Fake It Till You Make It

# Wiggly Fake It Till You Make It Format

This runnable Repo preserves the eight exact prompts and eight native carousel
examples gathered from @skaigenerated. Each selected scene is one independent
Replicate prediction so cost and retries stay visible.

Run from `v3`:

```bash
npm install
npm run format:skai-image -- check --format=fake-it-till-you-make-it
npm run format:skai-image -- smoke --format=fake-it-till-you-make-it
npm run format:skai-image -- init --format=fake-it-till-you-make-it --run=my-selfie --variant=yellow-pirelli-cap --input=/absolute/path/to/portrait.jpg
npm run format:skai-image -- validate --format=fake-it-till-you-make-it --run=my-selfie
npm run format:skai-image -- estimate --format=fake-it-till-you-make-it --run=my-selfie
```

Generation requires `REPLICATE_API_TOKEN` and explicit approval:

```bash
npm run format:skai-image -- render --format=fake-it-till-you-make-it --run=my-selfie --approve-paid
```

Use one run per selected variant. A complete eight-image set uses eight paid
predictions. No Replicate proof call was made while packaging this Repo.

Model routes:

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

---
name: wiggly-fake-it-till-you-make-it
description: Turn one portrait into up to eight believable lifestyle posts using the exact gathered SKAI prompts.
---

# Fake It Till You Make It

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

Ask one short question at a time:

1. Which portrait should I use?
2. Do you want one scene or the complete eight-image set?

Variants:

`sheet-mask-mirror`, `luxury-bathroom`, `shooting-range`,
`yellow-pirelli-cap`, `tropical-hat`, `nyc-bench`, `concrete-cafe`,
`bed-mask`

For each selected variant, use a unique run id:

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

Hard rules:

- Preserve the reference identity unless the user explicitly requests a new subject.
- Keep the selected gathered prompt exact.
- State that one scene is one paid prediction; all eight means eight predictions.
- Validate every run before spending.
- Never generate without `--approve-paid`.
- Persist and resume each prediction id.
- Never exceed three attempts for any scene.
- View every output and record scene-specific 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.",
    "No proof generation was purchased for this package.",
    "Each selected scene is one independent paid prediction.",
    "The complete eight-image set therefore uses eight predictions.",
    "Paid generation requires explicit approval and is capped at three attempts per scene."
  ]
}

{
  "required": [
    {
      "id": "portrait",
      "type": "image",
      "formats": ["jpg", "png", "webp"],
      "minimumWidth": 512,
      "minimumHeight": 512,
      "maximumBytes": 26214400
    }
  ],
  "question": "Which portrait should I use, and do you want one scene or the complete eight-image set?",
  "variants": [
    "sheet-mask-mirror",
    "luxury-bathroom",
    "shooting-range",
    "yellow-pirelli-cap",
    "tropical-hat",
    "nyc-bench",
    "concrete-cafe",
    "bed-mask"
  ],
  "defaults": {
    "model": "nano-banana-2",
    "variant": "yellow-pirelli-cap",
    "aspectRatio": "3:4",
    "outputCountPerRun": 1
  },
  "modelRoutes": {
    "economy": "google/nano-banana-2-lite",
    "default": "google/nano-banana-2",
    "premium": "google/nano-banana-pro"
  }
}

{
  "progress": "Prepare -> Validate -> Transform -> Inspect",
  "attemptCapPerScene": 3,
  "stages": [
    {
      "id": "prepare",
      "output": "One run pinned to the portrait, selected lifestyle prompt, and model route.",
      "paid": false,
      "approvalRequired": false
    },
    {
      "id": "validate",
      "output": "The portrait and exact selected prompt checked locally.",
      "paid": false,
      "approvalRequired": false
    },
    {
      "id": "transform",
      "output": "One selected scene per paid prediction; repeat only for approved variants.",
      "paid": true,
      "approvalRequired": true
    },
    {
      "id": "inspect",
      "output": "Automatic file checks plus an actual visual review for every scene.",
      "paid": false,
      "approvalRequired": true
    }
  ]
}

