mirror of
https://github.com/JimLiu/baoyu-skills.git
synced 2026-07-12 22:09:48 +08:00
Compare commits
5 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Jim Liu 宝玉
|
b53a5db60a | ||
|
Jim Liu 宝玉
|
372e03cef3 | ||
|
Jim Liu 宝玉
|
ea8ad82786 | ||
|
Jim Liu 宝玉
|
6fffe252c0 | ||
|
Jim Liu 宝玉
|
86a84739e8 |
@@ -6,7 +6,7 @@
|
||||
},
|
||||
"metadata": {
|
||||
"description": "Skills shared by Baoyu for improving daily work efficiency",
|
||||
"version": "1.30.0"
|
||||
"version": "1.30.2"
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
|
||||
@@ -2,6 +2,20 @@
|
||||
|
||||
English | [中文](./CHANGELOG.zh.md)
|
||||
|
||||
## 1.30.2 - 2026-02-06
|
||||
|
||||
### Refactor
|
||||
- `baoyu-cover-image`: optimize SKILL.md from 532 to 233 lines (56% reduction); extract reference image handling to `references/workflow/reference-images.md`; condense galleries to value-only tables with links.
|
||||
|
||||
## 1.30.1 - 2026-02-06
|
||||
|
||||
### Features
|
||||
- `baoyu-image-gen`: add OpenAI GPT Image edits support for reference images (`--ref`); auto-select Google or OpenAI when ref provided.
|
||||
|
||||
### Fixes
|
||||
- `baoyu-image-gen`: change ref-related warnings to explicit errors with fix hints; add reference image validation.
|
||||
- `baoyu-cover-image`: enhance reference image analysis with deep extraction template; require MUST INCORPORATE section for concrete visual elements.
|
||||
|
||||
## 1.30.0 - 2026-02-06
|
||||
|
||||
### Features
|
||||
|
||||
@@ -2,6 +2,20 @@
|
||||
|
||||
[English](./CHANGELOG.md) | 中文
|
||||
|
||||
## 1.30.2 - 2026-02-06
|
||||
|
||||
### 重构
|
||||
- `baoyu-cover-image`：优化 SKILL.md 从 532 行精简至 233 行（减少 56%）；将参考图片处理流程提取到 `references/workflow/reference-images.md`；画廊改为纯值表格并链接到详细参考文件。
|
||||
|
||||
## 1.30.1 - 2026-02-06
|
||||
|
||||
### 新功能
|
||||
- `baoyu-image-gen`：新增 OpenAI GPT Image edits 支持参考图片（`--ref`）；提供 ref 时自动选择 Google 或 OpenAI。
|
||||
|
||||
### 修复
|
||||
- `baoyu-image-gen`：将 ref 相关警告改为明确错误提示；新增参考图片验证。
|
||||
- `baoyu-cover-image`：增强参考图片分析，使用深度提取模板；要求 MUST INCORPORATE 章节以包含具体可复现的视觉元素。
|
||||
|
||||
## 1.30.0 - 2026-02-06
|
||||
|
||||
### 新功能
|
||||
|
||||
@@ -10,169 +10,94 @@ Generate elegant cover images for articles with 5-dimensional customization.
