Image-Generation - AI Image Generation Workflow

Core Concept: Analyze Style → Design Prompts → User Confirmation → Generate Images, Avoid Credit Wastage

Core Features

Image Generation:

Text-to-Image: Generate images based on text descriptions
Image-to-Image: Generate images with similar styles based on reference images
Batch Generation: Generate multiple images in batches using prompt templates
Consistent Style: Maintain unified visual style for a series of images

Image Processing:

Long Image Merging: Vertically stitch a series of images into a single long image
PPT Packaging: Package a series of images into a PPT file (one image per page)
Image Hosting Management: Upload images to hosting services and manage deletion links

Usage Scenarios

Applicable Scenarios:

Users explicitly request "generate images", "create illustrations", "make artwork"
Users provide text descriptions and need visual representation
Users provide reference images and request images with similar styles
Users need to create illustrations for articles, PPTs, or social media
Users need to batch generate a series of images with consistent style
Users need to merge multiple images into a long image or PPT

Inapplicable Scenarios:

Users only ask how to generate images (provide advice only)
Users need to edit existing images (use image editing tools)
Users need image recognition or analysis (use visual analysis tools)
Users need screenshots or screen recording (use system tools)

Workflow

Analyze Style → Design Prompts → Install Dependencies → Configure API → Confirm Generation → Save Images
    ↓          ↓           ↓         ↓         ↓         ↓
  Style Files  Prompt Files   node-fetch  secrets.md  One-by-One Confirmation  images/

Script Directory

All scripts are located in the

~/.claude/skills/pw-image-generation/scripts/

directory.

Agent Execution Instructions:

Determine the directory path of this SKILL.md file as
```
SKILL_DIR
```
Script path =
```
${SKILL_DIR}/scripts/<script-name>.ts
```
Replace all
```
${SKILL_DIR}
```
in this document with the actual path

Available Scripts:

Script	Function	Parameters
`generate-image.ts`	Generate images (with one-by-one confirmation)	`[output directory]`
`upload-image.ts`	Upload images to hosting service	`<image path>`
`delete-image.ts`	Manage hosted images	`list\|delete <index>\|delete-all`
`merge-to-long-image.ts`	Merge into long image	`<image directory> <output file>`
`merge-to-pptx.ts`	Package into PPT	`<image directory> <output file>`
`analyze-image.ts`	Analyze image style	`<image URL or path>`

Quick Start

Step 1: Create Project Directory

bash

mkdir my-image-project && cd my-image-project

Step 2: Copy Configuration Template (Optional)

bash

cp -r ~/.claude/skills/pw-image-generation/config.example ./config
cp ~/.claude/skills/pw-image-generation/references/.gitignore.template ./.gitignore
# Edit config/secrets.md to customize API keys (optional)

Step 3: Create Prompts

bash

mkdir -p prompts
cp ~/.claude/skills/pw-image-generation/references/prompt-templates/提示词模板.md ./prompts/我的提示词.md
vim ./prompts/我的提示词.md

Refer to

references/style-library.md

to select appropriate styles.

Step 4: Generate Images

bash

npx -y bun ~/.claude/skills/pw-image-generation/scripts/generate-image.ts

The script will ask for confirmation for each image to avoid credit waste.

Tool Script Details

1. Generate Images

Command:

bash

npx -y bun ~/.claude/skills/pw-image-generation/scripts/generate-image.ts [output directory]

Parameter Explanation:

```
[output directory]
```
: Optional, specify the image save directory, default is
```
./images
```

Workflow:

Read all prompt files in the
```
prompts/
```
directory
Display each prompt content one by one
Ask whether to generate the image (y/n/q)
Generate and save the image to the output directory
Support interruption and resumption

Confirmation Options:

```
y
```
(yes): Generate current image
```
n
```
(no): Skip current image and continue to the next
```
q
```
(quit): Exit the generation process

Examples:

bash

# Use default output directory
npx -y bun ~/.claude/skills/pw-image-generation/scripts/generate-image.ts

# Specify output directory
npx -y bun ~/.claude/skills/pw-image-generation/scripts/generate-image.ts ./my-images

2. Upload Images to Hosting Service

Command:

bash

npx -y bun ~/.claude/skills/pw-image-generation/scripts/upload-image.ts <image path>

Parameter Explanation:

```
<image path>
```
: Required, path to the local image file to upload

Features:

Automatically upload to freeimage.host (permanent storage)
Return usable image URL
Automatically save deletion link to
```
.upload-history.json
```
Used for reference image upload in image-to-image generation

