Cinematic Photographer

# Wiggly Cinematic Photographer Format

This runnable Repo preserves the exact prompt and source example gathered from @skaigenerated. It generates one moody editorial portrait through Replicate and refuses to finalize an uninspected image.

Run from `v3`:

```bash
npm install
npm run format:skai-image -- smoke --format=cinematic-photographer
npm run format:skai-image -- init --format=cinematic-photographer --run=my-portrait
npm run format:skai-image -- validate --format=cinematic-photographer --run=my-portrait
npm run format:skai-image -- estimate --format=cinematic-photographer --run=my-portrait
```

Generation requires `REPLICATE_API_TOKEN` and explicit approval:

```bash
npm run format:skai-image -- render --format=cinematic-photographer --run=my-portrait --approve-paid
```

View the output, record visual notes with `inspect --visual-pass --review-notes="..."`, then use `finalize --approve-final`.

Model routes:

- Economy: `google/nano-banana-2-lite`
- Default 4:5: `google/nano-banana-2`
- Source model: `openai/gpt-image-2` at its supported 2:3 portrait ratio

No Replicate proof call was made while packaging this Repo. The included source output and guide are the proof artifacts.

---
name: wiggly-cinematic-photographer
description: Create one moody editorial photographer portrait from the exact gathered SKAI prompt.
---

# Cinematic Photographer

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

Ask one short question first:

> Should I use the exact packaged photographer concept, or do you want to change the subject while keeping the cinematic recipe?

Use Nano Banana 2 by default, Nano Banana 2 Lite for economy, or GPT Image 2 when the user asks for the source model. The exact source prompt is the validated default.

```bash
npm run format:skai-image -- check --format=cinematic-photographer
npm run format:skai-image -- init --format=cinematic-photographer --run=<id>
npm run format:skai-image -- validate --format=cinematic-photographer --run=<id>
npm run format:skai-image -- estimate --format=cinematic-photographer --run=<id>
npm run format:skai-image -- render --format=cinematic-photographer --run=<id> --approve-paid
npm run format:skai-image -- inspect --format=cinematic-photographer --run=<id>
npm run format:skai-image -- inspect --format=cinematic-photographer --run=<id> --visual-pass --review-notes="<specific observations>"
npm run format:skai-image -- finalize --format=cinematic-photographer --run=<id> --approve-final
```

Hard rules:

- Keep the packaged prompt exact unless the user explicitly asks to change the subject.
- Validate before spending.
- Never generate without `--approve-paid`.
- Persist and resume the same prediction ID.
- Never exceed three attempts.
- View the actual output and record notes before `--approve-final`.
- 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",
        "openai/gpt-image-2"
      ]
    }
  ],
  "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.",
    "The gathered source example is the visual proof.",
    "Paid generation requires explicit approval and is capped at three attempts."
  ]
}

{
  "required": [],
  "question": "Should I use the exact packaged photographer concept, or do you want to change the subject while keeping the cinematic recipe?",
  "defaults": {
    "concept": "exact packaged prompt",
    "model": "nano-banana-2",
    "aspectRatio": "4:5",
    "outputCount": 1
  },
  "modelRoutes": {
    "economy": "google/nano-banana-2-lite",
    "default": "google/nano-banana-2",
    "sourceModel": "openai/gpt-image-2"
  }
}

{
  "progress": "Prepare -> Validate -> Generate -> Inspect",
  "attemptCap": 3,
  "stages": [
    {
      "id": "prepare",
      "output": "A run pinned to the exact gathered prompt and chosen model route.",
      "paid": false,
      "approvalRequired": false
    },
    {
      "id": "validate",
      "output": "Prompt, output contract, and provider route checked locally.",
      "paid": false,
      "approvalRequired": false
    },
    {
      "id": "generate",
      "output": "One portrait from the selected Replicate model.",
      "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/DbWAcxjDJYc/",
    "resourceUrl": "https://docs.google.com/document/d/1_78s28UMB0Qz4DT7Xpm_EpFNClUKw0oZzkJqc1vZv-4/edit",
    "guide": "assets/source/guide.pdf",
    "exampleOutput": "assets/source/example-output.png",
    "styleReference": "assets/source/style-reference.jpg",
    "promptPath": "prompts/transform.txt",
    "verification": "Prompt and image extracted from the downloaded Google Doc and visually checked against the rendered guide. The style reference is a second finished example from the source Instagram carousel; this text-to-image recipe has no original input photo."
  }
}

