Expression Pose Edit · Open Skill 公開技能

Expression Pose Edit

Expression Pose Edit 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

Beauty

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284959/2026-10-17/jpt3b6x3.webp

# Expression Pose Edit

New mood, matching pose. Your image gets the expression you name, with the body pose adjusted so the whole attitude matches.

## When to use

- The user wants the character in their image given a new facial expression with a matching body pose (expression and pose editor, emotion pose restyle still)
- A variation on a previous result: soft smile seated

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult or clear character, face readable. Ask for another image if the face is tiny, blurred or hidden |
| Description | Yes | — | What the user wants; merged into the prompt |
| Expression/pose | No | `bright open smile with open stance` | bright open smile with open stance (default), soft smile seated, surprised lean-in, cool-serious crossed arms, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 2:3 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='Expression Pose Edit', 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 expression pose edit. I can also try soft smile seated 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 character from the input with <expression and matching pose: a bright open smile with a relaxed open stance (default), or the user's described expression and pose>, facial features and identity preserved, body pose anatomically adjusted to support that expression, consistent lighting perspective and texture with the original scene, photoreal or matching the source art style, fully clothed. <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 them to the whole frame; keep the face's likeness readable under the style.

## 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 expression/pose `bright open smile with open stance`, ratio `3:4 default`, 3:4. Reply: "Done! Here's your expression pose edit."
**Variation**: "one more please". Keep the same inputs and change o