{
  "sourceReference": {
    "creator": "@skaigenerated",
    "postUrl": "https://www.instagram.com/skaigenerated/p/Da8Wg1QFpAd/",
    "resourceUrl": "https://docs.google.com/document/d/1ZxKvu3LJSc83TRrpYfxQlLTK8-o5Skt8FRvlF4UBrUU/edit",
    "guide": "assets/source/guide.pdf",
    "referenceInset": "assets/source/reference-input.jpg",
    "verification": "The delivered Google Doc supplied Nano Banana Pro and eight exact prompts. The Instagram carousel supplied the eight matching source outputs.",
    "referenceNote": "The creator did not publish a separate original input, so the clean sheet-mask carousel scene is reused only as Wiggly's visual identity anchor."
  },
  "examples": [
    { "variant": "sheet-mask-mirror", "path": "assets/source/sheet-mask-mirror.jpg" },
    { "variant": "luxury-bathroom", "path": "assets/source/luxury-bathroom.jpg" },
    { "variant": "shooting-range", "path": "assets/source/shooting-range.jpg" },
    { "variant": "yellow-pirelli-cap", "path": "assets/source/yellow-pirelli-cap.jpg" },
    { "variant": "tropical-hat", "path": "assets/source/tropical-hat.jpg" },
    { "variant": "nyc-bench", "path": "assets/source/nyc-bench.jpg" },
    { "variant": "concrete-cafe", "path": "assets/source/concrete-cafe.jpg" },
    { "variant": "bed-mask", "path": "assets/source/bed-mask.jpg" }
  ]
}

{
  "automatic": [
    "Exactly 1 decodable JPG, PNG, or WebP output per run",
    "At least 640x800 pixels",
    "Aspect ratio within 0.02 of 3:4",
    "At least 50 KB"
  ],
  "visual": [
    "The reference identity remains recognizable unless the user explicitly requests a new subject",
    "The selected scene matches its exact packaged prompt",
    "Faces, hands, clothing, phones, glasses, and scene props have coherent geometry",
    "The framing feels like a believable smartphone or candid lifestyle photograph",
    "The result is photorealistic rather than CGI or illustration"
  ],
  "finalization": {
    "automaticPassRequired": true,
    "visualPassRequired": true,
    "reviewNotesRequired": true,
    "explicitApprovalFlag": "--approve-final"
  }
}

{
  "purpose": "Judge identity continuity, believable lifestyle styling, natural smartphone framing, prop geometry, and photographic realism across all eight gathered scenes.",
  "examples": [
    {
      "id": "yellow-pirelli-cap",
      "title": "Yellow Pirelli Cap Mirror Selfie",
      "imagePath": "assets/source/yellow-pirelli-cap.jpg",
      "model": "Nano Banana Pro",
      "whyItWorks": [
        "The bright shirt, cap embroidery, jewelry, and phone stay crisp",
        "Flat daylight keeps the mirror selfie casual",
        "The playful expression prevents the frame from feeling over-directed"
      ]
    },
    {
      "id": "luxury-bathroom",
      "title": "Luxury Bathroom Streetwear",
      "imagePath": "assets/source/luxury-bathroom.jpg",
      "model": "Nano Banana Pro",
      "whyItWorks": [
        "Layered streetwear remains readable inside the dark tiled room",
        "The raised cocktail glass creates a convincing candid action",
        "Warm hotel light balances the cool mirror reflection"
      ]
    },
    {
      "id": "shooting-range",
      "title": "Leather Vest Shooting Range",
      "imagePath": "assets/source/shooting-range.jpg",
      "model": "Nano Banana Pro",
      "whyItWorks": [
        "The three-quarter angle makes the stance easy to read",
        "Safety gear, lane number, target, and handgun retain useful detail",
        "Hard fluorescent light supports the gritty candid look"
      ]
    },
    {
      "id": "sheet-mask-mirror",
      "title": "Sheet Mask Bathroom Mirror Selfie",
      "imagePath": "assets/source/sheet-mask-mirror.jpg",
      "model": "Nano Banana Pro",
      "whyItWorks": [
        "The crinkled translucent mask looks physically worn",
        "Wet hair and dim stone surfaces sell the private bathroom moment",
        "The loose pose feels unfiltered rather than editorial"
      ]
    },
    {
      "id": "tropical-hat",
      "title": "Tropical Sky Hat Selfie",
      "imagePath": "assets/source/tropical-hat.jpg",
      "model": "Nano Banana Pro",
      "whyItWorks": [
        "The extreme low angle turns the blue sky into clean negative space",
        "Frayed canvas, mirrored lenses, beads, and mesh retain tactile texture",
        "Hard midday light feels true to a spontaneous vacation selfie"
      ]
    },
    {
      "id": "nyc-bench",
      "title": "NYC Street Bench",
      "imagePath": "assets/source/nyc-bench.jpg",
      "model": "Nano Banana Pro",
      "whyItWorks": [
        "Both full-body outfits remain distinct and readable",
        "Iced drinks and deadpan expressions keep the frame casually social",
        "Dappled street light avoids a studio-polished finish"
      ]
    },
    {
      "id": "concrete-cafe",
      "title": "Raw Concrete Café",
      "imagePath": "assets/source/concrete-cafe.jpg",
      "model": "Nano Banana Pro",
      "whyItWorks": [
        "Golden window light builds strong cinematic contrast",
        "Leather, satin, concrete, and wood keep separate material textures",
        "The reclined posture creates a quiet unbothered mood"
      ]
    },
    {
      "id": "bed-mask",
      "title": "Lying in Bed With a Sheet Mask",
      "imagePath": "assets/source/bed-mask.jpg",
      "model": "Nano Banana Pro",
      "whyItWorks": [
        "The overhead crop feels intimate and accidental",
        "Mask wrinkles, earbuds, tattoos, and bedding retain realistic detail",
        "Warm side light preserves the raw phone-photo character"
      ]
    }
  ]
}

