Replicate
google/nano-banana-2-lite · google/nano-banana-2 · google/nano-banana-pro
Generate the approved media in this recipe.
REPLICATE_API_TOKENTurn only the clothing, bag, and shoes in one fashion photo into handmade paper cutouts while keeping the person, pose, light, and setting photographic.
By Wiggly Studio · Updated July 2026

Shared recipe family
Paper Outfit belongs to Image Filters. These recipes share a runtime; adjacent examples are not separate Repos. The download on this page packages this specific recipe.
See the full recipe familyBefore you start
google/nano-banana-2-lite · google/nano-banana-2 · google/nano-banana-pro
Generate the approved media in this recipe.
REPLICATE_API_TOKENSetup, validation & inspection
Node.js >=22 · npm
Typical run estimate
About $0.067 on the default route and usually 2-4 min
Estimates describe the saved recipe, not a price guarantee. Confirm current provider pricing and approve any spend before generation. Your coding agent may have its own fees or usage limits. Never paste API keys into chat.
Included assets
The published package includes its agent instructions, input contract, and quality rules, plus 8 viewable asset references below. Reference media teaches the recipe; it is not a new result for your input.

Every published native image already contains exactly one original-photo inset, so Discover adds no second reference overlay. The final two CTA slides are intentionally excluded.

Every published native image already contains exactly one original-photo inset, so Discover adds no second reference overlay. The final two CTA slides are intentionally excluded.

Supplied creator reference—not a new Wiggly-generated result.

Supplied creator reference—not a new Wiggly-generated result.

Supplied creator reference—not a new Wiggly-generated result.

Supplied creator reference—not a new Wiggly-generated result.
Examples
7 saved examples for this recipe—not 7 separate Repos. Each example keeps its original version and provenance.