Example:

bash

# Upload single image
npx -y bun ~/.claude/skills/pw-image-generation/scripts/upload-image.ts ./template/参考图.png

# After upload, you will get:
# - Image URL (used for image_url in prompts)
# - Deletion link (saved in history)

Output Example:

Upload successful!
Image URL: https://iili.io/xxx.png
Deletion link saved to .upload-history.json

3. Manage Hosted Images

Command:

bash

# List all uploaded images
npx -y bun ~/.claude/skills/pw-image-generation/scripts/delete-image.ts list

# Delete image with specified index
npx -y bun ~/.claude/skills/pw-image-generation/scripts/delete-image.ts delete <index>

# Delete all images
npx -y bun ~/.claude/skills/pw-image-generation/scripts/delete-image.ts delete-all

Parameter Explanation:

```
list
```
: List all upload records
```
delete <index>
```
: Delete image with specified index (index starts from 0)
```
delete-all
```
: Delete all images

Features:

View upload history and deletion links
Delete single or batch images
Automatically update history file

Example:

bash

# View upload history
npx -y bun ~/.claude/skills/pw-image-generation/scripts/delete-image.ts list
# Output:
# 0: 参考图.png - https://iili.io/xxx.png (2024-01-15)
# 1: 配图1.png - https://iili.io/yyy.png (2024-01-16)

# Delete image with index 0
npx -y bun ~/.claude/skills/pw-image-generation/scripts/delete-image.ts delete 0

# Delete all images (requires confirmation)
npx -y bun ~/.claude/skills/pw-image-generation/scripts/delete-image.ts delete-all

For detailed instructions, see

references/图床上传.md

4. Merge into Long Image

Command:

bash

npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-long-image.ts <image directory> <output file>

Parameter Explanation:

```
<image directory>
```
: Required, directory containing images to merge
```
<output file>
```
: Required, filename of the output long image

Features:

Vertically stitch multiple images
Automatically recognize jpg/png/gif/webp formats
Sort by filename numbers
Maintain original image width, automatically calculate height

Dependency Requirement: Need to install ImageMagick:

bash

brew install imagemagick

Example:

bash

# Merge all images in images directory
npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-long-image.ts ./images 长图.png

# Specify other directory
npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-long-image.ts ./my-images 合集.jpg

Usage Scenarios:

Create long images for Xiaohongshu/WeChat Official Accounts
Merge series tutorial screenshots
Create image collection displays

5. Package into PPT

Command:

bash

npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-pptx.ts <image directory> <output file>

Parameter Explanation:

```
<image directory>
```
: Required, directory containing images to package
```
<output file>
```
: Required, filename of the output PPT

Features:

One image per page
Automatically recognize jpg/png/gif/webp formats
Sort by filename numbers
16:9 aspect ratio, automatically adapt to page size
Images displayed in center

Example:

bash

# Package images in images directory into PPT
npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-pptx.ts ./images 配图.pptx

# Specify other directory
npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-pptx.ts ./my-images 展示.pptx

Usage Scenarios:

Quickly create image demonstration PPTs
Package series illustrations for sharing
Organize generated images into presentation documents

6. Analyze Image Style

Command:

bash

# Analyze from URL
npx -y bun ~/.claude/skills/pw-image-generation/scripts/analyze-image.ts <image URL>

# Analyze from local file
npx -y bun ~/.claude/skills/pw-image-generation/scripts/analyze-image.ts <local path>

Parameter Explanation:

```
<image URL or path>
```
: Required, URL or local file path of the image to analyze

Features:

Analyze visual style of images
Generate suitable prompt suggestions
Recognize colors, composition, and artistic styles
Save analysis results to
```
analysis/
```
directory

Example:

bash

# Analyze online image
npx -y bun ~/.claude/skills/pw-image-generation/scripts/analyze-image.ts https://example.com/image.jpg

# Analyze local image
npx -y bun ~/.claude/skills/pw-image-generation/scripts/analyze-image.ts ./template/参考图.png

Usage Scenarios:

Learn style features of reference images
Prepare prompts for image-to-image generation
Understand how to describe specific visual styles

File Structure

Project Directory Structure

my-image-project/
├── config/
│   └── secrets.md           # API configuration (optional)
├── template/                # PDF template images
├── prompts/                 # Prompt files
├── analysis/                # Style analysis (optional)
├── images/                  # Generated images
└── .gitignore

