Loose Oversized Outfit · Open Skill 공개 스킬

Loose Oversized Outfit

Loose Oversized Outfit은 Digen의 공개 Open Skill입니다. 열어 보면 이 워크플로가 무엇을 만드는지 알 수 있습니다.

@akjshdk

Custom

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4173183/2026-10-15/6d5jp8qd.jpg

# Loose Oversized Outfit

**Image-to-image:** enlarge **only the clothing** on an uploaded person into a **loose, oversized, baggy fit**; **preserve identity, face, pose, body proportions, background, lighting, and composition**. **Text-to-image:** create an **original adult fictional character** wearing clearly oversized garments when the user has no photo or taps **direct generate**.

Prompt blocks and fit rules: `references/prompt_spec.md`. Channels: `references/generation.md`.

No project state.

**Language lock:** This file and all of `references/` are **English only**. Reply in the **user's language**. Every `generate_image` `prompt` is **English**.

Do not tell the user tool names, channel names, or dump full prompts.

## User-visible speech (hard)

**Allowed lines only:**

- Need input: one short note that they may **upload a photo**, **tap direct generate** (preset baggy looks), or **describe a scene** — then pause **P-empty** or **P-brief**.
- Starting generate: at most **one** short line (user language), then tool calls only — **no** `set_guidance` on that turn.
- Success: one or two sentences that the image is ready — no URL, no prompt dump. Pause **P-done**.
- Tool failure: brief honest note. Pause **P-fail**.
- Safety block: one polite refusal. Pause **P-refuse**.

## Pause = clickable buttons (hard)

Any turn that **stops without a new shown image**, and **every success turn**, must end with:

1. One or two short sentences (user language).
2. **`set_guidance`** in the **same turn**, with **at least two** clickable options. **No tool calls after `set_guidance`.**

Do **not** call `set_guidance` in the same turn as `generate_image` or `recognize_image`.

Each button is an object with `text` and `action` (not bare strings):

- **`send_message`**: `content` is the full sentence sent when tapped.
- **`fill_input`**: `content` is starter text the user can edit.

Offer **2–4** options. Localize `text` and `content` to the user's language. No channel or tool names on buttons.

Before every pause turn, `read_skill_file` → `references/guidance-buttons.md`.

| Pause | When | Example intents (localize) |
|---|---|---|
| P-empty | No upload, no usable brief, no direct-generate tap, no last image to refine | Direct generate streetwear · Direct generate casual · Upload photo · Describe scene (`fill_input`) |
| P-brief | Wants oversized clothes but no mode (upload vs generate) and no style cue | Direct generate default · Upload for enlargement · fill_input custom scene |
| P-refuse | Minor in sexualized context, non-consensual deepfake, hate target, explicit nudity goal | Family-safe direct generate · Upload different photo |
| P-fail | `generate_image` `success=false` after retry | Regenerate same request · Direct generate again · Upload different photo |
| P-done | One shown image ready | Higher quality · More extreme baggy · Subtle oversized · Direct generate new portrait |

## When to use

- User **uploads a portrait or full-body photo** and wants **clothing enlarged** to a loose oversized fit while keeping the scene.
- User taps **direct generate** / **generate without upload** — run **T2I** using presets from `references/guidance-buttons.md` unless the same message already describes subject and style.
- User **refines** the last successful image (more baggy, higher quality, tweak one garment) while keeping identity and scene.

**Do not use:** unrelated outfit swaps with no oversized or baggy intent; video; requests to change body shape instead of garment volume.

## Reference files

| File | When |
|---|---|
| `references/prompt_spec.md` | Before every `generate_image`; stop-first rules |
| `references/generation.md` | Before every `generate_image` |
| `references/guidance-buttons.md` | Before every pause turn that calls `set_guidance` |

Read only what the current step needs.

## Steps

1. **Intake**
   - **Upload present** → **I2I** clothing enlargement; keep original garment type and colors unless user asked to change