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
# Auto-select all dimensions based on content
|
||||
# Auto-select dimensions based on content
|
||||
/baoyu-cover-image path/to/article.md
|
||||
|
||||
# Quick mode: skip confirmation, use auto-selection
|
||||
# Quick mode: skip confirmation
|
||||
/baoyu-cover-image article.md --quick
|
||||
|
||||
# Specify dimensions (new 5D system)
|
||||
# Specify dimensions
|
||||
/baoyu-cover-image article.md --type conceptual --palette warm --rendering flat-vector
|
||||
/baoyu-cover-image article.md --text title-subtitle --mood bold
|
||||
|
||||
# Style presets (backward-compatible shorthand for palette + rendering)
|
||||
# Style presets (shorthand for palette + rendering)
|
||||
/baoyu-cover-image article.md --style blueprint
|
||||
/baoyu-cover-image article.md --style blueprint --rendering hand-drawn # override rendering
|
||||
|
||||
# Visual only (no title text)
|
||||
/baoyu-cover-image article.md --no-title
|
||||
|
||||
# Direct content input
|
||||
/baoyu-cover-image
|
||||
[paste content]
|
||||
|
||||
# Direct input with options
|
||||
/baoyu-cover-image --palette mono --rendering digital --aspect 1:1 --quick
|
||||
[paste content]
|
||||
|
||||
# With reference images
|
||||
/baoyu-cover-image article.md --ref style-ref.png
|
||||
/baoyu-cover-image article.md --ref ref1.png ref2.png --quick
|
||||
|
||||
# Direct content input
|
||||
/baoyu-cover-image --palette mono --aspect 1:1 --quick
|
||||
[paste content]
|
||||
```
|
||||
|
||||
## Options
|
||||
|
||||
| Option | Description |
|
||||
|--------|-------------|
|
||||
| `--type <name>` | Cover type: hero, conceptual, typography, metaphor, scene, minimal |
|
||||
| `--palette <name>` | Color palette: warm, elegant, cool, dark, earth, vivid, pastel, mono, retro |
|
||||
| `--rendering <name>` | Rendering style: flat-vector, hand-drawn, painterly, digital, pixel, chalk |
|
||||
| `--style <name>` | Preset shorthand (expands to palette + rendering, see [Style Presets](references/style-presets.md)) |
|
||||
| `--text <level>` | Text density: none, title-only, title-subtitle, text-rich |
|
||||
| `--mood <level>` | Emotional intensity: subtle, balanced, bold |
|
||||
| `--font <name>` | Font style: clean, handwritten, serif, display |
|
||||
| `--type <name>` | hero, conceptual, typography, metaphor, scene, minimal |
|
||||
| `--palette <name>` | warm, elegant, cool, dark, earth, vivid, pastel, mono, retro |
|
||||
| `--rendering <name>` | flat-vector, hand-drawn, painterly, digital, pixel, chalk |
|
||||
| `--style <name>` | Preset shorthand (see [Style Presets](references/style-presets.md)) |
|
||||
| `--text <level>` | none, title-only, title-subtitle, text-rich |
|
||||
| `--mood <level>` | subtle, balanced, bold |
|
||||
| `--font <name>` | clean, handwritten, serif, display |
|
||||
| `--aspect <ratio>` | 16:9 (default), 2.35:1, 4:3, 3:2, 1:1, 3:4 |
|
||||
| `--lang <code>` | Title language (en, zh, ja, etc.) |
|
||||
| `--no-title` | Alias for `--text none` |
|
||||
| `--quick` | Skip confirmation, use auto-selection for missing dimensions |
|
||||
| `--quick` | Skip confirmation, use auto-selection |
|
||||
| `--ref <files...>` | Reference images for style/composition guidance |
|
||||
|
||||
## Five Dimensions
|
||||
|
||||
| Dimension | Controls | Values | Default |
|
||||
|-----------|----------|--------|---------|
|
||||
| **Type** | Visual composition, information structure | hero, conceptual, typography, metaphor, scene, minimal | auto |
|
||||
| **Palette** | Colors, color scheme, decorative hints | warm, elegant, cool, dark, earth, vivid, pastel, mono, retro | auto |
|
||||
| **Rendering** | Line quality, texture, depth, element style | flat-vector, hand-drawn, painterly, digital, pixel, chalk | auto |
|
||||
| **Text** | Text density, information hierarchy | none, title-only, title-subtitle, text-rich | title-only |
|
||||
| **Mood** | Emotional intensity, visual weight | subtle, balanced, bold | balanced |
|
||||