From input to output
From the published pipeline.json. The agent follows the packaged runtime and its approval gates.
Step 01
One run pinned to the source image, exact gathered prompt, and selected model route.
Step 02
The 3:4 fashion photo and prompt contract checked locally.
Step 03 · approval · provider
One realistic fashion photo with clothing, bag, and shoes replaced by handmade paper cutouts from one approved prediction.
Step 04 · approval
Automatic file checks plus an actual visual review.
Proof & quality
Judge photographic preservation, convincing handmade paper construction, clean cut edges, visible pencil texture, and edits limited to clothing, bag, and shoes.
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.
Every published native image already contains exactly one original-photo inset, so Discover adds no second reference overlay. The final two CTA slides are intentionally excluded.
Saved reference
Saved reference
These are the acceptance criteria in quality.json—not a claim that every pictured example passed the current version. Inspect each new output before finalizing.
Open the package
Actual files from the published v1.0.0 package. Expand any file to inspect the instructions, requirements, or evidence before sending the Repo to your agent.
# Wiggly Paper Outfit Format This runnable Repo preserves the exact prompt delivered by @skaigenerated and seven native carousel images. Every published image already includes one original-photo inset, so Wiggly does not add another. The final two CTA slides are intentionally excluded. Run from `v3`: ```bash npm install npm run format:skai-image -- check --format=paper-outfit npm run format:skai-image -- smoke --format=paper-outfit npm run format:skai-image -- init --format=paper-outfit --run=my-paper-outfit --input=/absolute/path/to/3-by-4-image.jpg npm run format:skai-image -- validate --format=paper-outfit --run=my-paper-outfit npm run format:skai-image -- estimate --format=paper-outfit --run=my-paper-outfit ``` 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=paper-outfit --run=my-paper-outfit --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 Wiggly's lower-cost Nano Banana routes and preserve the carousel's 3:4 output shape. Re-run `estimate` immediately before approval because provider pricing can change.
--- name: wiggly-paper-outfit description: Turn only the clothing, bag, and shoes in one 3:4 fashion photo into handmade paper cutouts using the exact gathered SKAI prompt. --- # Paper Outfit 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=paper-outfit npm run format:skai-image -- smoke --format=paper-outfit ``` Ask one short question: > Which 3:4 fashion photo should I turn into a handmade paper-outfit editorial? 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=paper-outfit --run=<id> --input=<absolute-image-path> [--model=<route>] npm run format:skai-image -- validate --format=paper-outfit --run=<id> npm run format:skai-image -- estimate --format=paper-outfit --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=paper-outfit --run=<id> --approve-paid npm run format:skai-image -- inspect --format=paper-outfit --run=<id> npm run format:skai-image -- inspect --format=paper-outfit --run=<id> --visual-pass --review-notes="<specific observations>" npm run format:skai-image -- finalize --format=paper-outfit --run=<id> --approve-final ``` Hard rules: - Preserve the face, hair, skin, expression, makeup, body, pose, lighting, shadows, background, crop, and perspective. - Apply the effect only to clothing, bag, and shoes. - Make each transformed piece look like a physical white-paper cutout with visible colored pencil, paint marks, cut edges, and layered construction. - Keep the person fully photographic; never turn the model into a drawing or apply a global digital filter. - Use a user-approved 3:4 input before validation. - 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. - 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 fashion photo should I turn into a handmade paper-outfit editorial?",
"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 fashion photo and prompt contract checked locally.",
"paid": false,
"approvalRequired": false
},
{
"id": "transform",
"output": "One realistic fashion photo with clothing, bag, and shoes replaced by handmade paper cutouts 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/Da2XgvnCqOG/",
"resourceUrl": "https://docs.google.com/document/d/1LjajzBWHChmEmc_Ujjwv9cRnQ8WRs1KouNBIPQ0PFG4/mobilebasic",
"guide": "assets/source/guide.txt",
"nativeHero": "assets/source/skai-hero.jpg",
"smokeInput": "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": "Every published native image already contains exactly one original-photo inset, so Discover adds no second reference overlay. The final two CTA slides are intentionally excluded."
},
"examples": [
{ "id": "native-hero", "path": "assets/source/skai-hero.jpg", "provenance": "@skaigenerated carousel title cover" },
{ "id": "amalfi-balcony", "path": "assets/source/skai-example-01.jpg", "provenance": "@skaigenerated carousel" },
{ "id": "coastal-terrace", "path": "assets/source/skai-example-02.jpg", "provenance": "@skaigenerated carousel" },
{ "id": "ice-cream-street", "path": "assets/source/skai-example-03.jpg", "provenance": "@skaigenerated carousel" },
{ "id": "front-step", "path": "assets/source/skai-example-04.jpg", "provenance": "@skaigenerated carousel" },
{ "id": "resort-wall", "path": "assets/source/skai-example-05.jpg", "provenance": "@skaigenerated carousel" },
{ "id": "museum-hall", "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 face, hair, skin, expression, makeup, body, pose, lighting, shadows, background, and crop remain photographic and recognizable",
