType": "creator-published-inset"
    },
    {
      "id": "lakeside-field",
      "path": "assets/source/lakeside-field.jpg",
      "referencePath": "assets/source/lakeside-field-reference.jpg",
      "referenceType": "creator-published-inset"
    }
  ]
}

{
  "automatic": [
    "Exactly 1 decodable JPG, JPEG, PNG, or WebP output",
    "At least 640x800 pixels",
    "Aspect ratio matches the selected route within 0.02",
    "At least 50 KB"
  ],
  "visual": [
    "Only the subject becomes a glowing white silhouette",
    "The original pose, proportions, background, composition, and environment remain recognizable",
    "Smooth edges, warm highlights, soft golden trails, and a subtle aura feel cinematic",
    "The background has natural depth without looking artificial, painted, or over-blurred",
    "The result remains premium and photographic without facial detail, warped anatomy, stray text, or watermarks"
  ],
  "finalization": {
    "automaticPassRequired": true,
    "visualPassRequired": true,
    "reviewNotesRequired": true,
    "explicitApprovalFlag": "--approve-final"
  }
}

{
  "purpose": "Judge subject-only silhouette transformation, exact pose and scene preservation, premium glow behavior, cinematic depth, and natural photographic finish.",
  "examples": [
    {
      "id": "coastal-cliff",
      "title": "Coastal Cliff",
      "imagePath": "assets/source/coastal-cliff.jpg",
      "referencePath": "assets/source/coastal-cliff-reference.jpg",
      "referenceType": "creator-published-inset",
      "model": "GPT Image 2",
      "whyItWorks": [
        "The relaxed standing pose, loose clothing, bag placement, coastline, and horizon stay fixed",
        "The white silhouette remains readable against a detailed green and blue landscape",
        "Warm glow and thin light trails add energy without replacing the scene"
      ]
    },
    {
      "id": "desert-camel",
      "title": "Desert Camel",
      "imagePath": "assets/source/desert-camel.jpg",
      "referencePath": "assets/source/desert-camel-reference.jpg",
      "referenceType": "creator-published-inset",
      "model": "GPT Image 2",
      "whyItWorks": [
        "The camel, reins, stance, dunes, and low horizon remain intact",
        "The subject alone becomes luminous while the animal stays photographic",
        "The warm desert palette naturally supports the golden aura"
      ]
    },
    {
      "id": "subway-platform",
      "title": "Subway Platform",
      "imagePath": "assets/source/subway-platform.jpg",
      "referencePath": "assets/source/subway-platform-reference.jpg",
      "referenceType": "creator-published-inset",
      "model": "GPT Image 2",
      "whyItWorks": [
        "The crossed-leg lean, folded arms, pole, train, signage, and platform perspective all survive",
        "The bright figure reads clearly against the dark station",
        "Cinematic contrast heightens the scene without changing its geometry"
      ]
    },
    {
      "id": "misty-hills",
      "title": "Misty Hills",
      "imagePath": "assets/source/misty-hills.jpg",
      "referencePath": "assets/source/misty-hills-reference.jpg",
      "referenceType": "creator-published-inset",
      "model": "GPT Image 2",
      "whyItWorks": [
        "The small standing pose and layered green ridges remain in the same positions",
        "A restrained glow keeps the subject visible through soft mist",
        "The background gains gentle separation without losing natural detail"
      ]
    },
    {
      "id": "pyramid-dance",
      "title": "Pyramid Dance",
      "imagePath": "assets/source/pyramid-dance.jpg",
      "referencePath": "assets/source/pyramid-dance-reference.jpg",
      "referenceType": "creator-published-inset",
      "model": "GPT Image 2",
      "whyItWorks": [
        "The airborne dance pose, foreground sand, and pyramid scale stay recognizable",
        "Fine glow lines preserve the unusual limb shapes without adding facial detail",
        "The luminous figure remains distinct inside a bright desert scene"
      ]
    },
    {
      "id": "mountain-meadow",
      "title": "Mountain Meadow",
      "imagePath": "assets/source/mountain-meadow.jpg",
      "referencePath": "assets/source/mountain-meadow-reference.jpg",
      "referenceType": "creator-published-inset",
      "model": "GPT Image 2",
      "whyItWorks": [
        "The outstretched arms, body proportions, meadow, and mountain skyline stay locked",
        "Sunset backlight and the generated aura feel like one consistent light source",
        "The distant landscape keeps its photographic texture and depth"
      ]
    },
    {
      "id": "lakeside-field",
      "title": "Lakeside Field",
      "imagePath": "assets/source/lakeside-field.jpg",
      "referencePath": "assets/source/lakeside-field-reference.jpg",
      "referenceType": "creator-published-inset",
      "model": "GPT Image 2",
      "whyItWorks": [
        "The standing subject, grassy foreground, lake, and green valley remain unchanged",
        "The white silhouette stays legible against both water and grass",
        "Warm highlights balance the cool landscape without making it look synthetic"
      ]
    }
  ]
}

