Red Dress Black Lake · compétence Open Skill

Red Dress Black Lake

hook: I turn an adult photo into a fashion still. Red dress, charcoal-black lake, overcast sky. Minimal drama. tips: Send an adult photo with a clear face. The result: a long red dress on black water. Tip: Keep 3:4 by default / Tip: Choose mid-thigh, waist-deep, or another depth in the description.

@TylerHayes

Beauty

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284953/2026-10-17/fnm2n938.webp

# Red Dress Black Lake

Red against black water. Your photo becomes a cinematic fashion still: a long saturated red dress drifting on a nearly motionless charcoal-black lake under an overcast sky.

## When to use

- The user wants their photo turned into a cinematic portrait of a woman in a long red dress standing in a dark mystical black lake (moody red-dress lake shoot, gothic fashion water portrait)
- A variation on a previous result: waist-deep

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult woman, face clear. Ask for another photo if the face is tiny, blurred or hidden |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Water depth | No | `mid-thigh` | mid-thigh (default), waist-deep, 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='Red Dress Black Lake', 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. "All set. Your red dress black lake is on the canvas. Next I can do waist-deep." 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: a photoreal cinematic fashion photograph of the same adult woman standing in a moody black lake, water to mid-thigh or waist, wearing a long saturated red dress with thin straps and an abundant lightweight train drifting across the almost-motionless charcoal-black surface, faint low mist, a barely visible dark shore and forest silhouettes under an overcast sky, sombre mystical atmosphere, preserve her face and identity, rich fabric detail, dramatic soft light, fully clothed. <user details and options>. The new outfit fully replaces the original clothes with a clearly different silhouette; real fabric texture, accurate fit and drape, styling and accessories; a setting and light that suit the outfit. 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 new outfit read as real fabric: bold silhouette change from the original clothes, named materials and textures, hero lighting, and a scene that suits the outfit (not the selfie background).

## 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 "this one" with a photo. Use water depth `mid-thigh`, ratio `3:4 default`, 3:4. Reply: "All set. Your red d