Cover Image

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

Auto-Selection Rules

When a dimension is omitted, select based on content signals.

Auto Type Selection

Auto Palette Selection

Auto Rendering Selection

Auto Text Selection

Default: title-only

Auto Mood Selection

Default: balanced

Auto Font Selection

Default: clean

Auto Provider Selection

Font Dimension

Controls typography style and character feel.

Values

Detail

clean

Modern, universal typography with neutral character.

Characteristics:

• Geometric sans-serif letterforms
• Sharp, uniform line weight
• Clean edges, no flourishes
• High readability at all sizes
• Minimal personality, maximum clarity

Use Cases:

• Technical documentation
• Professional/corporate content
• Minimal design approaches
• Data-driven articles
• Modern brand aesthetics

Prompt Hints:

• Use clean geometric sans-serif typography
• Modern, minimal letterforms
• Sharp edges, uniform stroke weight
• High contrast against background

handwritten

Warm, organic typography with personal character.

Characteristics:

• Hand-lettered or brush style
• Organic, varied line weight
• Natural imperfections
• Approachable, human feel
• Casual yet intentional

Use Cases:

• Personal stories
• Lifestyle content
• Wellness and self-improvement
• Creative tutorials
• Friendly brand voices

Prompt Hints:

• Use warm hand-lettered typography with organic brush strokes
• Friendly, personal feel
• Natural variation in stroke weight
• Approachable, human character

serif

Classic, elegant typography with editorial authority.

Characteristics:

• Traditional serif letterforms
• Refined, structured strokes
• Elegant proportions
• Timeless sophistication
• Formal, trustworthy feel

Use Cases:

• Editorial content
• Academic articles
• Luxury brand content
• Historical topics
• Literary pieces

Prompt Hints:

• Use elegant serif typography with refined letterforms
• Classic, editorial character
• Structured, proportional spacing
• Authoritative, sophisticated feel

display

Bold, decorative typography for maximum impact.

Characteristics:

• Heavy, expressive letterforms
• Decorative elements
• Strong visual presence
• Playful or dramatic character
• Designed for headlines

Use Cases:

• Announcements
• Entertainment content
• Promotional materials
• Event marketing
• Gaming topics

Prompt Hints:

• Use bold decorative display typography
• Heavy, expressive headlines
• Strong visual impact
• Attention-grabbing character

Default

clean -- Universal, pairs well with most rendering styles.

Rendering Compatibility

yes++ = highly recommended | yes = compatible | no = not recommended

Type Compatibility

Palette Interaction

Font style adapts to palette characteristics:

Auto Selection

When --font is omitted, select based on signals:

Default: clean

Mood Dimension

Controls emotional intensity and visual weight of cover images.

Values

Detail

subtle

Calm, understated visual presence.

Characteristics:

• Low contrast between elements
• Muted, desaturated colors
• Light visual weight
• Gentle, refined aesthetic
• Soft edges and transitions

Use Cases:

• Thought leadership content
• Professional/corporate communications
• Meditation, wellness topics
• Academic or scholarly articles
• Luxury brand aesthetics

Color Guidance:

• Pastels, earth tones, neutrals
• Low saturation (30-50%)
• Soft gradients
• Minimal color variety (2-3 colors)

balanced

Versatile, harmonious visual presence.

Characteristics:

• Medium contrast
• Natural saturation levels
• Balanced visual weight
• Clear but not aggressive
• Standard aesthetic approach

Use Cases:

• General articles (default)
• Most blog content
• Educational material
• Product documentation
• News and updates

Color Guidance:

• Standard saturation (50-70%)
• Complementary color schemes
• Clear foreground/background separation
• Moderate color variety (3-4 colors)

bold

Dynamic, high-impact visual presence.

Characteristics:

• High contrast between elements
• Vivid, saturated colors
• Heavy visual weight
• Energetic, attention-grabbing
• Sharp edges and strong shapes

Use Cases:

• Product launches
• Promotional announcements
• Event marketing
• Call-to-action content
• Entertainment/gaming topics

Color Guidance:

• High saturation (70-100%)
• Vibrant, primary colors
• Strong contrast ratios
• Dynamic color combinations (4+ colors)

Type Compatibility

yes++ = highly recommended | yes = compatible | no = not recommended

Palette Interaction

Mood modifies the base palette characteristics:

Rendering Interaction

Mood adjusts rendering characteristics:

Auto Selection

When --mood is omitted, select based on signals:

Default: balanced

Text Dimension

Controls text density and information hierarchy on cover images.