Skill Directory Structure

pw-image-generation/
├── SKILL.md                  # This file (core documentation)
├── config.example/           # Configuration templates
│   ├── README.md             # Configuration instructions
│   └── secrets.md            # API configuration template
├── references/               # Reference documents
│   ├── .gitignore.template   # Git ignore file template
│   ├── 图床上传.md           # Image hosting upload guide
│   ├── style-library.md      # Style library (9 preset styles)
│   └── prompt-templates/
│       └── 提示词模板.md     # Prompt templates
└── scripts/
    ├── analyze-image.ts      # Analyze image style
    ├── generate-image.ts     # Generate images (supports confirmation and skipping)
    ├── upload-image.ts       # Upload images to hosting service
    ├── delete-image.ts       # Manage and delete hosted images
    ├── merge-to-long-image.ts       # Merge into long image
    └── merge-to-pptx.ts        # Package into PPT

Common Issues and Error Handling

1. Image Generation Failure

Problem: Image generation fails or returns errors

Possible Causes:

API key not configured or invalid
Incorrect prompt format
Network connection issues
Insufficient API credits

Solutions:

bash

# Check configuration file
cat config/secrets.md

# Verify prompt format
cat prompts/提示词.md

# Test network connection
curl -I https://api.openai.com

# View detailed error information (automatically displayed by script)

2. Image Hosting Upload Failure

Problem: Failed to upload image to hosting service

Possible Causes:

Image file does not exist or incorrect path
Unsupported image format
Image file too large (exceeds 10MB)
Network connection issues

Solutions:

bash

# Check if file exists
ls -lh ./template/图片.png

# Check file size
du -h ./template/图片.png

# If file is too large, compress it
# Compress using ImageMagick
convert ./template/图片.png -quality 85 -resize 2000x2000\> ./template/图片_compressed.png

3. Long Image Merging Failure

Problem: Error "ImageMagick not found" when merging long images

Possible Causes:

ImageMagick not installed
ImageMagick not added to PATH

Solutions:

bash

# Install on macOS
brew install imagemagick

# Verify installation
convert --version

# If still failing, check PATH
which convert

4. PPT Generation Failure

Problem: Error when generating PPT or PPT cannot be opened

Possible Causes:

Image directory is empty or does not exist
Unsupported image format
Invalid output file path

Solutions:

bash

# Check image directory
ls -la ./images

# Check image format (supports jpg/png/gif/webp)
file ./images/*.png

# Ensure output directory exists
mkdir -p ./output
npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-pptx.ts ./images ./output/配图.pptx

5. Prompts Not Effective

Problem: Generated images do not match prompt descriptions

Possible Causes:

Prompt descriptions are not specific enough
Mixed Chinese and English in prompts
Prompts are too long or too short
Style descriptions are unclear

Solutions:

markdown

# Bad prompt
A picture

# Good prompt
Watercolor style, a cute kitten sitting on a windowsill, warm afternoon sunlight, soft colors, hand-painted texture

# Use style library
Refer to references/style-library.md to select appropriate style descriptions

6. Batch Generation Interruption

Problem: Unexpected interruption during batch generation

Possible Causes:

Unstable network
Manual interruption by user (Ctrl+C)
API rate limiting

Solutions:

The script will automatically skip already generated images
Re-run the generation command to continue
Already generated images will not be regenerated
Use
```
n
```
option to skip unwanted images

7. Configuration File Issues

Problem: Configuration file not effective or not found

Possible Causes:

Incorrect configuration file path
Incorrect configuration file format
Configuration template not copied

Solutions:

bash

# Copy configuration template
cp -r ~/.claude/skills/pw-image-generation/config.example ./config

# Check configuration file
cat config/secrets.md

# Configuration file format example
# API_BASE_URL=https://api.openai.com/v1
# API_KEY=sk-xxx

Best Practices

Image Size Specifications

Select appropriate image sizes based on different usage scenarios:

Scenario	Aspect Ratio	Recommended Pixels	Description
Article Illustrations	16:9	1920×1080	HD standard, suitable for large-screen reading
WeChat Official Account Cover	2.35:1	900×383	Official WeChat recommended size
Xiaohongshu Cover/Illustrations	3:4	1242×1660	Xiaohongshu recommended, suitable for iPhone screens
X Article Cover	5:2	1500×600	Official X Articles recommended
Paper Illustrations	16:9	1920×1080	HD standard

Additional Notes:

Xiaohongshu also supports 1:1 (1080×1080) and 4:3 (1440×1080)
WeChat Official Account secondary cover can use 200×200 (1:1)

Usage Suggestions:

Specify size in prompts:
```
size: 1920x1080
```
or
```
aspect_ratio: 16:9
```
Prioritize recommended sizes to avoid composition imbalance caused by later cropping
Different platforms have different size requirements, confirm target platform before generation

