muapi-photo-pack-generator
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinese📸 Photo Pack Generator Expert Skill (Identity-Lock Edition)
📸 照片包生成专家技能（Identity-Lock版）
Transform a single reference photo into a collection of themed images while maintaining extremely high facial identity fidelity.
This skill prioritizes identity preservation first, then applies stylistic transformations like LinkedIn portraits, dating photos, cinematic shots, or fantasy styles.
The system uses Identity Lock Prompting instead of describing the person, preventing the model from generating a new face.
将单张参考照片转换为一组主题图片，同时保持极高的面部身份保真度。
本技能优先以身份保留为核心，随后应用风格化转换，例如LinkedIn职业照、交友照片、电影质感镜头或奇幻风格等。
系统采用Identity Lock提示词技术，而非描述人物特征，避免模型生成全新面部。
Core Principles
核心原则
1️⃣ Identity Lock (MOST IMPORTANT)
1️⃣ Identity Lock（最为重要）
The generated images must always depict the same person from the reference image.
All prompts MUST include identity lock instructions.
Required identity rules:
- Preserve the exact facial identity from the reference image
- Do not modify eye shape or spacing
- Do not modify nose structure
- Do not modify jawline or chin shape
- Do not modify cheekbones
- Do not modify face proportions
- Identity must remain identical to the reference photo
生成的图像必须始终呈现参考图片中的同一人物。
所有提示词必须包含Identity Lock指令。
强制身份规则：
- 精准保留参考图片中的面部身份特征
- 不得修改眼形或眼距
- 不得修改鼻子结构
- 不得修改下颌线或下巴形状
- 不得修改颧骨
- 不得修改面部比例
- 身份特征必须与参考照片完全一致
2️⃣ Vision-First Scene Analysis
2️⃣ 视觉优先的场景分析
The agent MUST analyze the reference image before generation.
However the analysis must NOT describe the person (age, ethnicity, hair etc).
Allowed analysis fields:
- head orientation
- facial angle
- expression
- lighting direction
- framing (portrait / half body / full body)
Example:
Head orientation: slight left tilt
Expression: neutral friendly
Lighting: soft frontal light
Framing: head and shoulders portrait
Expression: neutral friendly
Lighting: soft frontal light
Framing: head and shoulders portrait
Agent必须在生成前分析参考图片。
但分析内容不得描述人物特征（年龄、种族、发型等）。
允许分析的维度：
- 头部朝向
- 面部角度
- 表情
- 光线方向
- 取景范围（头像/半身/全身）
示例：
头部朝向：轻微向左倾斜
表情：中性友好
光线：柔和正面光
取景范围：头肩肖像
表情：中性友好
光线：柔和正面光
取景范围：头肩肖像
Agent Execution Flow
Agent执行流程
Step 1 — Grounding Check
步骤1 — 基础检查
Ensure the user has provided a reference image.
Supported inputs:
- local image
- URL
- uploaded file
确认用户已提供参考图片。
支持的输入类型：
- 本地图片
- URL链接
- 上传文件
Step 2 — Vision Analysis
步骤2 — 视觉分析
Extract scene attributes only.
DO NOT describe:
- age
- ethnicity
- beard
- hair
- body type
Identity must come directly from the image.
仅提取场景属性。
禁止描述：
- 年龄
- 种族
- 胡须
- 发型
- 体型
身份特征必须直接来自图片本身。
Step 3 — Category Selection
步骤3 — 类别选择
If the user does not specify a category suggest:
- Tinder
- OldMoney
若用户未指定类别，建议以下选项：
- Tinder
- OldMoney
Step 4 — Prompt Construction
步骤4 — 提示词构建
Use the reference image as the identity source.
Preserve the exact facial identity from the reference image.
Identity must remain identical to the reference photo.
Do not change:
- eye shape
- eye spacing
- nose structure
- jawline
- cheekbones
- face proportions
Maintain similar head orientation as the reference.
Scene example:
Outdoor café portrait
Soft natural daylight
35mm portrait lens
Shallow depth of field
Photorealistic skin texture
Soft natural daylight
35mm portrait lens
Shallow depth of field
Photorealistic skin texture
以参考图片作为身份来源。
精准保留参考图片中的面部身份特征。
身份特征必须与参考照片完全一致。
不得更改：
- 眼形
- 眼距
- 鼻子结构
- 下颌线
- 颧骨
- 面部比例
保持与参考图片相似的头部朝向。
场景示例：
户外咖啡馆肖像
柔和自然日光
35mm人像镜头
浅景深
真实皮肤纹理
柔和自然日光
35mm人像镜头
浅景深
真实皮肤纹理
Step 5 — Negative Prompt
步骤5 — 负向提示词
Always include:
different person
altered face
changed facial features
new identity
generic face
beautified face
plastic skin
face distortion
altered face
changed facial features
new identity
generic face
beautified face
plastic skin
face distortion
必须始终包含：
different person
altered face
changed facial features
new identity
generic face
beautified face
plastic skin
face distortion
altered face
changed facial features
new identity
generic face
beautified face
plastic skin
face distortion
Step 6 — Execution
步骤6 — 执行
Example:
bash scripts/generate-pack.sh
--image "./my_face.jpg"
--category "LinkedIn"
--identity-lock true
--num 5
--image "./my_face.jpg"
--category "LinkedIn"
--identity-lock true
--num 5
示例：
bash scripts/generate-pack.sh
--image "./my_face.jpg"
--category "LinkedIn"
--identity-lock true
--num 5
--image "./my_face.jpg"
--category "LinkedIn"
--identity-lock true
--num 5
Supported Categories
支持的类别
| Category | Best For | Aesthetic |
|---|---|---|
| Professional | Studio | |
| CEO | Founders | Office |
| Tinder | Dating | Lifestyle |
| OldMoney | Luxury | Estate |
| Cyberpunk | Fantasy | Neon |
| Fitness | Gym | Athletic |
| Travel | Social | Bali/Paris |
| 90s | Retro | Vintage |
| Holiday | Seasonal | Festive |
| 类别 | 适用场景 | 美学风格 |
|---|---|---|
| 职业场景 | 工作室风 | |
| CEO | 创始人形象 | 办公室风 |
| Tinder | 交友场景 | 生活方式风 |
| OldMoney | 奢华风格 | 庄园风 |
| Cyberpunk | 奇幻风格 | 霓虹风 |
| Fitness | 健身场景 | 运动风 |
| Travel | 社交分享 | 巴厘岛/巴黎风 |
| 90s | 复古风格 | 怀旧风 |
| Holiday | 季节场景 | 节日风 |
Guardrails
约束规则
Fidelity First
保真优先
Identity preservation is always more important than style.
身份保留始终比风格转换更重要。
Never Re-Describe the Person
绝不重新描述人物
Avoid prompts like:
"Indian man in his 20s with short hair"
This causes the model to generate a new face.
Identity must come from the reference image only.
避免使用如下提示词：
"Indian man in his 20s with short hair"
这会导致模型生成全新的面部。
身份特征必须仅来自参考图片。
Recommended Models
推荐模型
Best results with:
- nano-banana-edit
最佳效果模型：
- nano-banana-edit
Result
输出结果
This system produces:
- consistent identity
- photorealistic images
- multi-style photo packs
- professional outputs
本系统可生成：
- 身份一致的图片
- 写实风格照片
- 多风格照片包
- 专业级输出内容