
Make the transformation obvious in one glance
- The native title cover names the visual recipe immediately
- Both people and the gaming scene remain recognizable
- The original-photo inset makes preservation easy to inspect
Wiggly / Format Lab /
Turn one photo into a bold retro American cartoon while preserving the exact people, pose, clothing, background, framing, and visible details.
One source image in. 1 inspected image out.
Judge identity, pose, clothing, scene, and composition preservation under a clean 1960s–1980s American cartoon treatment with bold outlines, flat color, simple cel shading, and vintage texture.








Exact gathered prompt
Transform the exact uploaded image into a full body illustration designed in a 1960s–1980s retro American cartoon style. Preserve the exact subject, facial identity, hairstyle, clothing, accessories, colors, proportions, pose, body language, facial expression, camera angle, framing, composition, perspective, lighting, and every visible detail from the original image. Do not redesign, reinterpret, simplify, replace, or invent any elements. The uploaded image must remain instantly recognizable, changing only the artistic style. The character should feature exaggerated rubber hose proportions, expressive body language, a slightly oversized head, simplified anatomy, elastic limbs, large classic oval cartoon eyes with simple black pupils, thin expressive eyebrows, rounded hands, clean geometric shapes, and a playful vintage personality while preserving the exact likeness, expression, and silhouette of the original subject. The illustration features thick bold black outlines, flat solid colors, minimal cel-style shading, subtle vintage film grain texture, slightly desaturated tones like old animation cels, smooth hand-drawn 2D linework, simple color blocking, soft retro print texture, and a classic mid-century American animation aesthetic. Preserve the original background exactly as shown in the uploaded image unless otherwise specified. Keep the original composition, framing, perspective, and camera angle exactly the same. Full body should remain visible if it is visible in the original image. High resolution, clean illustration, no realism, no 3D rendering, no anime, no Pixar, no Disney, no modern cartoon style, only authentic 1960s–1980s American retro animation aesthetics.
Source: @skaigenerated · model shown: Nano Banana Pro
Prepare -> Validate -> Transform -> Inspect
One run pinned to the photo, exact gathered prompt, and selected model route.
The 3:4 photo and prompt contract checked locally.
One retro cartoon image from one approved prediction.
Explicit approval required
Automatic file checks plus an actual visual review.
Explicit approval required
SKILL.md--- name: wiggly-80s-toon description: Turn one 3:4 photo into a retro American cartoon with the exact gathered SKAI prompt. --- # 80s Toon Use the packaged runner and exact prompt. Do not call Replicate separately or create another render path. From the extracted kit's `v3` directory: ```bash npm install npm run format:skai-image -- check --format=80s-toon npm run format:skai-image -- smoke --format=80s-toon ``` Ask one short question: > Which 3:4 photo should I turn into an 80s Toon, and should I use Nano Banana 2 (default), Lite (economy), or Pro (source-recommended)? 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 the source-recommended route: ```bash npm run format:skai-image -- init --format=80s-toon --run=<id> --input=<absolute-image-path> [--model=<route>] npm run format:skai-image -- validate --format=80s-toon --run=<id> npm run format:skai-image -- estimate --format=80s-toon --run=<id> ``` Stop after `estimate` and ask the user to approve the paid prediction. Only after explicit approval should you supply `--approve-paid`: ```bash npm run format:skai-image -- render --format=80s-toon --run=<id> --approve-paid npm run format:skai-image -- inspect --format=80s-toon --run=<id> npm run format:skai-image -- inspect --format=80s-toon --run=<id> --visual-pass --review-notes="<specific observations>" npm run format:skai-image -- finalize --format=80s-toon --run=<id> --approve-final ``` Hard rules: - Preserve the exact people, identity, hairstyle, clothing, accessories, colors, proportions, pose, body language, expression, lighting, background, framing, perspective, and composition. - Use thick bold black outlines, flat solid colors, minimal cel shading, clean geometric shapes, and smooth hand-drawn 2D linework. - Keep the playful vintage anatomy and classic oval eyes without redesigning or replacing the subject. - Use slightly desaturated old-cel tones, subtle film grain, and soft retro print texture. - Avoid realism, 3D rendering, anime, and modern glossy cartoon styling. - 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 the source-recommended route. - 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. - Return the finished image and `quality-report.json` to the user after finalization. - Never print, store, or commit `REPLICATE_API_TOKEN`.
requirements.json{
"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 SKAI source recommends Nano Banana Pro; Wiggly also exposes cheaper Nano Banana 2 Lite and Nano Banana 2 routes.",
"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."
]
}
inputs.json{
"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 an 80s Toon, and should I use Nano Banana 2 (default), Lite (economy), or Pro (source-recommended)?",
"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": "Nano Banana Pro"
}
pipeline.json{
"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 3:4 photo and prompt contract checked locally.", "paid": false, "approvalRequired": false },
{ "id": "transform", "output": "One retro cartoon image from one approved prediction.", "paid": true, "approvalRequired": true },
{ "id": "inspect", "output": "Automatic file checks plus an actual visual review.", "paid": false, "approvalRequired": true }
]
}
prompts/transform.txtTransform the exact uploaded image into a full body illustration designed in a 1960s–1980s retro American cartoon style. Preserve the exact subject, facial identity, hairstyle, clothing, accessories, colors, proportions, pose, body language, facial expression, camera angle, framing, composition, perspective, lighting, and every visible detail from the original image. Do not redesign, reinterpret, simplify, replace, or invent any elements. The uploaded image must remain instantly recognizable, changing only the artistic style. The character should feature exaggerated rubber hose proportions, expressive body language, a slightly oversized head, simplified anatomy, elastic limbs, large classic oval cartoon eyes with simple black pupils, thin expressive eyebrows, rounded hands, clean geometric shapes, and a playful vintage personality while preserving the exact likeness, expression, and silhouette of the original subject. The illustration features thick bold black outlines, flat solid colors, minimal cel-style shading, subtle vintage film grain texture, slightly desaturated tones like old animation cels, smooth hand-drawn 2D linework, simple color blocking, soft retro print texture, and a classic mid-century American animation aesthetic. Preserve the original background exactly as shown in the uploaded image unless otherwise specified. Keep the original composition, framing, perspective, and camera angle exactly the same. Full body should remain visible if it is visible in the original image. High resolution, clean illustration, no realism, no 3D rendering, no anime, no Pixar, no Disney, no modern cartoon style, only authentic 1960s–1980s American retro animation aesthetics.
quality.json{
"automatic": ["The source input is 3:4 within 0.02", "Exactly 1 decodable JPG, JPEG, PNG, or WebP output", "At least 1080x1440 pixels", "Aspect ratio matches the selected route within 0.02", "At least 50 KB"],
"visual": ["The exact people, facial identity, pose, body language, expression, clothing, accessories, background, framing, perspective, and composition remain recognizable", "Thick black outlines, flat solid colors, minimal cel shading, and clean hand-drawn linework replace realism", "Slightly oversized heads, elastic limbs, classic oval eyes, rounded hands, and simple geometry feel playful but preserve the source", "Subtle grain, slightly desaturated cel tones, and soft print texture create an authentic retro animation finish", "The image avoids realism, 3D rendering, anime, and modern glossy cartoon styling"],
"finalization": { "automaticPassRequired": true, "visualPassRequired": true, "reviewNotesRequired": true, "explicitApprovalFlag": "--approve-final" }
}