着物ポートレート · skill Open Skill công khai

着物ポートレート

帯ひとつで、変わる。 着物と浴衣のポートレートを、布と所作で撮ります。 ・8拍構成 — 帯、襟、袖、襟足、歩、風、光、余韻 ・顔は最小限 — 主役は布・手・後ろ姿。襟足のカットがこのジャンルの核です ・光 — 紙や葉を通した柔らかい一方向光。正面からのフラットな光は和装を死なせます ・季節 — 桜の振袖、紫陽花の浴衣、紅葉の訪問着、雪の袴 ・音 — 衣擦れ、下駄の音、風、遠い鐘。アンビエントか無音 画面内の文字はすべて日本語です。性的な表現は扱いません。実在のモデル・店舗は使用しません。オリジナル制作のみです。

@omegabubble

Beauty

1 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4267104/2026-10-18/5qnc7ssh.png

---

allowed-tools:
  - generate_image
  - generate_video
  - generate_music
  - mix_clips
  - recognize_video
  - download_video
---

# 着物ポートレート / Kimono Portrait

A kimono portrait is about **fabric and posture**, not the face: the collar, the obi, the sleeve, the back of the neck.

## When to use

- The user asks for 着物, 浴衣, 和装, or a kimono portrait.
- The user wants a kimono rental shop promo or a wedding 前撮り style piece.
- The user wants a vertical kimono short for TikTok / Shorts / Reels.
- The user uploads a kimono reference and wants an original portrait film.

Do **not** use this skill for: sexualised imagery or real named models — see Notes.

## Steps

### 0. Clarify — which garment, and which season

Call `write_todos` with the plan: clarify → (optional) reference analysis → choose the setting → storyboard → stills → shots → sound → edit.

Ask only what you still need:

1. **Which garment?** — 振袖 / 訪問着 / 浴衣 / 袴
2. **Which season?** — 桜 / 紫陽花 / 紅葉 / 雪
3. **Which angle?** — 後ろ姿と襟足 / 帯のアップ / 正面は最小限
4. **Frame?** — portrait 9:16 / landscape 16:9

Read the choice back in one Japanese line and get a yes.

### 1. Reference analysis (only if the user supplies a clip or image)

```
recognize_video(video_url=<url>, prompt='Analyse this as a Japanese kimono portrait video. Report: the light and hour, average shot length, how static the camera is, how much of the frame is a close-up, whether people are shown face-on, and the sound design. Do not describe the plot.')
```

For a YouTube / TikTok / Instagram link, resolve it first with `download_video(url=...)`.
Turn the answer into a short treatment note and read it back. Then build an **original** piece.

### 2. Storyboard — 8 beats, about 30 seconds

| # | Beat | Length | What happens |
|---|---|---|---|
| 1 | 帯 | 4s | The obi being tied, hands only |
| 2 | 襟 | 4s | The collar line, macro |
| 3 | 袖 | 4s | A sleeve falling, fabric moving |
| 4 | 襟足 | 4s | The nape of the neck, from behind |
| 5 | 歩 | 4s | Walking away down a stone path |
| 6 | 風 | 5s | Fabric lifting in the wind |
| 7 | 光 | 5s | Seasonal light through the fabric |
| 8 | 余韻 | 4s | A still frame: a hem on tatami. Hold |

**Rule: the frame stays on fabric, hands and the back — not on a face**

### 3. 日本語での作法 — what makes it Japanese

**All on-screen text is Japanese. No English anywhere.**

**和装の符号（必ずどれかを入れる）**
- 振袖、訪問着、浴衣、袴、帯、半衿、帯締め
- 襟足、袖、裾、足袋、草履、簪
- 季節：桜、紫陽花、紅葉、雪、芒
- 場所：石段、鳥居、障子、畳、庭、竹林
- 小物：扇子、巾着、和傘、かんざし
- 所作：帯を結ぶ、袖を押さえる、一礼

**光**
Soft directional daylight through paper or leaves; avoid flat frontal light. Dusk for 浴衣, pale morning for 振袖.

**音**
Fabric, geta on stone, wind, a distant bell. Ambient pad or silence.

**テロップ**
- One line only: `帯ひとつで、変わる。` — mincho, white, small

### 4. Stills

```
generate_image(model='t2i', prompt='Japanese kimono portrait still: the back of a person in a deep-indigo kimono with an elaborate obi, standing on a stone path in autumn, face not visible, soft directional light, shallow depth of field, no text, cinematic, subtle grain', name='後ろ姿', entity_type='storyboard_images', orientation='portrait')
```

```
generate_image(model='i2i', input_urls=[<user asset>], prompt='the same kimono, macro close-up of the obi knot and the cord, hands only, no face, no text', name='帯', entity_type='storyboard_images')
```

### 5. Shots

```
generate_video(model='i2v', input_urls=[<still asset>], prompt='gentle motion: the sleeve and hem lifting slightly in the wind, a very slow camera drift, face not visible, no camera shake', name='風', entity_type='storyboard_videos', orientation='portrait')
```

Keep `orientation` identical across every shot; never write a physical model name — channels only.

### 6. Sound

```
generate_music(model='music', prompt='quiet Japanese kimono ambience: fabric moving, geta on stone, a distant wind chime, one koto note, soft ambient pad, no drums, 45 seconds', name='和装', entity_type='music')
```

A single Japanese line through `tts.design` is optional. **Confirm the e