image-generation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Image Generation Skill

图像生成Skill

Overview

概述

Image Generation uses FAL.ai nanobanana pro to create professional-quality images from text descriptions. This skill teaches you how to craft effective prompts and use the automation system to generate assets directly in Claude Code.

Keywords: image generation, nanobanana pro, prompt engineering, AI art, visual content creation, asset generation, automation

图像生成功能使用FAL.ai nanobanana pro根据文本描述创建专业级别的图片。本Skill将教你如何设计有效的提示词，并使用自动化系统在Claude Code中直接生成资产。

关键词：图像生成、nanobanana pro、提示词工程、AI艺术、视觉内容创作、资产生成、自动化

Core Models

核心模型

nanobanana pro — Recommended

nanobanana pro — 推荐使用

Quality: Highest, most detailed
Speed: 30-60 seconds
Best For: Product photography, hero images, final assets
Use Case: When quality matters most

画质：最高，细节最丰富
速度：30-60秒
最佳适用场景：产品摄影、主视觉图、最终资产
使用时机：对画质要求最高时

nanobanana pro

Quality: High, good detail
Speed: 5-15 seconds
Best For: Testing, iterations, social media
Use Case: When speed matters

画质：高，细节出色
速度：5-15秒
最佳适用场景：测试、迭代、社交媒体内容
使用时机：对速度要求最高时

nanobanana pro

Quality: Latest, improved
Speed: 20-40 seconds
Best For: Production work
Use Case: When you want the latest model

画质：最新版本，效果优化
速度：20-40秒
最佳适用场景：生产级工作
使用时机：想要使用最新模型时

Prompt Engineering Framework

提示词工程框架

The 5-Part Prompt Formula

五部分提示词公式

Every effective prompt has 5 components:

1. Subject — What is the main thing?

"A luxury leather watch"
"A modern logo"
"An Instagram post graphic"

2. Description — What does it look like?

"with gold accents and brown leather strap"
"geometric style, minimalist design"
"vibrant colors, eye-catching composition"

3. Style — What's the artistic style?

"professional product photography"
"modern illustration"
"digital design"
"photorealistic"

4. Technical Details — Quality and format specs

"studio lighting, sharp focus, 4K, centered composition"
"high contrast, trending design, professional quality"
"detailed, well-lit, professional photography"

5. Mood/Aesthetic — What's the feeling?

"luxury and professional"
"energetic and modern"
"clean and minimalist"
"warm and inviting"

每个有效的提示词包含5个组成部分：

1. 主体 — 核心对象是什么？

"一块奢华皮质手表"
"一个现代标志"
"一张Instagram帖子配图"

2. 细节描述 — 它看起来是什么样的？

"带有金色装饰和棕色皮质表带"
"几何风格，极简设计"
"色彩鲜艳，吸睛构图"

3. 风格 — 艺术风格是什么？

"专业产品摄影风格"
"现代插画风格"
"数字设计风格"
"写实风格"

4. 技术细节 — 画质和格式规格

"影棚灯光，清晰对焦，4K分辨率，居中构图"
"高对比度，潮流设计，专业画质"
"细节丰富，光线充足，专业摄影风格"

5. 氛围/美学 — 传递什么感觉？

"奢华且专业"
"充满活力且现代"
"简洁且极简"
"温暖且有吸引力"

Complete Prompt Example

完整提示词示例

A luxury leather watch with gold accents and brown strap, 
professional product photography, studio lighting with rim light, 
centered composition, sharp focus, 4K, luxury and professional mood

一块带有金色装饰和棕色皮质表带的奢华皮质手表，
专业产品摄影风格，带轮廓光的影棚灯光，
居中构图，清晰对焦，4K分辨率，奢华专业的氛围

Prompt Engineering Techniques

提示词工程技巧

Technique 1: Be Specific

❌ Bad: "A watch"
✅ Good: "A luxury leather watch with gold accents on white background"

Technique 2: Use Descriptive Adjectives

❌ Bad: "A logo"
✅ Good: "A modern, geometric, minimalist logo in blue and white"

Technique 3: Reference Styles

❌ Bad: "A nice graphic"
✅ Good: "A graphic in the style of modern Instagram design trends"

Technique 4: Specify Quality

❌ Bad: "A photo"
✅ Good: "A professional 4K product photograph with studio lighting"

Technique 5: Include Composition

❌ Bad: "A person"
✅ Good: "A person in rule of thirds composition, natural lighting, centered"

技巧1：描述要具体

❌ 不佳："一块手表"
✅ 优秀："一块白色背景下带有金色装饰的奢华皮质手表"

技巧2：使用描述性形容词

❌ 不佳："一个标志"
✅ 优秀："蓝白配色的现代几何极简标志"

