Stone Age Caveman Transform · Open Skill 공개 스킬

Stone Age Caveman Transform

**in** An adult photo with the face clear and visible. **out** Same face, brow ridge, wind-burned skin, fur at the shoulder. Your photo -> stone age portrait. I kept the likeness and changed only the era around it. Pick a setting: cave mouth, riverside camp, hunting plain. Intensity goes subtle weathered or full. If the face is tiny or blurred, send another. Sorry, that one is on me.

@CalderVoss

Roleplay

1 0 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321699/2026-10-23/379j9kaf.webp

# Stone Age Caveman Transform

Brow ridge, wind-burned skin, fur across the shoulder. The face in your photo stays exactly yours while it steps back into the stone age, firelit and wild.

## When to use

- The user wants their photo turned into a prehistoric caveman portrait (caveman filter, stone-age ancestor look, hunter-gatherer makeover, primal portrait)
- A variation on a previous result: subtle weathered version

Not for: Video output (use a video skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult, face clear and unobstructed. Ask for another photo if the face is tiny, blurred, heavily filtered or hidden |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Intensity | No | `full transformation` | full transformation (default), subtle weathered version, or user-described |
| Setting | No | `firelit cave mouth` | firelit cave mouth (default), riverside fishing camp at dawn, open hunting plain at dusk, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 2:3, 9:16 on request |

- If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use.
- Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors.

## Steps

1. Read `references/image-edit.md` for prompt structure.
2. **Identity read**: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')`.
3. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Stone Age Caveman Transform', entity_type='skill_generation')`. Merge the user's details and options into the template.
4. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely.
5. Reply in one or two sentences, e.g. "Here it is: your stone age caveman transform. Shall I do a version with subtle weathered version?" Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: the same adult person from the photo transformed into a prehistoric caveman look with <intensity: full transformation (default), subtle weathered version, or user-described>, keeping every facial feature, eye shape and expression recognizable; heavy brow, sun-cracked skin, tangled long hair and a short rough beard, wrapped in rough hides and animal furs, bone beads and a flint blade at the belt, set in <setting: firelit cave mouth with hides and spears (default), riverside fishing camp at dawn, or open hunting plain at dusk>, warm ember rim light, cinematic 4K realism, fully clothed in fur. <user details and options>. Make the change unmistakable at first glance: full costume, bold silhouette, character makeup or prosthetic details, themed props and set, dramatic hero lighting. Not a subtle filter. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text unless requested.
```

Quality bar: Make the change unmistakable: a strong silhouette shift and full costume, not just ears or face paint, while the face stays the same person.

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never in