Secret Label Cover · Open Skill 公开技能

Secret Label Cover

Secret Label Cover 是 Digen 上的公开 Open Skill。打开后即可了解该工作流能制作什么。

@CraftyCleo

Custom

1 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321667/2026-10-21/rcck2byd.webp

# Secret Label Cover

Private details, hidden in plain sight. Every sensitive part of the photo gets covered by crisp 'Secret' label blocks in your colors, so the shot is ready to post without losing the person.

## When to use

- The user wants a photo made shareable by covering its private details with playful 'Secret' labels (secret label cover, censor my document, redact my photo with labels, hide private info)
- A variation on a previous result: held document

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult, face clear and the sensitive object visible in frame; a front-facing shot where the object sits level works best. Ask for another photo if the face is tiny or the object to cover is cut off at the edge |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Area to cover | No | `held document or card` | held document or card (default), screen or form, printed address, or user-described |
| Label style | No | `four stacked 'Secret' blocks in coral red and navy blue` | four stacked 'Secret' blocks in coral red and navy blue (default), one wide banner, a scattered tag cluster, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 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='Secret Label Cover', 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. "Done! Here's your secret label cover. I can also try held document if you like." 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 kept completely unchanged — same face, expression, hair, pose, hands and outfit — while the sensitive area at <area: the held document or card (default), a screen or form, an address on paper, or user-described> is covered by <labels: four stacked 'Secret' label blocks in coral red and navy blue (default), one wide banner, or user-described arrangement> with crisp rounded corners, bold white label text, the original background, lighting and framing of the photo kept as they are, tidy graphic-overlay look, fully clothed, no exposed private data anywhere in frame. <user details and options>. Apply the style to the entire frame with its signature traits (medium, texture, palette, linework); the person stays recognizable under the style. 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: Name the style's visual traits (medium, brushwork or render, palette, line quality) and apply