Prompt Design

Basic Principles:

Specific and clear: Detailed description of scene, style, color, and composition
Consistent style: Use preset style descriptions from the style library
Consistent language: All English or all Chinese, avoid mixing
Moderate length: 50-200 words is appropriate; too short lacks details, too long is confusing

Recommended Structure:

markdown

[Style] + [Subject] + [Scene] + [Atmosphere] + [Technical Details]

Example:
Watercolor style, a cute kitten sitting on a windowsill, warm afternoon sunlight, soft colors, hand-painted texture

Reference Resources:

```
references/style-library.md
```
: 9 preset styles

references/prompt-templates/提示词模板.md

: Prompt templates

Image Generation Process

Recommended Steps:

First generate 1-2 test images to verify prompt effectiveness
Adjust prompts based on test results
Batch generate remaining images after confirming satisfactory results
Use confirmation mechanism to avoid wasting API credits
Regularly back up generated images

Avoid Wastage:

Carefully check prompts before each generation
Use
```
n
```
option to skip unwanted images
Use
```
q
```
option to exit promptly
Do not blindly batch generate

Image-to-Image Tips

Upload Reference Image:

bash

# 1. Upload reference image to hosting service
npx -y bun ~/.claude/skills/pw-image-generation/scripts/upload-image.ts ./template/参考图.png

# 2. Copy the returned URL

# 3. Use in prompt
# image_url: https://iili.io/xxx.png
# prompt: Scene with similar style, maintain color tone and composition

Notes:

Recommended reference image size is 1024x1024 or larger
Reference image should be high-definition
Prompts should clearly state which features to retain
Try different prompt combinations multiple times

File Management

Recommended Directory Structure:

my-image-project/
├── config/              # Configuration files (not submitted to git)
├── template/            # Reference images
├── prompts/             # Prompt files
│   ├── 01-封面.md
│   ├── 02-内容1.md
│   └── 03-内容2.md
├── images/              # Generated images
│   ├── 01-封面.png
│   ├── 02-内容1.png
│   └── 03-内容2.png
└── output/              # Final output (long images/PPTs)

Naming Conventions:

Prompt files: Use numeric prefixes for sorting (01-, 02-, 03-)
Generated images: Automatically use prompt file names
Facilitates batch processing and sorting

Performance Optimization

Improve Generation Speed:

Use smaller image sizes (1024x1024 instead of 2048x2048)
Avoid overly complex prompts
Use image-to-image appropriately (faster than text-to-image)

Save API Credits:

Use confirmation mechanism, do not skip confirmation
Test single images first, then batch generate
Save good prompts as templates for reuse
Regularly clean up unnecessary images on hosting service

Quality Control

Checklist:

Prompt descriptions are clear and specific
Style descriptions are unified and consistent
Test image results are satisfactory
Image size and format are correct
File naming is standardized and organized
Important images are backed up

Common Issues:

Inconsistent image style: Check style descriptions in prompts
Poor image quality: Add technical detail descriptions (e.g., "high definition", "rich details")
Image content deviation: Make prompts more specific and add constraint conditions

Important Notes

Avoid Credit Wastage

Asks for confirmation before each generation
Supports skipping already generated images
Generate one image at a time to avoid batch credit consumption

Configuration Management

Configuration file
```
config/secrets.md
```
is optional
Uses default configuration when not configured (requires setting environment variable API_KEY)
Configuration files are not submitted to version control (already in .gitignore)
Supports custom API endpoints and models

Runtime Environment

Scripts run with Bun, no need to install dependencies locally:

bash

# Run directly, Bun will handle dependencies automatically
npx -y bun ~/.claude/skills/pw-image-generation/scripts/generate-image.ts

System Requirements:

Node.js or Bun runtime
macOS/Linux/Windows (WSL)
ImageMagick required for long image merging

Configuration Instructions

See

config.example/secrets.md

for configuration options:

Configurable Items:

```
API_BASE_URL
```
: API base URL (default: OpenAI API)
```
ANALYSIS_MODEL_ID
```
: Image analysis model (default: gpt-4-vision-preview)
```
GENERATION_MODEL_ID
```
: Image generation model (default: dall-e-3)
```
API_KEY
```
: API key (required)

Configuration Example:

markdown

# config/secrets.md
API_BASE_URL=https://api.openai.com/v1
ANALYSIS_MODEL_ID=gpt-4-vision-preview
GENERATION_MODEL_ID=dall-e-3
API_KEY=sk-your-api-key-here

Style Library

The Skill provides 9 preset styles to ensure consistent image styles:

Watercolor (watercolor) - Soft and warm
Flat Design (flat-design) - Modern and concise
3D Render (3d-render) - Stereoscopic and realistic
Oil Painting (oil-painting) - Artistic and classic
Cyberpunk (cyberpunk) - Sci-fi and futuristic
Pixel Art (pixel-art) - Retro and nostalgic
Hand-Drawn Illustration (hand-drawn) - Warm and personalized
Photorealistic (photorealistic) - Highly realistic
Abstract Art (abstract) - Emotional expression

See

references/style-library.md

for detailed descriptions and usage scenarios of each style.