| **Font** | Typography style, character feel | clean, handwritten, serif, display | clean |
|
||||
| Dimension | Values | Default |
|
||||
|-----------|--------|---------|
|
||||
| **Type** | hero, conceptual, typography, metaphor, scene, minimal | auto |
|
||||
| **Palette** | warm, elegant, cool, dark, earth, vivid, pastel, mono, retro | auto |
|
||||
| **Rendering** | flat-vector, hand-drawn, painterly, digital, pixel, chalk | auto |
|
||||
| **Text** | none, title-only, title-subtitle, text-rich | title-only |
|
||||
| **Mood** | subtle, balanced, bold | balanced |
|
||||
| **Font** | clean, handwritten, serif, display | clean |
|
||||
|
||||
Dimensions can be freely combined. Auto-selection rules: [references/auto-selection.md](references/auto-selection.md)
|
||||
Auto-selection rules: [references/auto-selection.md](references/auto-selection.md)
|
||||
|
||||
## Type Gallery
|
||||
## Galleries
|
||||
|
||||
| Type | Description | Best For |
|
||||
|------|-------------|----------|
|
||||
| `hero` | Large visual impact, title overlay | Product launch, brand promotion, major announcements |
|
||||
| `conceptual` | Concept visualization, abstract core ideas | Technical articles, methodology, architecture design |
|
||||
| `typography` | Text-focused layout, prominent title | Opinion pieces, quotes, insights |
|
||||
| `metaphor` | Visual metaphor, concrete expressing abstract | Philosophy, growth, personal development |
|
||||
| `scene` | Atmospheric scene, narrative feel | Stories, travel, lifestyle |
|
||||
| `minimal` | Minimalist composition, generous whitespace | Zen, focus, core concepts |
|
||||
**Types**: hero, conceptual, typography, metaphor, scene, minimal
|
||||
→ Details: [references/types.md](references/types.md)
|
||||
|
||||
Type composition details: [references/types.md](references/types.md)
|
||||
**Palettes**: warm, elegant, cool, dark, earth, vivid, pastel, mono, retro
|
||||
→ Details: [references/palettes/](references/palettes/)
|
||||
|
||||
## Palette Gallery
|
||||
**Renderings**: flat-vector, hand-drawn, painterly, digital, pixel, chalk
|
||||
→ Details: [references/renderings/](references/renderings/)
|
||||
|
||||
| Palette | Vibe | Primary Colors |
|
||||
|---------|------|----------------|
|
||||
| `warm` | Friendly, approachable | Orange, golden yellow, terracotta |
|
||||
| `elegant` | Sophisticated, refined | Soft coral, muted teal, dusty rose |
|
||||
| `cool` | Technical, professional | Engineering blue, navy, cyan |
|
||||
| `dark` | Cinematic, premium | Electric purple, cyan, magenta |
|
||||
| `earth` | Natural, organic | Forest green, sage, earth brown |
|
||||
| `vivid` | Energetic, bold | Bright red, neon green, electric blue |
|
||||
| `pastel` | Gentle, whimsical | Soft pink, mint, lavender |
|
||||
| `mono` | Clean, focused | Black, near-black, white |
|
||||
| `retro` | Nostalgic, vintage | Muted orange, dusty pink, maroon |
|
||||
**Text Levels**: none (pure visual) | title-only (default) | title-subtitle | text-rich (with tags)
|
||||
→ Details: [references/dimensions/text.md](references/dimensions/text.md)
|
||||
|
||||
Palette definitions: [references/palettes/](references/palettes/)
|
||||
**Mood Levels**: subtle (low contrast) | balanced (default) | bold (high contrast)
|
||||
→ Details: [references/dimensions/mood.md](references/dimensions/mood.md)
|
||||
|
||||
## Rendering Gallery
|
||||
|
||||
| Rendering | Description | Key Characteristics |
|
||||
|-----------|-------------|---------------------|
|
||||
| `flat-vector` | Clean modern vector | Uniform outlines, flat fills, geometric icons |
|
||||
| `hand-drawn` | Sketchy organic illustration | Imperfect strokes, paper texture, doodles |
|
||||
| `painterly` | Soft watercolor/paint | Brush strokes, color bleeds, soft edges |
|
||||
| `digital` | Polished modern digital | Precise edges, subtle gradients, UI components |
|
||||
| `pixel` | Retro 8-bit pixel art | Pixel grid, dithering, chunky shapes |
|
||||
| `chalk` | Chalk on blackboard | Chalk strokes, dust effects, board texture |
|
||||
|
||||
