Soft Glow Filter

# Wiggly Soft Glow Filter Format

This runnable Repo preserves the exact prompt delivered by @skaigenerated, the
native title cover, six native before-and-after examples, and one extracted
source inset for a truthful hero comparison. The final two carousel CTA slides
are intentionally excluded.

Run from `v3`:

```bash
npm install
npm run format:skai-image -- check --format=soft-glow-filter
npm run format:skai-image -- smoke --format=soft-glow-filter
npm run format:skai-image -- init --format=soft-glow-filter --run=my-soft-glow --input=/absolute/path/to/3-by-4-image.jpg
npm run format:skai-image -- validate --format=soft-glow-filter --run=my-soft-glow
npm run format:skai-image -- estimate --format=soft-glow-filter --run=my-soft-glow
```

The input must already be 3:4 so the fixed output route can preserve the source
framing. Add `--model=nano-banana-2-lite` or `--model=nano-banana-pro` to
`init` to select the economy or premium route.

Generation requires `REPLICATE_API_TOKEN`. Stop after `estimate` and get the
user's explicit approval before supplying the paid flag:

```bash
npm run format:skai-image -- render --format=soft-glow-filter --run=my-soft-glow --approve-paid
```

No Replicate proof call was made while packaging this Repo.

- Economy: `google/nano-banana-2-lite`
- Default: `google/nano-banana-2`
- Premium: `google/nano-banana-pro`
- Model named in the source guide: `openai/gpt-image-2`

The source model is recorded for provenance. The runnable lanes use the
lower-cost Nano Banana routes requested for Wiggly and preserve the carousel's
3:4 output shape. Re-run `estimate` immediately before approval because
provider pricing can change.

---
name: wiggly-soft-glow-filter
description: Give one existing 3:4 photo a realistic soft-glow film grade and restrained handwritten memory captions using the exact gathered SKAI prompt.
---

# Soft Glow Filter

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

From the extracted kit's `v3` directory, prepare the local runner first:

```bash
npm install
npm run format:skai-image -- check --format=soft-glow-filter
npm run format:skai-image -- smoke --format=soft-glow-filter
```

Ask one short question:

> Which 3:4 photo should I turn into a soft-glow memory?

Then initialize the free run. Omit `--model` for Nano Banana 2, or add
`--model=nano-banana-2-lite` for economy or `--model=nano-banana-pro` for
premium:

```bash
npm run format:skai-image -- init --format=soft-glow-filter --run=<id> --input=<absolute-image-path> [--model=<route>]
npm run format:skai-image -- validate --format=soft-glow-filter --run=<id>
npm run format:skai-image -- estimate --format=soft-glow-filter --run=<id>
```

Stop after `estimate` and ask the user to approve the paid prediction. Only
after the user explicitly approves the cost should you supply `--approve-paid`:

```bash
npm run format:skai-image -- render --format=soft-glow-filter --run=<id> --approve-paid
npm run format:skai-image -- inspect --format=soft-glow-filter --run=<id>
npm run format:skai-image -- inspect --format=soft-glow-filter --run=<id> --visual-pass --review-notes="<specific observations>"
npm run format:skai-image -- finalize --format=soft-glow-filter --run=<id> --approve-final
```

Hard rules:

- Preserve the subject, face, pose, background, framing, and all key details.
- Use a user-approved 3:4 input before validation so the fixed route can preserve composition honestly.
- 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.
- Add only 2–5 clean captions, each 1–3 words, chosen from the supplied list.
- Keep caption lettering thin, handwritten, and pastel white, cream, or butter yellow with only subtle sketch arrows.
- Keep the result realistic and natural; use restrained glow, blur, grain, and vintage film texture.
- Never add emojis, hashtags, long text, or cheesy quotes.
- Validate and estimate before spending, pause for explicit user approval, 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 source guide names GPT Image 2; Wiggly's runnable lanes use Nano Banana 2 Lite, Nano Banana 2, and Nano Banana Pro.",
    "No Replicate proof call was made for this package.",
    "One render attempt is one paid prediction.",
    "Paid generation requires explicit approval and is capped at three attempts."
  ]
}

{
  "required": [
    {
      "id": "image",
      "type": "image",
      "formats": ["jpg", "png", "webp"],
      "minimumWidth": 512,
      "minimumHeight": 512,
      "maximumBytes": 26214400,
      "aspectRatio": "3:4",
      "aspectRatioTolerance": 0.02
    }
  ],
  "question": "Which 3:4 photo should I turn into a soft-glow memory?",
  "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"
  },
  "sourceModel": "openai/gpt-image-2"
}