{
  "id": "light-silhouette",
  "version": "1.0.0",
  "title": "Light Silhouette",
  "description": "Turn only the subject into a glowing white human silhouette while preserving the original pose, scene, lighting, shadows, and composition.",
  "status": "agent-ready",
  "owner": "Wiggly Studio",
  "source": {
    "creator": "@skaigenerated",
    "postUrl": "https://www.instagram.com/p/Daxp6JYCvuf/",
    "resourceTitle": "Light Silhouette Prompt",
    "resourceUrl": "https://docs.google.com/document/d/1fkCvR3TDStmfpjo6ULhGmw-A2V2It-bulTVFNv-cISs",
    "resourceAccess": "Instagram DM to public Google Doc",
    "ctaKeyword": "AI",
    "modelShown": "GPT Image 2"
  },
  "outputs": [
    "1 inspected Light Silhouette photograph",
    "state.json with model and prediction provenance",
    "quality-report.json with automatic and visual inspection"
  ]
}

{
  "name": "wiggly-light-silhouette-format-kit",
  "private": true,
  "version": "1.0.0",
  "type": "module",
  "engines": {
    "node": ">=22"
  },
  "scripts": {
    "check:kit": "node kit-smoke.mjs",
    "format:skai-image": "tsx scripts/skai-image-format.ts",
    "test": "tsx tests/skai-image-format-runner.test.ts --format=light-silhouette && node kit-smoke.mjs"
  },
  "dependencies": {
    "image-size": "2.0.2",
    "replicate": "1.4.0",
    "tsx": "4.20.6"
  }
}

{
  "slug": "light-silhouette",
  "version": "1.0.0",
  "promptPath": "prompts/transform.txt",
  "input": {
    "mode": "image",
    "formats": ["jpg", "png", "webp"],
    "minimumWidth": 512,
    "minimumHeight": 512,
    "maximumBytes": 26214400
  },
  "defaultModel": "nano-banana-2",
  "modelRoutes": {
    "nano-banana-2-lite": {
      "label": "Nano Banana 2 Lite",
      "lane": "economy",
      "model": "google/nano-banana-2-lite",
      "family": "nano-banana",
      "aspectRatio": "3:4",
      "outputFormat": "jpg"
    },
    "nano-banana-2": {
      "label": "Nano Banana 2",
      "lane": "default",
      "model": "google/nano-banana-2",
      "family": "nano-banana",
      "aspectRatio": "3:4",
      "outputFormat": "jpg",
      "resolution": "1K"
    },
    "nano-banana-pro": {
      "label": "Nano Banana Pro",
      "lane": "premium",
      "model": "google/nano-banana-pro",
      "family": "nano-banana",
      "aspectRatio": "3:4",
      "outputFormat": "jpg",
      "resolution": "1K"
    }
  },
  "expectedOutputs": 1,
  "maximumAttempts": 3,
  "smokeInputPath": "assets/source/coastal-cliff-reference.jpg",
  "smokeExamplePath": "assets/source/coastal-cliff.jpg",
  "minimumOutputWidth": 640,
  "minimumOutputHeight": 800,
  "minimumOutputBytes": 51200,
  "manualReview": [
    "only the main subject becomes a glowing white human silhouette",
    "the exact pose, proportions, scene, shadows, composition, and environment remain intact",
    "the silhouette has smooth edges, no facial detail, soft golden light trails, and a restrained aura",
    "the background gains gentle cinematic depth without looking painted or over-blurred",
    "the result stays photographic and premium without stray text, warped anatomy, or watermarks"
  ]
}