Rendering definitions: [references/renderings/](references/renderings/)
|
||||
|
||||
## Text & Mood
|
||||
|
||||
| Text Level | Title | Subtitle | Tags | Use Case |
|
||||
|------------|:-----:|:--------:|:----:|----------|
|
||||
| `none` | - | - | - | Pure visual, no text |
|
||||
| `title-only` | ✓ | - | - | Simple headline (default) |
|
||||
| `title-subtitle` | ✓ | ✓ | - | Title + supporting context |
|
||||
| `text-rich` | ✓ | ✓ | ✓ (2-4) | Information-dense |
|
||||
|
||||
| Mood | Contrast | Saturation | Weight | Use Case |
|
||||
|------|:--------:|:----------:|:------:|----------|
|
||||
| `subtle` | Low | Muted | Light | Corporate, thought leadership |
|
||||
| `balanced` | Medium | Normal | Medium | General articles (default) |
|
||||
| `bold` | High | Vivid | Heavy | Announcements, promotions |
|
||||
|
||||
Full guides: [references/dimensions/text.md](references/dimensions/text.md) | [references/dimensions/mood.md](references/dimensions/mood.md)
|
||||
|
||||
## Font Gallery
|
||||
|
||||
| Font | Description | Best For |
|
||||
|------|-------------|----------|
|
||||
| `clean` | Modern geometric sans-serif | Tech, professional, minimal |
|
||||
| `handwritten` | Warm hand-lettered style | Personal, friendly, lifestyle |
|
||||
| `serif` | Classic elegant typography | Editorial, academic, luxury |
|
||||
| `display` | Bold decorative headlines | Announcements, entertainment |
|
||||
|
||||
Full guide: [references/dimensions/font.md](references/dimensions/font.md)
|
||||
|
||||
## Style Presets & Compatibility
|
||||
|
||||
- **Style Presets**: `--style X` expands to palette + rendering. See [references/style-presets.md](references/style-presets.md)
|
||||
- **Compatibility Matrices**: Palette×Rendering, Type×Rendering, Type×Text, Type×Mood. See [references/compatibility.md](references/compatibility.md)
|
||||
- ✓✓ = highly recommended | ✓ = compatible | ✗ = not recommended
|
||||
**Fonts**: clean (sans-serif) | handwritten | serif | display (bold decorative)
|
||||
→ Details: [references/dimensions/font.md](references/dimensions/font.md)
|
||||
|
||||
## File Structure
|
||||
|
||||
Output directory depends on `default_output_dir` preference:
|
||||
|
||||
| Preference | Output Path |
|
||||
|------------|-------------|
|
||||
| `same-dir` | `{article-dir}/` |
|
||||
| `imgs-subdir` | `{article-dir}/imgs/` |
|
||||
| `independent` (default) | `cover-image/{topic-slug}/` |
|
||||
| Pasted content | `cover-image/{topic-slug}/` (always) |
|
||||
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 (text, images, etc.)
|
||||
├── source-{slug}.{ext} # Source files
|
||||
├── refs/ # Reference images (if provided)
|
||||
│ ├── ref-01-{slug}.{ext}
|
||||
│ ├── ref-01-{slug}.md # Description file (optional)
|
||||
│ ├── ref-02-{slug}.{ext}
|
||||
│ ├── ref-02-{slug}.md # Description file (optional)
|
||||
│ └── extracted-style.md # Verbally extracted style (if no file path)
|
||||
│ └── ref-01-{slug}.md # Description file
|
||||
├── prompts/cover.md # Generation prompt
|
||||
└── cover.png # Output image
|
||||
```
|
||||
|
||||
**Slug**: Extract main topic (2-4 words, kebab-case). Example: "The Future of AI" → `future-of-ai`
|
||||
**Conflict**: If directory exists, append timestamp: `{topic-slug}-YYYYMMDD-HHMMSS`
|
||||
**Source Files**: Copy all sources with naming `source-{slug}.{ext}` (multiple supported)
|
||||
**Slug**: 2-4 words, kebab-case. Conflict: append `-YYYYMMDD-HHMMSS`
|
||||
|
||||
## Workflow
|
||||
|
||||
@@ -181,20 +106,10 @@ Output directory depends on `default_output_dir` preference:
|
||||
```
|
||||
Cover Image Progress:
|
||||
- [ ] Step 0: Check preferences (EXTEND.md) ⛔ BLOCKING
|
||||
- [ ] Found → load preferences → continue
|
||||
- [ ] Not found → run first-time setup → MUST complete before Step 1
|
||||
- [ ] Step 1: Analyze content + determine output directory
|
||||
- [ ] 1.1 Reference images ⚠️ (if provided)
|
||||
- [ ] File path given → saved to refs/ ✓
|
||||
- [ ] No path → asked user OR extracted verbally
|
||||