Values

Detail

none

Pure visual cover with no text elements.

Use Cases:

• Photography-focused covers
• Abstract art pieces
• Visual-only social sharing
• When title added externally

Composition:

• Full visual area available
• No reserved text zones
• Emphasis on visual metaphor

title-only

Single headline, maximum impact.

Use Cases:

• Most article covers (default)
• Clear single message
• Strong brand recognition

Composition:

• Title: prominent placement
• Reserved zone: top or bottom 15%
• Visual supports title message

Title Guidelines:

• Use exact title from source content or user-provided title
• Do NOT invent or modify titles
• Match content language

title-subtitle

Title with supporting context.

Use Cases:

• Technical articles needing clarification
• Series with episode/part info
• Content with dual messages

Composition:

• Title: primary element
• Subtitle: secondary element
• Reserved zone: 25%
• Clear hierarchy between title/subtitle

Subtitle Guidelines:

• Clarify or contextualize title
• Can include series name, author, date
• Smaller, less prominent than title

text-rich

Information-dense cover with multiple text elements.

Use Cases:

• Infographic-style covers
• Event announcements with details
• Promotional material with features
• Content with multiple key points

Composition:

• Title: primary focus
• Subtitle: supporting info
• Tags: 2-4 keyword labels
• Reserved zone: 40%
• Clear visual hierarchy

Tag Guidelines:

• 2-4 tags maximum
• Short keywords (1-2 words each)
• Positioned as badges/labels
• Can highlight: category, date, author, key features

Type Compatibility

yes++ = highly recommended | yes = compatible | no = not recommended

Auto Selection

When --text is omitted, select based on signals:

Default: title-only

cool

Calm, professional, technical

Color Palette

Decorative Hints

• Circuit patterns, code snippets
• Geometric shapes, clean lines
• Data visualization elements
• Subtle tech iconography

Best For

Technology, SaaS, APIs, architecture, data science, engineering

dark

Dramatic, premium, cinematic

Color Palette

Decorative Hints

• Glowing effects, neon accents
• Gradient overlays
• Dramatic lighting
• Tech/futuristic patterns

Best For

Entertainment, gaming, premium products, dark mode interfaces

earth

Natural, organic, grounded

Color Palette

Decorative Hints

• Leaf and plant motifs
• Natural textures (wood, stone)
• Organic shapes and curves
• Nature-inspired patterns

Best For

Nature, wellness, sustainability, travel, organic products

elegant

Sophisticated, refined, professional

Color Palette

Decorative Hints

• Abstract geometric patterns
• Elegant gradients
• Minimalist decorative lines
• Luxurious textures

Best For

Business, luxury brands, thought leadership, professional services

mono

Clean, minimal, focused

Color Palette

Decorative Hints

• Minimal lines and shapes
• Strong typography focus
• Clean geometric patterns
• Subtle textures

Best For

Minimalist design, zen topics, focus, essential concepts

pastel

Soft, gentle, dreamy

Color Palette

Decorative Hints

• Soft clouds, bubbles
• Gentle gradients
• Cute character elements
• Whimsical patterns

Best For

Children, fantasy, creative projects, gentle topics, dreamlike content

retro

Nostalgic, vintage, classic

Color Palette

Decorative Hints

• Vintage patterns
• Grain and texture overlays
• Classic typography elements
• Nostalgic decorative borders

Best For

History, nostalgia, vintage topics, classic design, exploration

vivid

Energetic, vibrant, attention-grabbing

Color Palette

Decorative Hints

• Bold geometric shapes
• Dynamic gradients
• Playful patterns
• Energetic movement lines

Best For

Product launches, events, gaming, youth brands, announcements

warm

Friendly, approachable, human-centered

Color Palette

Decorative Hints

• Sun rays, warm lighting effects
• Rounded shapes, organic curves
• Hearts, smiling faces, friendly icons
• Warm gradient overlays

Best For

Personal growth, lifestyle, education, human stories, emotion, community

chalk

Educational, classroom, textured

Core Characteristics

Chalk-on-blackboard aesthetic with dusty texture, hand-drawn feel, and educational character. Think classroom boards, workshop presentations, and tutorial graphics.