技巧3：参考风格流派

❌ 不佳："一张好看的图形"
✅ 优秀："符合现代Instagram设计趋势的图形"

技巧4：明确画质要求

❌ 不佳："一张照片"
✅ 优秀："带有影棚灯光的专业4K产品照片"

技巧5：包含构图要求

❌ 不佳："一个人"
✅ 优秀："采用三分法构图、自然光线、居中的人物"

Claude Code Integration

Claude Code集成

How to Use in Claude Code

如何在Claude Code中使用

Claude Code can directly generate images using the automation system:

python

from claude_integration import generate_asset

Claude Code可通过自动化系统直接生成图片：

python

from claude_integration import generate_asset

Generate a single image

生成单张图片

result = generate_asset( category="product-photos", name="luxury-watch", prompt="A luxury leather watch with gold accents on white background, professional product photography, studio lighting, 4K, sharp focus", size="1024x1024", num_variations=1 )

print(f"Generated: {result['images']}")

undefined

result = generate_asset( category="product-photos", name="luxury-watch", prompt="一块白色背景下带有金色装饰的奢华皮质手表，专业产品摄影风格，影棚灯光，4K分辨率，清晰对焦", size="1024x1024", num_variations=1 )

print(f"已生成：{result['images']}")

undefined

Setup for Claude Code

Claude Code配置步骤

Ensure these files are in your project:

your-project/
├── vibe-creative-automation/
│   ├── fal_api.py
│   ├── creative_cli.py
│   ├── claude_integration.py
│   └── requirements.txt
└── assets/  (will be created automatically)

Set environment variable:

bash

export FAL_API_KEY="your_key_here"

Install dependencies:

bash

pip install requests

确保项目中包含以下文件：

your-project/
├── vibe-creative-automation/
│   ├── fal_api.py
│   ├── creative_cli.py
│   ├── claude_integration.py
│   └── requirements.txt
└── assets/  (将自动创建)

设置环境变量：

bash

export FAL_API_KEY="your_key_here"

安装依赖：

bash

pip install requests

Claude Code Workflow

Claude Code工作流程

When you ask Claude: "Generate 3 variations of a product photo for my watch"

Claude will:

Read Image Generation skill to understand prompting
Read Creative Strategist to get your style
Craft the prompt combining both
Call automation system with the prompt
Generate 3 images using FLUX model
Save to folder like
```
assets/product-photos/luxury-watch/
```
Show you results with file paths

当你向Claude提问："为我的手表生成3张不同版本的产品照片"

Claude将：

读取图像生成Skill以理解提示词设计方法
读取创意策略师Skill以匹配你的风格
结合两者设计提示词
调用自动化系统传入提示词
使用FLUX模型生成3张图片
保存到指定文件夹，例如
```
assets/product-photos/luxury-watch/
```
向你展示结果及文件路径

Example: Claude Code Generates Product Photos

示例：Claude Code生成产品照片

python

from claude_integration import generate_asset

python

from claude_integration import generate_asset

Your Creative Strategist style (from your style guide)

你的创意策略师风格（来自你的风格指南）

YOUR_STYLE = { "primary_style": "photorealistic", "mood": "professional and luxurious", "lighting": "studio lighting with rim light", "composition": "centered" }

YOUR_STYLE = { "primary_style": "写实风格", "mood": "专业且奢华", "lighting": "带轮廓光的影棚灯光", "composition": "居中" }

Generate product photo using your style

使用你的风格生成产品照片

prompt = f""" A luxury leather watch with gold accents, {YOUR_STYLE['primary_style']}, {YOUR_STYLE['mood']}, {YOUR_STYLE['lighting']}, {YOUR_STYLE['composition']}, white background, 4K, sharp focus, professional product photography """

result = generate_asset( category="product-photography", name="luxury-watch", prompt=prompt, size="1024x1024", num_variations=3 )

for img_path in result['images']: print(f"✅ Generated: {img_path}")

undefined

prompt = f""" 一块带有金色装饰的奢华皮质手表， {YOUR_STYLE['primary_style']}, {YOUR_STYLE['mood']}, {YOUR_STYLE['lighting']}, {YOUR_STYLE['composition']}, 白色背景, 4K分辨率, 清晰对焦, 专业产品摄影风格 """

result = generate_asset( category="product-photography", name="luxury-watch", prompt=prompt, size="1024x1024", num_variations=3 )

for img_path in result['images']: print(f"✅ 已生成：{img_path}")

