Lock identity, composition, lighting, and wardrobe before style words so a portrait series stays consistent instead of drifting frame to frame.
提示词
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.
替换变量
[SUBJECT]The person or reference image.
[FRAMING]e.g. head-and-shoulders, 3/4.
[LIGHTING]e.g. soft key, rim light.
该用哪个模型
- Nano Banana Pro — Identity-preserving image edits are handled by the image model, not the text model.
示例输入
- [SUBJECT] = uploaded reference photo. [USE] = "LinkedIn headshot".
示例输出
我们只发布来自真实模型运行的示例输出。此模板尚未经过正式测试，因此不显示输出。请用上方的输入自行运行。
为何这一结构有效
- Structure-before-style stops adjectives from fighting each other.
- An explicit negative list removes common artefacts.
常见失败与修复
Face drifts between generations.
修复：Reuse the same reference and keep identity terms first in the prompt.
已知局限
- Image models vary; results are not guaranteed and need review.
常见问题
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.