{
  "progress": "Prepare -> Validate -> Transform -> Inspect",
  "attemptCap": 3,
  "stages": [
    {
      "id": "prepare",
      "output": "One run pinned to the source image, exact gathered prompt, and selected model route.",
      "paid": false,
      "approvalRequired": false
    },
    {
      "id": "validate",
      "output": "The 3:4 image and prompt contract checked locally.",
      "paid": false,
      "approvalRequired": false
    },
    {
      "id": "transform",
      "output": "One realistic soft-glow film image with restrained handwritten captions 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/skaigenerated/p/Da2XzrdCvEQ/",
    "resourceUrl": "https://docs.google.com/document/d/1r474WFlLhQfs3V1bb3l8jKr5OR9HiNJNc52xVTrjxv0/mobilebasic",
    "guide": "assets/source/guide.txt",
    "nativeHero": "assets/source/skai-hero.jpg",
    "referenceInset": "assets/source/reference-input.jpg",
    "verification": "The delivered Google Doc supplied the exact GPT Image 2 prompt. The Instagram carousel supplied one native 3:4 title cover and six native 3:4 transformation examples.",
    "referenceNote": "The title cover does not contain a before image, so Discover adds exactly one reference inset extracted from the first native comparison. Each nested source example already contains its own native inset. The two CTA slides are intentionally excluded."
  },
  "examples": [
    { "id": "native-hero", "path": "assets/source/skai-hero.jpg", "provenance": "@skaigenerated carousel title cover" },
    { "id": "mountain-seat", "path": "assets/source/skai-example-01.jpg", "provenance": "@skaigenerated carousel" },
    { "id": "ridge-overlook", "path": "assets/source/skai-example-02.jpg", "provenance": "@skaigenerated carousel" },
    { "id": "summit-rest", "path": "assets/source/skai-example-03.jpg", "provenance": "@skaigenerated carousel" },
    { "id": "motorbike-road", "path": "assets/source/skai-example-04.jpg", "provenance": "@skaigenerated carousel" },
    { "id": "forest-rock", "path": "assets/source/skai-example-05.jpg", "provenance": "@skaigenerated carousel" },
    { "id": "creek-log", "path": "assets/source/skai-example-06.jpg", "provenance": "@skaigenerated carousel" }
  ]
}

{
  "automatic": [
    "The source input is 3:4 within 0.02 so composition can be preserved",
    "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": [
    "The subject, face, pose, background, framing, and key details remain recognizable",
    "Soft glow, gentle blur, dot grain, and vintage film texture remain restrained and photographic",
    "The image contains only 2–5 clean handwritten captions of 1–3 words each",
    "Every caption comes from the supplied phrase list and sits on a readable background area",
    "Lettering is thin pastel white, cream, or butter yellow with only subtle sketch arrows",
    "There are no emojis, hashtags, long captions, cheesy quotes, or obviously synthetic details"
  ],
  "finalization": {
    "automaticPassRequired": true,
    "visualPassRequired": true,
    "reviewNotesRequired": true,
    "explicitApprovalFlag": "--approve-final"
  }
}

{
  "purpose": "Judge source preservation, realistic soft glow, restrained blur and film grain, clean handwritten memory captions, readable placement, and natural photographic detail.",
  "examples": [
    {
      "id": "native-hero",
      "title": "Make the format readable in one glance",
      "imagePath": "assets/source/skai-hero.jpg",
      "model": "GPT Image 2 · SKAI source",
      "whyItWorks": [
        "The title and primary result explain the visual recipe immediately",
        "The subject and mountain setting remain photographic",
        "Soft texture and small handwritten notes preview the finished treatment"
      ]
    },
    {
      "id": "mountain-seat",
      "title": "Turn a summit photo into a saved memory",
      "imagePath": "assets/source/skai-example-01.jpg",
      "model": "GPT Image 2 · SKAI source",
      "whyItWorks": [
        "The source inset proves the person, pose, clothing, and location stay recognizable",
        "Glow and film softness change the mood without replacing the scene",
        "Three short captions sit in readable areas and support the photograph"
      ]
    },
    {
      "id": "ridge-overlook",
      "title": "Let a wide landscape keep its scale",
      "imagePath": "assets/source/skai-example-02.jpg",
      "model": "GPT Image 2 · SKAI source",
      "whyItWorks": [
        "The figure and ridge remain the same recognizable composition",
        "Muted grain and haze feel like a film treatment instead of a new illustration",
        "The sparse captions leave the landscape room to breathe"
      ]
    },
    {
      "id": "summit-rest",
      "title": "Keep a playful pose while softening the frame",
      "imagePath": "assets/source/skai-example-03.jpg",
      "model": "GPT Image 2 · SKAI source",
      "whyItWorks": [
        "Both people, their pose, and the open mountain background survive",
        "The light remains believable beneath a gentle vintage finish",
        "Caption placement avoids faces and the busiest parts of the image"
      ]
    },
    {
      "id": "motorbike-road",
      "title": "Make a group ride feel archival",
      "imagePath": "assets/source/skai-example-04.jpg",
      "model": "GPT Image 2 · SKAI source",
      "whyItWorks": [
        "The riders, bikes, road, and mountain geometry remain intact",
        "The softer palette carries a coherent memory-dump mood",
        "Short notes and arrows stay readable without covering the group"
      ]
    },
    {
      "id": "forest-rock",
      "title": "Give a quiet forest stop a gentle glow",
      "imagePath": "assets/source/skai-example-05.jpg",
      "model": "GPT Image 2 · SKAI source",
      "whyItWorks": [
        "The seated person and wooded trail preserve their source relationship",
        "Glow, grain, and subdued greens remain natural",
        "Two restrained captions add context without turning into a poster"
      ]
    },
    {
      "id": "creek-log",
      "title": "Keep texture alive in a darker scene",
      "imagePath": "assets/source/skai-example-06.jpg",
      "model": "GPT Image 2 · SKAI source",
      "whyItWorks": [
        "The person, log, creek, and foliage remain recognizable",
        "The vintage softness does not erase the environmental detail",
        "Small pale captions hold up against a busier forest background"
      ]
    }
  ]
}

