Lock identity, composition, lighting, and wardrobe before style words so a portrait series stays consistent instead of drifting frame to frame.
プロンプト
Create an editorial portrait of [SUBJECT] for [USE]. Preserve facial identity and natural skin texture. Composition: [FRAMING]. Lighting: [LIGHTING]. Wardrobe: [WARDROBE]. Background: [BACKGROUND]. Color grade: [PALETTE]. Avoid plastic skin, distorted hands, text, logos, and over-sharpening.
変数を置き換える
[SUBJECT]The person or reference image.
[FRAMING]e.g. head-and-shoulders, 3/4.
[LIGHTING]e.g. soft key, rim light.
どのモデルを使うか
- Nano Banana Pro — Identity-preserving image edits are handled by the image model, not the text model.
入力例
- [SUBJECT] = uploaded reference photo. [USE] = "LinkedIn headshot".
出力例
私たちは実際のモデル実行による出力例のみを公開しています。このテンプレートはまだ正式にテストされていないため、出力は表示されません。上記の入力を使ってご自身で実行してみてください。
この構造が機能する理由
- Structure-before-style stops adjectives from fighting each other.
- An explicit negative list removes common artefacts.
よくある失敗と修正
Face drifts between generations.
修正: Reuse the same reference and keep identity terms first in the prompt.
既知の制限事項
- Image models vary; results are not guaranteed and need review.
よくある質問
Where are the tested portrait prompts?
The image gallery has portrait prompts with real example outputs. This page is a reusable template for building your own.