{
  "automatic": [
    "Exactly one decodable image",
    "At least 640x800",
    "At least 50 KB",
    "Aspect ratio matches the chosen model route",
    "SHA-256 provenance is recorded"
  ],
  "manualReview": [
    "Face, eyes, fingers, and camera geometry are coherent",
    "The portrait reads as a real editorial photograph",
    "Lighting is moody and low-key without losing the face",
    "The subject and camera stay sharply prioritized",
    "Film grain adds texture without destroying detail"
  ],
  "finalizationGate": [
    "Automatic checks pass",
    "The actual image is viewed",
    "Specific visual notes are recorded",
    "--approve-final is present"
  ]
}

{
  "purpose": "Judge cinematic realism, camera anatomy, lighting, shallow focus, and film texture against the gathered source example.",
  "examples": [
    {
      "id": "skai-cinematic-photographer",
      "type": "source-reference",
      "title": "Cinematic photographer source proof",
      "imagePath": "assets/source/example-output.png",
      "styleReferencePath": "assets/source/style-reference.jpg",
      "guidePath": "assets/source/guide.pdf",
      "sourceUrl": "https://www.instagram.com/p/DbWAcxjDJYc/",
      "model": "GPT Image 2",
      "whyItWorks": [
        "The camera and face share crisp priority",
        "Low-key light still preserves warm skin detail",
        "The background stays minimal and cinematic",
        "Film grain supports the editorial finish"
      ]
    }
  ]
}

{
  "id": "cinematic-photographer",
  "version": "1.0.0",
  "title": "Cinematic Photographer",
  "description": "Create a moody editorial portrait of a photographer with tactile film detail.",
  "status": "agent-ready",
  "owner": "Wiggly Studio",
  "source": {
    "creator": "@skaigenerated",
    "postUrl": "https://www.instagram.com/p/DbWAcxjDJYc/",
    "resourceUrl": "https://docs.google.com/document/d/1_78s28UMB0Qz4DT7Xpm_EpFNClUKw0oZzkJqc1vZv-4/edit",
    "ctaKeyword": "AI",
    "modelShown": "GPT Image 2"
  },
  "outputs": [
    "1 portrait image",
    "state.json with model and prediction provenance",
    "quality-report.json with automatic and visual inspection"
  ]
}

{
  "name": "wiggly-cinematic-photographer-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 && node kit-smoke.mjs"
  },
  "dependencies": {
    "image-size": "2.0.2",
    "replicate": "1.4.0",
    "tsx": "4.20.6"
  }
}

{
  "slug": "cinematic-photographer",
  "version": "1.0.0",
  "promptPath": "prompts/transform.txt",
  "input": {
    "mode": "none"
  },
  "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": "4:5",
      "outputFormat": "jpg"
    },
    "nano-banana-2": {
      "label": "Nano Banana 2",
      "lane": "default",
      "model": "google/nano-banana-2",
      "family": "nano-banana",
      "aspectRatio": "4:5",
      "outputFormat": "jpg",
      "resolution": "1K"
    },
    "gpt-image-2": {
      "label": "GPT Image 2",
      "lane": "source model",
      "model": "openai/gpt-image-2",
      "family": "gpt-image",
      "aspectRatio": "2:3",
      "outputFormat": "jpeg",
      "quality": "medium"
    }
  },
  "expectedOutputs": 1,
  "maximumAttempts": 3,
  "smokeExamplePath": "assets/source/example-output.png",
  "minimumOutputWidth": 640,
  "minimumOutputHeight": 800,
  "minimumOutputBytes": 51200,
  "manualReview": [
    "face and camera anatomy",
    "moody low-key lighting",
    "shallow depth of field",
    "editorial realism",
    "film grain without muddy detail"
  ]
}