Flashlit Polaroid Duo · skill publik Open Skill

Flashlit Polaroid Duo

I like the straight-on flash and plain white curtain backdrop. It gives me that nostalgic instant-film look without much fuss. The soft blur and grain fit a cel-bright anime still, while the handheld snacks keep the frame casual. **from the floor:** **tips from me:** - add an adult photo if you want the face preserved - use the woman and man references for each adult identity - keep the default handheld snacks, or select no props - use 3:4 by default, or ask for 1:1 or 4:5 post what you make here, especially your own anime portraits.

@CalebMonroe

Beauty

1 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284955/2026-10-17/72uxkzsk.webp

# Flashlit Polaroid Duo

Flash, curtains, soft blur. A nostalgic two-person instant-film snapshot: frontal flash, slight blur, grain, handheld snacks, before plain white curtains.

## When to use

- The user wants a friendly two-person instant-film snapshot with frontal flash before white curtains (flashlit polaroid duo, nostalgic party flash photo, couple instant snapshot)
- A variation on a previous result: handheld snacks

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Person photo | No | — | Optional; if given, the face is preserved |
| Woman reference | No | — | identity photo |
| Man reference | No | — | identity photo |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Props | No | `handheld snacks or drinks` | handheld snacks or drinks (default), no props, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 4:5 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. Fill the template below from the user's description. Use the tuned defaults for anything they leave out; ask one short question only if the subject itself is unclear.
3. If a person photo is given: `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.')` and add the identity clause.
4. With reference images: `generate_image(prompt=<PROMPT>, input_urls=[refs...], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Flashlit Polaroid Duo', entity_type='skill_generation')`; without: the same call with `model='t2i.hd'` and no `input_urls`.
5. **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.
6. Reply in one or two sentences, e.g. "Your flashlit polaroid duo is ready. Want another take with handheld snacks?" Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
<if photo: The same adult from the reference: <identity line>.> Intentional changes: a friendly two-person instant-film snapshot of <adult woman: from the woman reference if given, else a smiling woman in her twenties> and <adult man: from the man reference if given, else a smiling man in his twenties> standing close before plain white curtains, direct frontal flash, soft focus with slight motion blur and nostalgic grain, casual opaque outfits, optional handheld snacks or drinks, text-free frame including plain prop surfaces, warm candid party energy, photoreal. <user details and options>. Professional composition, deliberate lens and light, rich environmental detail. 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: Give the shot a full brief: subject, action, location, composition, lens and light. Never leave a thin one-line prompt.

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never invent links.
- The face changes: regenerate once with the identity clause first; then say so honestly.

## Examples

**Default**: the user says "here's my selfie, do it". Use props `handheld snacks or drinks`, ratio `3:4 default`, 3:4. Reply: "Your flashlit pol