Lines

• Chalk-like stroke quality
• Slightly rough edges
• Varied opacity (pressure simulation)
• Visible texture in strokes

Texture

• Chalk dust and smudges
• Blackboard texture
• Erased line remnants
• Grainy surface feel

Depth

• Flat with texture variation
• Layering through opacity
• Smudging for soft effects
• No traditional shadows

Element Vocabulary

• Hand-drawn diagrams
• Chalk-style icons
• Mathematical/educational symbols
• Decorative: arrows, boxes, underlines
• Chart and diagram elements

Typography Approach

• Chalk handwriting style
• Slightly irregular letters
• Educational, approachable feel
• Visible texture in text

digital

Polished, precise, modern

Core Characteristics

Clean digital aesthetic with subtle gradients, soft shadows, and polished finish. Think modern UI design, tech illustrations, and SaaS graphics.

Lines

• Crisp, precise edges
• Smooth bezier curves
• Consistent weight or subtle variation
• Perfect corners and endings

Texture

• Subtle noise or grain (optional)
• Soft gradients
• Clean fills with polish
• Glass-like surfaces

Depth

• Soft drop shadows
• Subtle gradients for dimension
• Layered with transparency
• 3D-style depth through shadows

Element Vocabulary

• Precision icons and symbols
• Gradient-filled shapes
• Glass-morphism elements
• Decorative: glows, highlights, reflections
• Tech-inspired patterns

Typography Approach

• Modern sans-serif fonts
• Crisp, clean rendering
• Subtle shadows or glows
• Professional appearance

flat-vector

Clean, modern, geometric illustration

Core Characteristics

Flat design with clean outlines, uniform fills, and no texture or depth. Think modern app icons, infographic illustrations, and vector-based editorial art.

Lines

• Clean outlines with uniform stroke weight
• Closed shapes (coloring-book style)
• Rounded line endings, avoid sharp corners
• Consistent stroke width throughout

Texture

• None: smooth, flat color fills only
• No gradients, shadows, or noise
• Solid color blocks

Depth

• Flat: no shadows, no perspective
• 2D layering with overlap for depth illusion
• Optional 2.5D isometric layering (front/back occlusion, no atmospheric perspective)
• No 3D effects or bevels

Element Vocabulary

• Geometric icons and simple shapes
• Bold outlined objects with clean fills
• Geometric simplification: complex objects -> basic shapes (trees -> lollipop/triangle, buildings -> rectangles)
• "Toy model" aesthetic: cute, rounded proportions
• Decorative: dots, lines, sunbursts, pill-shaped clouds, small stars
• Isolated elements on clean backgrounds

Typography Approach

• Clean sans-serif or bold geometric lettering
• Strong readability, consistent weight
• Easily scalable at any size

hand-drawn

Organic, personal, sketch-like

Core Characteristics

Hand-crafted appearance with visible line quality, natural imperfections, and warm character. Think editorial sketches, notebook doodles, and artisan illustration.

Lines

• Varied stroke weight (pressure sensitivity)
• Slightly wobbly, organic curves
• Pencil or marker quality
• Visible line endings (not perfectly capped)

Texture

• Light paper grain
• Pencil smudges or marker bleeds
• Optional cross-hatching for shading
• Scanned paper feel

Depth

• Minimal: flat with line weight variation
• Overlapping strokes for layering
• Optional simple drop shadows (hand-drawn style)

Element Vocabulary

• Sketchy icons and doodles
• Objects with character and quirk
• Wobbly circles and imperfect shapes
• Decorative: stars, swirls, arrows, speech bubbles
• White space as design element

Typography Approach

• Hand-lettered or marker-style fonts
• Varied weight and width
• Casual, friendly character
• Organic baseline (slightly wavy)

painterly

Artistic, soft, brush-textured

Core Characteristics

Traditional art media appearance with visible brushstrokes, soft edges, and artistic texture. Think watercolor paintings, digital art, and editorial illustration.

Lines

• Soft, blurry edges
• Brush stroke quality
• Varied weight from pressure
• Painted, not drawn

Texture

• Visible brush strokes
• Paper or canvas texture
• Paint splatters or drips
• Layered translucent washes

Depth

• Soft edges, atmospheric perspective
• Layered translucent colors
• Gradient washes
• Depth through color intensity

Element Vocabulary

• Painted illustrations
• Organic, flowing shapes
• Soft-edged icons and symbols
• Decorative: splashes, dots, strokes
• Blurred boundaries between elements

Typography Approach

• Painted or brush-script fonts
• Soft edges on text
• Hand-painted feel
• Artistic character

pixel

Retro, nostalgic, 8-bit

Core Characteristics

Grid-based pixel art aesthetic with chunky squares, limited color palette, and nostalgic feel. Think classic video games, retro computing, and 8-bit art.