{
  "id": "fake-it-till-you-make-it",
  "version": "1.0.0",
  "title": "Fake It Till You Make It",
  "description": "Turn one reference portrait into eight believable lifestyle posts spanning mirrors, streetwear, travel, nightlife, and quiet candid moments.",
  "status": "agent-ready",
  "owner": "Wiggly Studio",
  "source": {
    "creator": "@skaigenerated",
    "postUrl": "https://www.instagram.com/skaigenerated/p/Da8Wg1QFpAd/",
    "resourceUrl": "https://docs.google.com/document/d/1ZxKvu3LJSc83TRrpYfxQlLTK8-o5Skt8FRvlF4UBrUU/edit",
    "ctaKeyword": "AI",
    "modelShown": "Nano Banana Pro"
  },
  "outputs": [
    "1 inspected 3:4 image per selected lifestyle scene",
    "up to 8 finalized scene runs for the complete set",
    "state.json and quality-report.json for every scene"
  ]
}

{
  "name": "wiggly-fake-it-till-you-make-it-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=fake-it-till-you-make-it && node kit-smoke.mjs"
  },
  "dependencies": {
    "image-size": "2.0.2",
    "replicate": "1.4.0",
    "tsx": "4.20.6"
  }
}

{
  "slug": "fake-it-till-you-make-it",
  "version": "1.0.0",
  "promptPath": "prompts/yellow-pirelli-cap.txt",
  "promptVariants": {
    "sheet-mask-mirror": "prompts/sheet-mask-mirror.txt",
    "luxury-bathroom": "prompts/luxury-bathroom.txt",
    "shooting-range": "prompts/shooting-range.txt",
    "yellow-pirelli-cap": "prompts/yellow-pirelli-cap.txt",
    "tropical-hat": "prompts/tropical-hat.txt",
    "nyc-bench": "prompts/nyc-bench.txt",
    "concrete-cafe": "prompts/concrete-cafe.txt",
    "bed-mask": "prompts/bed-mask.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 / source model",
      "model": "google/nano-banana-pro",
      "family": "nano-banana",
      "aspectRatio": "3:4",
      "outputFormat": "jpg",
      "resolution": "1K"
    }
  },
  "expectedOutputs": 1,
  "maximumAttempts": 3,
  "smokeInputPath": "assets/source/reference-input.jpg",
  "smokeExamplePath": "assets/source/yellow-pirelli-cap.jpg",
  "minimumOutputWidth": 640,
  "minimumOutputHeight": 800,
  "minimumOutputBytes": 51200,
  "manualReview": [
    "recognizable reference identity",
    "selected lifestyle scene fidelity",
    "believable face, hands, clothing, and props",
    "natural smartphone framing",
    "photographic realism"
  ]
}