"Only clothing, bag, and shoes receive the handmade paper-cutout treatment",
"The transformed pieces look like physical white paper drawn with visible colored pencil and paint marks",
"Cut edges, layered shapes, and attachment to the original silhouette feel intentional and coherent",
"The person is not turned into an illustration and the result does not resemble a global digital filter",
"There are no malformed hands, limbs, facial features, or obviously synthetic background details"
],
"finalization": {
"automaticPassRequired": true,
"visualPassRequired": true,
"reviewNotesRequired": true,
"explicitApprovalFlag": "--approve-final"
}
}
{
"purpose": "Judge photographic preservation, convincing handmade paper construction, clean cut edges, visible pencil texture, and edits limited to clothing, bag, and shoes.",
"examples": [
{
"id": "native-hero",
"title": "Explain the paper-outfit trick in one glance",
"imagePath": "assets/source/skai-hero.jpg",
"model": "GPT Image 2 · SKAI source",
"whyItWorks": [
"The title, result, and single original-photo inset explain the transformation immediately",
"The face, pose, skin, lighting, street, and shadows remain photographic",
"The dress and bag read as physical paper cutouts laid over the real photo"
]
},
{
"id": "amalfi-balcony",
"title": "Keep a sunny travel portrait completely real",
"imagePath": "assets/source/skai-example-01.jpg",
"model": "GPT Image 2 · SKAI source",
"whyItWorks": [
"The source inset proves the person, pose, terrace, and sea stay recognizable",
"Pencil marks and white paper texture appear only on the outfit and accessories",
"Cut edges and layered pieces feel handmade instead of digitally recolored"
]
},
{
"id": "coastal-terrace",
"title": "Let the background keep all of its detail",
"imagePath": "assets/source/skai-example-02.jpg",
"model": "GPT Image 2 · SKAI source",
"whyItWorks": [
"The face, hair, body, architecture, and coast remain unchanged",
"The gingham top, skirt, and shoes share one coherent paper treatment",
"The effect stays readable without flattening the photograph"
]
},
{
"id": "ice-cream-street",
"title": "Carry the treatment across a full outfit",
"imagePath": "assets/source/skai-example-03.jpg",
"model": "GPT Image 2 · SKAI source",
"whyItWorks": [
"The subject, ice cream, car, street, and lighting remain photographic",
"Top, shorts, and bag use matching drawn texture and crisp cut edges",
"The paper pieces sit over the body while respecting pose and silhouette"
]
},
{
"id": "front-step",
"title": "Make layered separates feel handmade",
"imagePath": "assets/source/skai-example-04.jpg",
"model": "GPT Image 2 · SKAI source",
"whyItWorks": [
"The portrait and doorway remain realistic and recognizable",
"Top and skirt use distinct paper colors without changing the person",
"White outlines and pencil strokes make the physical overlay legible"
]
},
{
"id": "resort-wall",
"title": "Preserve a soft candid pose",
"imagePath": "assets/source/skai-example-05.jpg",
"model": "GPT Image 2 · SKAI source",
"whyItWorks": [
"The face, skin, arms, body, wall, plants, and light remain photographic",
"Each garment and accessory becomes its own cut-paper object",
"The new pieces still follow the original pose and proportions"
]
},
{
"id": "museum-hall",
"title": "Keep dramatic architecture outside the edit",
"imagePath": "assets/source/skai-example-06.jpg",
"model": "GPT Image 2 · SKAI source",
"whyItWorks": [
"The person, pose, hall, exhibits, and golden light stay real",
"The floral dress gains visible paper texture and hand-drawn pigment",
"The limited edit makes the result feel like a tactile fashion collage"
]
}
]
}
{
"id": "paper-outfit",
"version": "1.0.0",
"title": "Paper Outfit",
"description": "Turn only the clothing, bag, and shoes in one fashion photo into handmade paper cutouts while keeping the person and photograph real.",
"status": "agent-ready",
"owner": "Wiggly Studio",
"source": {
"creator": "@skaigenerated",
"postUrl": "https://www.instagram.com/skaigenerated/p/Da2XgvnCqOG/",
"resourceUrl": "https://docs.google.com/document/d/1LjajzBWHChmEmc_Ujjwv9cRnQ8WRs1KouNBIPQ0PFG4/mobilebasic",
"ctaKeyword": "AI",
"modelShown": "GPT Image 2"
},
"outputs": [
"1 inspected 3:4 realistic fashion photo with handmade paper outfit cutouts",
"state.json with model and prediction provenance",
"quality-report.json with automatic and visual inspection"
]
}
{
"name": "wiggly-paper-outfit-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=paper-outfit && node kit-smoke.mjs"
},
"dependencies": {
"image-size": "2.0.2",
"replicate": "1.4.0",
"tsx": "4.20.6"
}
}
{
"slug": "paper-outfit",
"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 photographic face, body, pose, expression, lighting, shadows, background, crop, and perspective",
"edits limited to clothing, bag, and shoes",
"physical white-paper texture, colored-pencil marks, paint strokes, cut edges, and layered construction",
"paper pieces aligned cleanly to the original outfit silhouette",
"no illustrated person, global filter treatment, malformed anatomy, or synthetic background changes"
]
}
Run it with a coding agent
The agent reads this version’s instructions, checks the requirements, and walks you through the approved workflow. Review the inputs and estimate before starting.
Typical run
About $0.067 on the default route and usually 2-4 min
You provide
One 3:4 JPEG, PNG, or WebP fashion photo at least 512px on both axes · A Replicate API token only when generation is approved
Output
One inspected 3:4 paper-outfit editorial plus prediction and quality provenance