{
  "id": "soft-glow-filter",
  "version": "1.0.0",
  "title": "Soft Glow Filter",
  "description": "Give one existing photo a realistic soft cinematic glow, gentle film texture, and a few restrained handwritten memory captions without changing the subject or scene.",
  "status": "agent-ready",
  "owner": "Wiggly Studio",
  "source": {
    "creator": "@skaigenerated",
    "postUrl": "https://www.instagram.com/skaigenerated/p/Da2XzrdCvEQ/",
    "resourceUrl": "https://docs.google.com/document/d/1r474WFlLhQfs3V1bb3l8jKr5OR9HiNJNc52xVTrjxv0/mobilebasic",
    "ctaKeyword": "AI",
    "modelShown": "GPT Image 2"
  },
  "outputs": [
    "1 inspected 3:4 realistic soft-glow memory image",
    "state.json with model and prediction provenance",
    "quality-report.json with automatic and visual inspection"
  ]
}

{
  "name": "wiggly-soft-glow-filter-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=soft-glow-filter && node kit-smoke.mjs"
  },
  "dependencies": {
    "image-size": "2.0.2",
    "replicate": "1.4.0",
    "tsx": "4.20.6"
  }
}

{
  "slug": "soft-glow-filter",
  "version": "1.0.0",
  "promptPath": "prompts/transform.txt",
  "input": {
    "mode": "image",
    "formats": ["jpg", "png", "webp"],
    "minimumWidth": 512,
    "minimumHeight": 512,
    "maximumBytes": 26214400,
    "aspectRatio": "3:4",
    "aspectRatioTolerance": 0.02
  },
  "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",
      "costEstimate": "about $0.034 per output image at the current listed rate",
      "timeEstimate": "usually 5-60 seconds"
    },
    "nano-banana-2": {
      "label": "Nano Banana 2",
      "lane": "default",
      "model": "google/nano-banana-2",
      "family": "nano-banana",
      "aspectRatio": "3:4",
      "outputFormat": "jpg",
      "resolution": "1K",
      "costEstimate": "about $0.067 per 1K output image at the current listed rate",
      "timeEstimate": "usually 10-120 seconds"
    },
    "nano-banana-pro": {
      "label": "Nano Banana Pro",
      "lane": "premium",
      "model": "google/nano-banana-pro",
      "family": "nano-banana",
      "aspectRatio": "3:4",
      "outputFormat": "jpg",
      "resolution": "1K",
      "costEstimate": "about $0.15 per 1K output image at the current listed rate",
      "timeEstimate": "usually 30-180 seconds"
    }
  },
  "expectedOutputs": 1,
  "maximumAttempts": 3,
  "smokeInputPath": "assets/source/reference-input.jpg",
  "smokeExamplePath": "assets/source/skai-example-01.jpg",
  "minimumOutputWidth": 640,
  "minimumOutputHeight": 800,
  "minimumOutputBytes": 51200,
  "manualReview": [
    "recognizable source subject, face, pose, background, framing, and key details",
    "soft cinematic glow with gentle blur, dot grain, and a restrained vintage film feel",
    "only 2–5 handwritten captions, each 1–3 words and selected from the supplied list",
    "readable text placement in thin pastel white, cream, or butter yellow",
    "subtle sketch arrows with no emojis, hashtags, long text, or cheesy quotes",
    "fully realistic and natural finish without obviously synthetic details"
  ]
}