undefined

Batch Generation Example

批量生成示例

python

from claude_integration import batch_generate_assets

python

from claude_integration import batch_generate_assets

Generate multiple assets at once

一次性生成多个资产

assets = [ { "type": "custom", "category": "product-photos", "name": "watch", "prompt": "Luxury watch, professional photography, studio lighting, 4K" }, { "type": "custom", "category": "product-photos", "name": "wallet", "prompt": "Premium leather wallet, professional photography, studio lighting, 4K" }, { "type": "custom", "category": "product-photos", "name": "sunglasses", "prompt": "Designer sunglasses, professional photography, studio lighting, 4K" } ]

results = batch_generate_assets(assets)

for result in results: print(f"{result['asset_name']}: {result['images']}")

undefined

assets = [ { "type": "custom", "category": "product-photos", "name": "watch", "prompt": "奢华手表，专业摄影风格，影棚灯光，4K分辨率" }, { "type": "custom", "category": "product-photos", "name": "wallet", "prompt": "高端皮质钱包，专业摄影风格，影棚灯光，4K分辨率" }, { "type": "custom", "category": "product-photos", "name": "sunglasses", "prompt": "设计师款太阳镜，专业摄影风格，影棚灯光，4K分辨率" } ]

results = batch_generate_assets(assets)

for result in results: print(f"{result['asset_name']}: {result['images']}")

undefined

Image Sizes

图片尺寸选择

Choose the right size for your use case:

Size	Use Case	Speed	Detail
512x512	Testing, thumbnails	Fast	Good
768x768	Social media, web	Medium	Good
1024x1024	Product photos, hero images	Medium	Excellent
1536x1536	Large prints, high-res	Slow	Excellent
2048x2048	4K, maximum detail	Very Slow	Maximum

根据你的使用场景选择合适的尺寸：

尺寸	使用场景	速度	细节
512x512	测试、缩略图	快	良好
768x768	社交媒体、网页	中等	良好
1024x1024	产品照片、主视觉图	中等	极佳
1536x1536	大幅打印、高分辨率内容	慢	极佳
2048x2048	4K、最高细节	极慢	极致

Generation Parameters

生成参数

Guidance Scale (3.5 - 7.5)

引导尺度（3.5 - 7.5）

Controls how strictly the model follows your prompt:

3.5 — More creative freedom, less literal
5.0 — Balanced (recommended)
7.5 — Strict adherence to prompt, more literal

Example:

python

undefined

控制模型对提示词的遵循严格程度：

3.5 — 创意自由度更高，字面匹配度较低
5.0 — 平衡效果（推荐）
7.5 — 严格遵循提示词，字面匹配度更高

示例：

python

undefined

More creative

更具创意

result = generate_asset(..., guidance_scale=3.5)

Balanced (default)

平衡效果（默认）

result = generate_asset(..., guidance_scale=5.0)

Strict

严格遵循

result = generate_asset(..., guidance_scale=7.5)

undefined

result = generate_asset(..., guidance_scale=7.5)

undefined

Inference Steps (20 - 50)

推理步数（20 - 50）

More steps = higher quality but slower:

20 — Fast, acceptable quality
28 — Balanced (default)
40 — High quality
50 — Maximum quality

Example:

python

undefined

步数越多，画质越高但速度越慢：

20 — 生成快，画质可接受
28 — 平衡效果（默认）
40 — 高画质
50 — 最高画质

示例：

python

undefined

Fast generation

快速生成

result = generate_asset(..., inference_steps=20)

Balanced (default)

平衡效果（默认）

result = generate_asset(..., inference_steps=28)

High quality

高画质

result = generate_asset(..., inference_steps=40)

undefined

result = generate_asset(..., inference_steps=40)

undefined

Practical Prompt Examples

实用提示词示例

Product Photography

产品摄影

A luxury leather watch with gold accents on white background, 
professional product photography, studio lighting with rim light, 
centered composition, sharp focus, 4K, highly detailed

一块白色背景下带有金色装饰的奢华皮质手表，
专业产品摄影风格，带轮廓光的影棚灯光，
居中构图，清晰对焦，4K分辨率，细节丰富

Social Media Graphic

社交媒体图形

Instagram post graphic for product launch, vibrant colors, 
eye-catching composition, modern design, 1080x1080 format, 
trending aesthetic, professional quality

产品发布用Instagram帖子图形，色彩鲜艳，
吸睛构图，现代设计，1080x1080格式，
潮流美学，专业画质

Logo Design

标志设计

Modern tech company logo, geometric style, blue and white colors, 
minimalist design, scalable, professional, clean lines, 
suitable for all media

科技公司现代标志，几何风格，蓝白配色，
极简设计，可缩放，专业风格，线条简洁，
适用于所有媒体场景

Illustration

插画

Colorful illustration of a person working at a computer, 
modern illustration style, bright colors, friendly mood, 
professional quality, trending design

