Outfit Three-Angle View · Open Skill 公開技能

Outfit Three-Angle View

Outfit Three-Angle View 是 Digen 上的公開 Open Skill。開啟後即可了解此工作流能製作什麼。

@NateSullivan

TryOn

3 2 2

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284959/2026-10-16/myvth888.webp

# Outfit Three-Angle View

Upload a face and an outfit. Get one wide sheet with front, side and back full-body views of that person wearing the clothes.

## When to use

- The user wants a full-body front/side/back view of a person wearing a reference outfit (character and outfit synthesis, three-angle turnaround)
- A variation on a previous result: 3:2 on request

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult with the face clearly visible. Ask for another photo if the face is tiny, blurred, heavily covered or in profile |
| Outfit reference | No | — | photo of the costume or clothes to wear |
| Ratio | No | `16:9 default wide sheet` | 16:9 default wide sheet; 3:2 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='landscape', aspect_ratio='16:9', name='Outfit Three-Angle View', 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 outfit three-angle view. I can also try 3:2 on request 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: a wide horizontal sheet showing front, side and back full-body views of the same adult person wearing the referenced outfit: recreate facial features and hairstyle from the person photo and the outfit's design, colors and embellishments from the outfit reference, consistent lighting across three panels. <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 landscape 16:9. 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 "use this pic" with a photo. Use ratio `16:9 default wide sheet`, 16:9. Reply: "Done! Here's your outfit three-angle view."
**Variation**: "one more please". Keep the same inputs and change one option (3:2 on request).
**Missing input**: no photo was sent. Ask: "I need one clear, front-facing photo to begin. Could you send it?"

## References

- `references/image-edit.md`