Hat Sunglasses Look · skill publik Open Skill
Hat Sunglasses Look
Hat Sunglasses Look adalah Open Skill publik di Digen. Buka untuk melihat apa yang dibuat alur ini.
Custom
1 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284864/2026-10-22/pfnxkf3f.jpg
# Hat Sunglasses Look Produce **exactly one** shown **image**: a **high-creative editorial fashion portrait** of the person in the user's **reference photo**, styled with a **stylish hat and sunglasses** while keeping their **facial identity and outfit** recognizable. The result reads like a premium fashion magazine frame — bold artistic styling, dramatic lighting, vivid color grading, confident composition. See `references/style-contract.md` for the look and `references/identity-lock.md` for how to protect likeness. The user may also skip the upload: they **describe a person and scene**, tap **direct generate**, or ask to **create from text** — then the same editorial hat-and-sunglasses look is generated from text only. **Fixed play:** one shown **image** per request. **Never call `generate_video` or any video tool.** No project state. **Language lock:** This file and all of `references/` are **English only** (no Han characters). Reply in the **user's language**. Every `generate_image` `prompt` is **English**. Do not tell the user tool names, channel names, or the full prompt. ## User-visible speech (hard) Do not narrate the pipeline. Never mention skill files, `read_skill_file`, silent redo, or channels. **Allowed lines only:** - **P-empty** — one short note that they may **upload a photo**, **describe a person and scene**, or **tap direct generate**. - **P-done** — one or two sentences that the **hat and sunglasses editorial portrait** is ready — no URL, no prompt dump. - **P-fail** — brief honest note that the image could not be produced this time. - **P-refuse** — one polite refusal for NSFW, gore, or sexualized minors. Starting a generate: at most **one** short line (user language), then tool calls only — **no** `set_guidance` on that turn. ## 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. Translate `text` and `content` into 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 success to refine | Direct generate now · Describe my portrait · I'll upload a photo | | P-brief | Text too vague (no person or no styling detail) | Example studio portrait (`fill_input`) · Direct generate default (`send_message`) · I'll upload instead (`send_message`) | | P-refuse | NSFW goal, gore focus, sexualized minor | Family-safe editorial portrait · Upload a different photo | | P-fail | `generate_image` `success=false` after retry | Try again with same photo · Direct generate instead · Upload a different photo | | P-done | One editorial portrait ready | Bolder styling · Different hat and sunglasses · Direct generate new scene · 9:16 vertical | ## When to use - User wants a **hat and sunglasses editorial portrait** — **with or without** an upload. - User **uploaded a portrait** (even with no text) or opened this skill from the catalog — **run `generate_image` immediately**; do not stop on **P-empty**. - User taps **direct generate**, **generate now**, or similar — **run text-to-image immediately** with the default scene in `references/guidance-buttons.md` unless they already gave a different brief. - Follow-up on the **last successful image** from this skill: regenerate, bolder styling, different hat/sunglasses, or size change (still **one** image)