Lines

• Sharp, blocky edges (no curves)
• Grid-aligned pixels
• Jagged diagonal lines
• Uniform square pixels

Texture

• None: pure pixels
• Dithering for shading
• Limited color palette
• Grid visibility

Depth

• Flat: no shadows
• Depth through layering
• Isometric perspective common
• Parallax-style depth layers

Element Vocabulary

• Pixel-art icons and characters
• Blocky shapes and objects
• Sprite-style elements
• Decorative: pixel stars, hearts, coins
• Game UI elements (health bars, buttons)

Typography Approach

• Pixel/bitmap fonts
• Grid-aligned letters
• Chunky, blocky appearance
• Retro gaming feel

Style Presets

Quick style presets for common use cases. Use --style <preset> to apply.

Available Presets

Preset Details

tech-dark

科技感黑色系，适合技术博客和科技文章。

type: conceptual
palette: dark
rendering: digital
mood: bold
font: clean

Prompt hints:

• Deep black background (#000000)
• Electric blue accents (#3B82F6)
• Circuit patterns, geometric shapes
• Large bold title with glow effect

tech-clean

清爽科技风，适合技术文档和架构图。

type: conceptual
palette: cool
rendering: flat-vector
mood: balanced
font: clean

Prompt hints:

• Light gray background (#F7FAFC)
• Deep blue primary (#2B6CB0)
• Clean geometric icons
• Minimal decoration

lifestyle-warm

温馨生活风，适合生活方式和个人故事。

type: scene
palette: warm
rendering: painterly
mood: subtle
font: handwritten

Prompt hints:

• Warm cream background (#FFFAF0)
• Soft orange accents (#ED8936)
• Organic shapes, gentle gradients
• Friendly, approachable feel

business-elegant

商务优雅风，适合商业文章和专业报告。

type: hero
palette: elegant
rendering: digital
mood: subtle
font: serif

Prompt hints:

• Off-white background (#FAFAFA)
• Deep purple accents (#553C9A)
• Clean lines, professional layout
• Elegant typography

announcement-bold

醒目公告风，适合产品发布和活动公告。

type: hero
palette: vivid
rendering: flat-vector
mood: bold
font: display

Prompt hints:

• White or vibrant background
• Bold primary colors
• Dynamic shapes, high contrast
• Large impactful title

minimal-zen

极简禅意风，适合哲学思考和核心概念。

type: minimal
palette: mono
rendering: flat-vector
mood: subtle
font: clean

Prompt hints:

• Pure white background (#FFFFFF)
• Black or dark gray accents
• Single focal element
• Maximum whitespace (60%+)

creative-playful

创意童趣风，适合创意内容和轻松话题。

type: metaphor
palette: pastel
rendering: hand-drawn
mood: balanced
font: handwritten

Prompt hints:

• Light pink/cream background
• Soft pastel colors
• Playful doodles, organic lines
• Friendly, whimsical feel

retro-vintage

复古怀旧风，适合历史内容和怀旧话题。

type: scene
palette: retro
rendering: painterly
mood: subtle
font: serif

Prompt hints:

• Sepia-toned background
• Burnt orange, mustard colors
• Vintage textures, grain overlay
• Classic typography

Usage

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

# Preset with custom aspect
/cover-image article.md --style announcement-bold --aspect 2.35:1

# Override preset dimensions
/cover-image article.md --style tech-dark --palette cool

Custom Presets

Users can create custom presets by adding to their EXTEND.md:

style_presets:
  my-brand:
    type: hero
    palette: elegant
    rendering: digital
    mood: subtle
    font: clean
    custom_prompt_hints: |
      Use brand colors: primary #FF6B35, background #1A1A2E
      Include subtle brand pattern in background

Type Composition Guidelines

Type Gallery

Type-Specific Composition

Visual Elements Library

Icon and symbol vocabulary organized by topic. Use these as building blocks for cover compositions.

Tech & Development

Ideas & Innovation

Communication & Collaboration

Nature & Growth

Tools & Actions

Abstract Concepts

Combination Patterns

Create visual metaphors by combining elements:

Rendering-Specific Treatment

Confirm Options Workflow

Step 2: Confirm Options

After analyzing content, confirm the 6 dimensions and provider with the user.

