EP.5 渋谷スクランブル

# 🎬 Seedance 2.0 (Runway) — 動画生成 使い方ガイド

## TOOL
**Runway** (https://app.runwayml.com/)

## モデル / モード
- モデル: `Seedance 2.0`
- 入力: text-to-video または image-to-video

## Runway 画面の入力箇所 → 何を入れるか

| Runway 画面 | このページのどこを使うか |
|---|---|
| **Reference Image (@IMG_1)** | 上記「Reference Image」の画像をドラッグ&ドロップ |
| **Prompt** | 下記プロンプト本文をコピー |
| **Duration** | 5s / 10s / 15s から選択 |
| **Aspect Ratio** | 16:9 横長 (本編) / 9:16 縦長 (SNS Reels) |
| **Audio** | ON 必須 (OFF だとナレーション・効果音が入らない) |
| **Generate** | 60〜180秒で完成、Download MP4 |

## 注意
- 顔が映る image-to-video は Seedance のフィルタによりブロックされる場合あり → text-to-video に切り替えるか、Kling v3 を使用

## 実投入するプロンプト本文

```text
The same Japanese man from the reference image, early 30s, keeping his exact face bones, skin tone, curly hair texture, and facial features identical to the reference. Styled as an intellectual gentleman in smart casual private-life outfit — thin black-rimmed round fashion glasses (伊達メガネ, non-prescription, clean minimalist metal-and-acetate frame), a well-fitted soft charcoal grey wool-blend cardigan (cashmere-feel) loosely buttoned over a clean cream crew-neck fine-knit, slim dark taupe wool trousers, simple brown leather derby shoes. A classic brown leather watch on his left wrist. No other jewelry. The look is quietly refined, well-read, private-life casual — never worker-uniform, never fashion-trendy, never businessman.

Background is a completely plain seamless neutral light-grey studio backdrop — no scene, no location, no props, no crowd, no city, no text, no patterns. Pure minimalist portrait setting so he is isolated cleanly from any environment. Soft even studio key light from camera-left, gentle fill from right, clean rim light separating him from the grey seamless, no harsh shadows on the backdrop, no visible floor line.

@IMG_1's expression: calm intellectual composure, a quiet attentive gaze, the gentle gravity of a thoughtful protagonist. Soft half-smile. His two hands are held in front of his chest with fingers interlaced quietly and deliberately, as if about to snap — a stilled moment of intent. Standing full upright, facing camera directly.

Medium close-up shot framed from mid-thigh up, 9:16 vertical portrait. Photorealistic ARRI Alexa Mini cinematic look, 85mm portrait lens feel, shallow depth of field, subsurface skin scattering, visible skin pores, subtle 35mm film grain, natural clean color balance. Preserve the reference person's identity completely — same face bones, same curly hair texture, just an intellectual gentleman studio portrait. No background elements, no readable text, no logos, no watermarks, no cartoon, no CGI look.
```