Dark Mood Fashion Portrait · सार्वजनिक Open Skill
Dark Mood Fashion Portrait
Dark Mood Fashion Portrait Digen पर एक सार्वजनिक Open Skill है। खोलें और जानें कि यह वर्कफ़्लो क्या बनाता है।
Custom
0 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4173183/2026-10-15/qghb4tyk.jpg
# Dark Mood Fashion Portrait Produce **exactly one** shown **cinematic dark fashion portrait** per confirmed create action: - **Photo path (I2I):** From an optional upload, preserve **likeness** (face, identity, facial proportions, natural asymmetry, **reference hair color**) while applying this skill's **locked cinematic template** (dark intimate wood interior, low-key warm rim light, over-shoulder pose, messy low updo styling, minimalist black open-back dress, filmic amber grading). **Micro-variations** (lamp halo strength, shadow depth) follow the user brief or defaults in `references/portrait-spec.md`. - **Direct path (T2I):** With **no upload**, generate one **adult** woman using the default subject and locked template in `references/portrait-spec.md`, unless the user brief overrides traits. No project state; track mentally: `source_mode` = `upload` | `t2i` | `refine_last`, plus any user notes on lighting or shadow mood. **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:** - Need input: one short note that they can **generate now without a photo** or **upload an optional reference** for likeness — then pause **P-empty**. - Bad subject: one gentle note if the upload is unusable — then pause **P-bad-input**. - 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 portrait 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**. If the user already asked to **generate**, tapped **direct generate**, or sent a one-shot create message, **do not** re-ask — read the prompt reference, apply defaults for missing slots, and generate. ## 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 | |---|---| | P-empty | No upload, no direct-generate intent, and no last successful result from this skill to refine | | P-mood | Upload or brief OK but user wants a lighting mood variant — optional; skip if they said "default" or tapped direct generate | | P-bad-input | Upload has no clear person, is unreadable, or unsuitable for likeness | | P-refuse | Minor subject, non-consensual deepfake intent, hate imagery, or explicit sexual content as the goal | | P-fail | `generate_image` `success=false` after retry | | P-done | One portrait ready | ## When to use - User wants a **cinematic dark fashion portrait** in a **warm low-key interior** with **identity preserved** from an optional photo. - User taps **generate now** / **direct generate** / equivalent with **no upload**. - Follow-up on **last successful output from this skill**: **regenerate**, **stronger rim light**, **deeper shadows**, **more face in light**, or **higher quality**. **Do not use:** video, unrelated background-only edits with no portrait intent, or requests targeting mi