Skip Conditions

Confirmation Flow

1. Display auto-selected options
2. Ask user to confirm or modify
3. If modified, validate choice
4. Proceed to prompt creation

Confirmation Message Template

Cover Image Options:

Content: [title/topic]
Language: [detected language]

Dimensions:
- Type: [type] -- [brief reason]
- Palette: [palette] -- [brief reason]
- Rendering: [rendering] -- [brief reason]
- Text: [text level]
- Mood: [mood]
- Font: [font]

Provider: [provider] -- [brief reason]
Aspect: [ratio] (default: 16:9)
Output: [directory path]

Proceed? [y/n] or modify: [type=X palette=Y provider=Z ...]

Quick Mode

When --quick is set, skip confirmation entirely:

1. Auto-select all dimensions 2. Auto-select provider based on language and references 3. Use default aspect ratio (16:9) unless --aspect specified 4. Proceed directly to prompt creation 5. Show selections in completion report

Dimension Validation

When user provides a value, validate it exists:

If invalid, show valid options and ask again.

Provider Selection

When provider is not specified, auto-select based on signals:

Aspect Ratio Selection

When aspect ratio is not specified, ask separately:

Aspect Ratio Options:
- 16:9 (default) -- Widescreen, blog posts
- 2.35:1 -- 公众号封面 (900x383px)
- 4:3 -- Classic, presentations
- 3:2 -- Photography standard
- 1:1 -- Square, social media
- 3:4 -- Portrait, mobile

Select aspect ratio: [default: 16:9]

Platform Mapping

Step 3: Prompt Template

Save to prompts/cover.md:

---
type: cover
palette: [confirmed palette]
rendering: [confirmed rendering]
references:
  - ref_id: 01
    filename: refs/ref-01-{slug}.{ext}
    usage: direct | style | palette
---

# Content Context
Article title: [full original title from source]
Content summary: [2-3 sentence summary of key points and themes]
Keywords: [5-8 key terms extracted from content]

# Visual Design
Cover theme: [2-3 words visual interpretation]
Type: [confirmed type]
Palette: [confirmed palette]
Rendering: [confirmed rendering]
Font: [confirmed font]
Text level: [confirmed text level]
Mood: [confirmed mood]
Aspect ratio: [confirmed ratio]
Language: [confirmed language]

# Text Elements
[Based on text level:]
- none: "No text elements"
- title-only: "Title: [exact title from source or user]"
- title-subtitle: "Title: [title] / Subtitle: [context]"
- text-rich: "Title: [title] / Subtitle: [context] / Tags: [2-4 keywords]"

# Mood Application
[Based on mood level:]
- subtle: "Use low contrast, muted colors, light visual weight, calm aesthetic"
- balanced: "Use medium contrast, normal saturation, balanced visual weight"
- bold: "Use high contrast, vivid saturated colors, heavy visual weight, dynamic energy"

# Font Application
[Based on font style:]
- clean: "Use clean geometric sans-serif typography. Modern, minimal letterforms."
- handwritten: "Use warm hand-lettered typography with organic brush strokes. Friendly, personal feel."
- serif: "Use elegant serif typography with refined letterforms. Classic, editorial character."
- display: "Use bold decorative display typography. Heavy, expressive headlines."

# Composition
Type composition:
- [Type-specific layout and structure]

Visual composition:
- Main visual: [metaphor derived from content meaning]
- Layout: [positioning based on type and aspect ratio]
- Decorative: [palette-specific elements that reinforce content theme]

Color scheme: [primary, background, accent from palette definition, adjusted by mood]
Rendering notes: [key characteristics from rendering definition]
Type notes: [key characteristics from type definition]
Palette notes: [key characteristics from palette definition]

[Reference images section if provided]

Reference-Driven Design

When reference images are provided, they are the primary visual input and MUST strongly influence the output.

Passing `--ref` alone is NOT enough. Image generation models often ignore reference images unless the prompt text explicitly describes what to reproduce. Always combine --ref with detailed textual instructions.

Type-Specific Composition

Title Guidelines

When text level includes title:

• Source: Use the exact title provided by user, or extract from source content
• Do NOT invent titles: Stay faithful to the original
• Match confirmed language

Reference Image Handling

When user provides reference images (--ref or pasted images):

Reference Analysis Template

Output: Each extracted element should be written as a copy-pasteable prompt instruction prefixed with "MUST" or "REQUIRED".