一个人在电脑前工作的彩色插画，
现代插画风格，明亮色彩，友好氛围，
专业画质，潮流设计

Hero Image

主视觉图

A futuristic tech workspace with multiple monitors, 
professional photography, modern aesthetic, blue and purple lighting, 
cinematic composition, 4K, highly detailed

带有多台显示器的未来科技工作空间，
专业摄影风格，现代美学，蓝紫色灯光，
电影级构图，4K分辨率，细节丰富

Integration with Other Skills

与其他Skill的集成

Image Generation + Creative Strategist:

Use your style guide to craft better prompts
Maintain consistency across all generated images

Image Generation + Product Photography:

Generate product shots for e-commerce
Create lifestyle product photos

Image Generation + Social Graphics:

Generate graphics for social media
Create platform-specific content

Image Generation + Brand Asset:

Generate logos and icons
Create brand illustrations

图像生成 + 创意策略师：

使用你的风格指南设计更好的提示词
保持所有生成图片的风格一致性

图像生成 + 产品摄影：

为电商平台生成产品照片
创建生活化产品照片

图像生成 + 社交媒体图形：

为社交媒体生成图形内容
创建适配不同平台的内容

图像生成 + 品牌资产：

生成标志和图标
创建品牌插画

Command Line Usage

命令行使用方式

You can also use the CLI directly:

bash

undefined

你也可以直接使用CLI：

bash

undefined

Generate custom asset

生成自定义资产

python creative_cli.py custom
--category "product-photos"
--name "luxury-watch"
--prompt "A luxury leather watch with gold accents on white background, professional product photography, studio lighting, 4K, sharp focus"
--size 1024x1024
--num-images 3
--model fal-ai/nano-banana-pro

undefined

python creative_cli.py custom
--category "product-photos"
--name "luxury-watch"
--prompt "一块白色背景下带有金色装饰的奢华皮质手表，专业产品摄影风格，影棚灯光，4K分辨率，清晰对焦"
--size 1024x1024
--num-images 3
--model fal-ai/nano-banana-pro

undefined

Troubleshooting

故障排除

Problem: Images don't match my style

问题：生成的图片不符合我的风格

Solution:

Add more specific style descriptors to prompt
Reference your Creative Strategist guide
Test with different guidance scales
Generate multiple variations

解决方案：

在提示词中添加更具体的风格描述
参考你的创意策略师指南
尝试不同的引导尺度
生成多个版本的图片

Problem: Generation is too slow

问题：生成速度太慢

Solution:

Use
```
fal-ai/nano-banana-pro
```
model
Reduce image size to 768x768
Reduce inference steps to 20

解决方案：

使用
```
fal-ai/nano-banana-pro
```
模型
将图片尺寸缩小至768x768
将推理步数减少至20

Problem: Images are too creative/not literal enough

问题：图片过于创意/与提示词不符

Solution:

Increase guidance scale to 7.5
Be more specific in prompt
Add more technical details

解决方案：

将引导尺度提高至7.5
提示词描述更具体
添加更多技术细节

Problem: API errors

问题：API调用出错

Solution:

Verify FAL_API_KEY is set correctly
Check internet connection
Verify API key is valid
Try again after a moment

解决方案：

验证FAL_API_KEY是否正确设置
检查网络连接
验证API密钥是否有效
稍后重试

Best Practices

最佳实践

Start with Creative Strategist — Define your style first
Be Specific — More details = better results
Test Variations — Generate multiple versions
Iterate — Refine based on results
Use Consistent Prompts — Similar prompts = consistent style
Reference Your Style — Include style descriptors in every prompt
Batch Generate — Generate multiple assets at once
Organize Assets — Keep generated images organized

先使用创意策略师 — 先定义你的风格
描述要具体 — 细节越多，结果越好
测试多个版本 — 生成多种变体
迭代优化 — 根据结果调整提示词
使用一致的提示词 — 相似提示词可保证风格一致
参考你的风格 — 在每个提示词中包含风格描述
批量生成 — 一次性生成多个资产
整理资产 — 有序管理生成的图片

Next Steps

后续步骤

Define Your Style — Complete Creative Strategist first
Craft Your Prompt — Use the 5-part formula
Test Generation — Generate a test image
Iterate — Refine based on results
Batch Generate — Create multiple assets
Use in Projects — Integrate with other skills

You now have the power to generate professional images with AI. Start creating! 🎨

定义你的风格 — 先完成创意策略师Skill
设计提示词 — 使用五部分公式
测试生成 — 生成一张测试图片
迭代优化 — 根据结果调整
批量生成 — 创建多个资产
在项目中使用 — 与其他Skill集成

你现在拥有了用AI生成专业图片的能力。开始创作吧！ 🎨