Usage Suggestions

Agent Usage Guide

When users request image generation:

Confirm Requirements: Ask users about image usage, style preferences, and quantity
Prepare Environment: Guide users to create project directories and configurations
Design Prompts: Design prompts based on requirements, refer to the style library
Generate Tests: First generate 1-2 test images
Batch Generation: Batch generate after confirming satisfactory results
Post-Processing: Merge into long images or package into PPT as needed

Typical Workflows

Scenario 1: Article Illustrations

bash

# 1. Create project
mkdir article-images && cd article-images

# 2. Prepare prompts
mkdir prompts
# Create prompts/01-封面.md, 02-配图1.md, etc.

# 3. Generate images
npx -y bun ~/.claude/skills/pw-image-generation/scripts/generate-image.ts

# 4. Merge into long image (optional)
npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-long-image.ts ./images 长图.png

Scenario 2: PPT Illustrations

bash

# 1. Create project
mkdir ppt-images && cd ppt-images

# 2. Prepare prompts (named in page order)
mkdir prompts
# Create prompts/01-标题页.md, 02-内容1.md, etc.

# 3. Generate images
npx -y bun ~/.claude/skills/pw-image-generation/scripts/generate-image.ts

# 4. Package into PPT
npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-pptx.ts ./images 配图.pptx

Scenario 3: Image-to-Image

bash

# 1. Upload reference image
npx -y bun ~/.claude/skills/pw-image-generation/scripts/upload-image.ts ./template/参考图.png

# 2. Use returned URL in prompt
# prompts/01-类似风格.md:
# image_url: https://iili.io/xxx.png
# prompt: Scene with similar style, maintain color tone and composition

# 3. Generate images
npx -y bun ~/.claude/skills/pw-image-generation/scripts/generate-image.ts

Command Cheat Sheet

bash

# Generate images
npx -y bun ~/.claude/skills/pw-image-generation/scripts/generate-image.ts [output directory]

# Upload images
npx -y bun ~/.claude/skills/pw-image-generation/scripts/upload-image.ts <image path>

# Manage hosting service
npx -y bun ~/.claude/skills/pw-image-generation/scripts/delete-image.ts list
npx -y bun ~/.claude/skills/pw-image-generation/scripts/delete-image.ts delete <index>
npx -y bun ~/.claude/skills/pw-image-generation/scripts/delete-image.ts delete-all

# Merge into long image
npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-long-image.ts <image directory> <output file>

# Package into PPT
npx -y bun ~/.claude/skills/pw-image-generation/scripts/merge-to-pptx.ts <image directory> <output file>

# Analyze image
npx -y bun ~/.claude/skills/pw-image-generation/scripts/analyze-image.ts <image URL or path>

pw-image-generation

NPX Install

Tags

SKILL.md Content (Chinese)

Image-Generation - AI Image Generation Workflow

Core Features

Usage Scenarios

Workflow

Script Directory

Quick Start

Step 1: Create Project Directory

Step 2: Copy Configuration Template (Optional)

Step 3: Create Prompts

Step 4: Generate Images

Tool Script Details

1. Generate Images

2. Upload Images to Hosting Service

3. Manage Hosted Images

4. Merge into Long Image

5. Package into PPT

6. Analyze Image Style

File Structure

Project Directory Structure

Skill Directory Structure

Common Issues and Error Handling

1. Image Generation Failure

2. Image Hosting Upload Failure

3. Long Image Merging Failure

4. PPT Generation Failure

5. Prompts Not Effective

6. Batch Generation Interruption

7. Configuration File Issues

Best Practices

Image Size Specifications

Prompt Design

Image Generation Process

Image-to-Image Tips

File Management

Performance Optimization

Quality Control

Important Notes

Avoid Credit Wastage

Configuration Management

Runtime Environment

Configuration Instructions

Style Library

Usage Suggestions

Agent Usage Guide

Typical Workflows

Command Cheat Sheet