Qwen Image API 调用指南

API 端点

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

环境变量

DASHSCOPE_API_KEY=your-api-key

Python 调用示例

import requests
import os
import json
import time

def generate_cover(prompt, output_path, size='1664*928'):
    """
    使用 Qwen-Image-Plus 生成封面图片
    
    Args:
        prompt: 图片描述提示词
        output_path: 输出图片路径
        size: 图片尺寸 (1664*928, 1024*1024, 928*1664, 1472*1104, 1104*1472)
    
    Returns:
        str: 生成的图片路径
    """
    api_key = os.environ.get('DASHSCOPE_API_KEY')
    
    headers = {
        'Authorization': f'Bearer {api_key}',
        'Content-Type': 'application/json',
        'X-DashScope-Async': 'enable'  # 异步模式
    }
    
    payload = {
        'model': 'qwen-image-plus',
        'input': {
            'prompt': prompt
        },
        'parameters': {
            'size': size,
            'n': 1
        }
    }
    
    # 1. 提交任务
    url = 'https://dashscope.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis'
    response = requests.post(url, headers=headers, json=payload)
    result = response.json()
    
    if 'output' not in result or 'task_id' not in result['output']:
        raise Exception(f"Task creation failed: {result}")
    
    task_id = result['output']['task_id']
    
    # 2. 轮询任务状态
    for i in range(60):  # 最多等待 3 分钟
        time.sleep(3)
        query_url = f'https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}'
        query_response = requests.get(query_url, headers={'Authorization': f'Bearer {api_key}'})
        query_result = query_response.json()
        status = query_result.get('output', {}).get('task_status', 'UNKNOWN')
        
        if status == 'SUCCEEDED':
            # 3. 下载图片
            image_url = query_result['output']['results'][0]['url']
            img_response = requests.get(image_url)
            
            with open(output_path, 'wb') as f:
                f.write(img_response.content)
            
            return output_path
        
        elif status == 'FAILED':
            raise Exception(f"Generation failed: {query_result}")
    
    raise Exception("Generation timeout after 3 minutes")


def resize_for_wechat(input_path, output_path):
    """
    将图片调整为公众号封面尺寸 900x383
    
    Args:
        input_path: 输入图片路径
        output_path: 输出图片路径
    """
    from PIL import Image
    
    img = Image.open(input_path)
    
    # 缩放并裁剪
    img_resized = img.resize((900, 502), Image.LANCZOS)
    top = (502 - 383) // 2
    img_crop = img_resized.crop((0, top, 900, top + 383))
    img_crop.save(output_path)
    
    return output_path

错误处理

尺寸映射

Reference Images Workflow

Step 1: Save Reference Images

When user provides reference images, save them systematically:

<output-dir>/refs/
├── ref-01-{slug}.{ext}      # Reference image file
├── ref-01-{slug}.md         # Analysis/notes file
├── ref-02-{slug}.{ext}
├── ref-02-{slug}.md
└── ...

Naming Convention

• ref-NN: Sequential number (01, 02, 03...)
• {slug}: 2-4 word kebab-case describing the reference
• {ext}: Original file extension (png, jpg, etc.)

Step 2: Analyze Reference Images

For each reference image, extract:

Step 3: Generate Analysis File

Create a .md file for each reference with analysis:

# Reference 01: [name]

## Visual Style
- Rendering: [flat-vector/hand-drawn/etc.]
- Line quality: [description]
- Texture: [description]

## Composition
- Layout: [description]
- Focal point: [description]
- Whitespace: [percentage/feel]

## Colors
- Primary: [hex values]
- Secondary: [hex values]
- Background: [hex values]

## Elements
- [List of visual elements]

## Integration Notes
- [How to use this reference in generation]

Step 4: Add to Prompt Frontmatter

When reference files are saved, add to prompt frontmatter:

---
type: cover
palette: warm
rendering: flat-vector
references:
  - ref_id: 01
    filename: refs/ref-01-style-reference.png
    usage: style
  - ref_id: 02
    filename: refs/ref-02-color-reference.jpg
    usage: palette
---

Usage Types

Step 5: Embed in Prompt Body

CRITICAL: Passing --ref alone is NOT enough. You MUST write detailed textual instructions.

# Reference Style -- MUST INCORPORATE

CRITICAL: The generated cover MUST visually reference the provided images.

## From Ref 1 ([filename]) -- REQUIRED elements:
- [Brand element]: [Specific description]
- [Signature pattern]: [Specific description]
- [Colors]: [Exact hex values]
- [Typography]: [Specific treatment]
- [Layout element]: [Specific spatial element]

## Integration approach:
[Specific layout instruction describing how reference elements combine]

Guidelines

• Each visual element gets its own bullet with "MUST" or "REQUIRED"
• Descriptions must be specific enough to reproduce
• The integration approach must describe exact spatial arrangement
• After generation, verify reference elements are visible; if not, strengthen and regenerate