Cover Image Generator

Generate elegant cover images for articles with 5-dimensional customization. Supports Chinese text rendering.

Usage

# Auto-select dimensions based on content
/cover-image path/to/article.md

# Quick mode: skip confirmation
/cover-image article.md --quick

# Specify dimensions
/cover-image article.md --type conceptual --palette warm --rendering flat-vector

# WeChat Official Account cover
/cover-image article.md --aspect 2.35:1

# Specify provider
/cover-image article.md --provider qwen

# Use style preset
/cover-image article.md --style tech-dark

# Large font for better visibility
/cover-image article.md --font-size large

# Generate multiple options
/cover-image article.md --n 3

# With reference images (Google/OpenAI only)
/cover-image article.md --ref style-ref.png

# Direct content input
/cover-image --palette mono --aspect 1:1 --quick
[paste content]

Options

Providers

Provider Selection Logic

1. --provider specified -> use it
2. Chinese title detected -> auto-select qwen
3. Reference images provided -> use google or openai
4. Default -> qwen

Qwen-Image (Default)

Best for Chinese text rendering. Native support for Chinese characters.

API Endpoint: https://dashscope.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis

Environment Variable: DASHSCOPE_API_KEY

Supported Sizes: 1664*928, 1024*1024, 928*1664, 1472*1104, 1104*1472

OpenAI

Good for English text and creative designs.

Environment Variable: OPENAI_API_KEY

Supported Sizes: 1024x1024, 1536x1024, 1024x1536

Google

Good for multimodal generation with reference images.

Environment Variable: GOOGLE_API_KEY

Supported Sizes: Various aspect ratios supported

Five Dimensions

Auto-selection rules: references/auto-selection.md

Galleries

Types: hero, conceptual, typography, metaphor, scene, minimal -> Details: references/types.md

Palettes: warm, elegant, cool, dark, earth, vivid, pastel, mono, retro -> Details: references/palettes/

Renderings: flat-vector, hand-drawn, painterly, digital, pixel, chalk -> Details: references/renderings/

Text Levels: none (pure visual) | title-only (default) | title-subtitle | text-rich (with tags) -> Details: references/dimensions/text.md

Mood Levels: subtle (low contrast) | balanced (default) | bold (high contrast) -> Details: references/dimensions/mood.md

Fonts: clean (sans-serif) | handwritten | serif | display (bold decorative) -> Details: references/dimensions/font.md

File Structure

Output directory per default_output_dir preference:

• same-dir: {article-dir}/
• imgs-subdir: {article-dir}/imgs/
• independent (default): cover-image/{topic-slug}/

<output-dir>/
├── source-{slug}.{ext}    # Source files
├── refs/                  # Reference images (if provided)
│   ├── ref-01-{slug}.{ext}
│   └── ref-01-{slug}.md   # Description file
├── prompts/cover.md       # Generation prompt
└── cover.png              # Output image

Slug: 2-4 words, kebab-case. Conflict: append -YYYYMMDD-HHMMSS

Workflow

Progress Checklist

Cover Image Progress:
- [ ] Step 1: Analyze content + save refs + determine output dir
- [ ] Step 2: Confirm options (6 dimensions + provider) unless --quick
- [ ] Step 3: Create prompt
- [ ] Step 4: Generate image
- [ ] Step 5: Resize for platform (if needed)
- [ ] Step 6: Completion report

Step 1: Analyze Content

1. Save reference images (if provided) -> references/workflow/reference-images.md
2. Save source content (if pasted, save to source.md)
3. Analyze content: topic, tone, keywords, visual metaphors
4. Deep analyze references: Extract specific, concrete elements
5. Detect language: Compare source, user input
6. Determine output directory: Per File Structure rules
7. Auto-select provider: Based on language and references

Step 2: Confirm Options

Full confirmation flow: references/workflow/confirm-options.md

Step 3: Create Prompt

Save to prompts/cover.md. Template: references/workflow/prompt-template.md

CRITICAL - References in Frontmatter:

• Files saved to refs/ -> Add to frontmatter references list
• Style extracted verbally (no file) -> Omit references, describe in body
• Before writing -> Verify: test -f refs/ref-NN-{slug}.{ext}

Reference elements in body MUST be detailed, prefixed with "MUST"/"REQUIRED", with integration approach.

Step 4: Generate Image

1. Backup existing cover.png if regenerating
2. Select provider based on language and options
3. Process references from prompt frontmatter:
   • direct usage -> pass reference images directly (google/openai only)
   • style/palette -> extract traits, append to prompt
4. Generate via provider API:
   • Qwen: POST to dashscope API, poll for result
   • OpenAI: Use ImageGen tool or API
   • Google: Use ImageGen tool with reference images
5. On failure: auto-retry once

Step 5: Resize for Platform

Resize generated image to target platform size:

Step 6: Completion Report

Cover Generated!

Provider: [provider]
Topic: [topic]
Type: [type] | Palette: [palette] | Rendering: [rendering]
Text: [text] | Mood: [mood] | Font: [font] | Aspect: [ratio]
Title: [title or "visual only"]
Language: [lang]
References: [N images or "extracted style" or "none"]
Location: [directory path]

Files:
- source-{slug}.{ext}
- prompts/cover.md
- cover.png
- cover-{platform}.png (if resized)

Composition Principles

• Whitespace: 40-60% breathing room
• Visual anchor: Main element centered or offset left
• Characters: Simplified silhouettes; NO realistic humans
• Title: Use exact title from user/source; never invent

Aspect Ratios

Environment Variables

References

Dimensions: text.md | mood.md | font.md Palettes: references/palettes/ Renderings: references/renderings/ Types: references/types.md Style Presets: references/style-presets.md Auto-Selection: references/auto-selection.md Visual Elements: references/visual-elements.md Workflow: confirm-options.md | prompt-template.md | reference-images.md | qwen-api.md