- [ ] 1.2 Output directory determined
|
||||
- [ ] Step 2: Confirm options (6 dimensions) ⚠️ REQUIRED unless --quick or all specified
|
||||
- [ ] Step 1: Analyze content + save refs + determine output dir
|
||||
- [ ] Step 2: Confirm options (6 dimensions) ⚠️ unless --quick
|
||||
- [ ] Step 3: Create prompt
|
||||
- [ ] References in prompt ONLY if files exist in refs/
|
||||
- [ ] Extracted style/palette appended to prompt body (if no file)
|
||||
- [ ] Step 4: Generate image
|
||||
- [ ] 4.1 References verified before generation
|
||||
- [ ] 4.2 Pass refs via --ref if skill supports AND files exist
|
||||
- [ ] Step 5: Completion report
|
||||
```
|
||||
|
||||
@@ -202,146 +117,40 @@ Cover Image Progress:
|
||||
|
||||
```
|
||||
Input → [Step 0: Preferences] ─┬─ Found → Continue
|
||||
│
|
||||
└─ Not found → First-Time Setup ⛔ BLOCKING
|
||||
│
|
||||
└─ Complete setup → Save EXTEND.md → Continue
|
||||
│
|
||||
┌───────────────────────────────────────────────────────────────────────────┘
|
||||
└─ Not found → First-Time Setup ⛔ BLOCKING → Save EXTEND.md → Continue
|
||||
↓
|
||||
Analyze + Save Refs → [Output Dir ⚠️] → [Confirm: 6 Dimensions] → Prompt → Generate → Complete
|
||||
↓
|
||||
(skip if --quick or all specified)
|
||||
Analyze + Save Refs → [Output Dir] → [Confirm: 6 Dimensions] → Prompt → Generate → Complete
|
||||
↓
|
||||
(skip if --quick or all specified)
|
||||
```
|
||||
|
||||
### Step 0: Load Preferences (EXTEND.md) ⛔ BLOCKING
|
||||
|
||||
**Purpose**: Load user preferences or run first-time setup.
|
||||
|
||||
**CRITICAL**: If EXTEND.md not found, MUST complete first-time setup before ANY other questions or steps. Do NOT proceed to content analysis, do NOT ask about reference images, do NOT ask about dimensions — ONLY complete the preferences setup first.
|
||||
|
||||
Use Bash to check EXTEND.md existence (priority order):
|
||||
### Step 0: Load Preferences ⛔ BLOCKING
|
||||
|
||||
Check EXTEND.md existence (priority: project → user):
|
||||
```bash
|
||||
# Check project-level first
|
||||
test -f .baoyu-skills/baoyu-cover-image/EXTEND.md && echo "project"
|
||||
|
||||
# Then user-level (cross-platform: $HOME works on macOS/Linux/WSL)
|
||||
test -f "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "user"
|
||||
```
|
||||
|
||||
| Result | Action |
|
||||
|--------|--------|
|
||||
| Found | Read, parse, display preferences summary → Continue to Step 1 |
|
||||
| Not found | ⛔ **BLOCKING**: Run first-time setup ONLY ([references/config/first-time-setup.md](references/config/first-time-setup.md)) → Complete and save EXTEND.md → Then continue to Step 1 |
|
||||
| Found | Load, display summary → Continue |
|
||||
| Not found | ⛔ Run first-time setup ([references/config/first-time-setup.md](references/config/first-time-setup.md)) → Save → Continue |
|
||||
|
||||
**Preferences Summary** (when found):
|
||||
|
||||
```
|
||||
Preferences loaded from [project/user]:
|
||||
• Watermark: [enabled/disabled] [content if enabled]
|
||||
• Type/Palette/Rendering: [value or "auto"]
|
||||
• Text: [value or "title-only"] | Mood: [value or "balanced"]
|
||||
• Aspect: [default_aspect] | Output: [dir or "not set — will ask in Step 1.5"]
|
||||
• Quick mode: [enabled/disabled] | Language: [value or "auto"]
|
||||
```
|
||||
|
||||
**EXTEND.md Supports**: Watermark | Preferred type | Preferred palette | Preferred rendering | Preferred text | Preferred mood | Preferred font | Default aspect ratio | Default output directory | Quick mode | Custom palette definitions | Language preference
|
||||
|
||||
Schema: [references/config/preferences-schema.md](references/config/preferences-schema.md)
|
||||
**CRITICAL**: If not found, complete setup BEFORE any other steps or questions.
|
||||
|
||||
### Step 1: Analyze Content
|
||||
|
||||
**1.0 Detect & Save Reference Images** ⚠️ REQUIRED if images provided
|
||||
|
||||
Check if user provided reference images. Handle based on input type:
|
||||
|
||||
| Input Type | Action |
|
||||
|------------|--------|
|
||||
| Image file path provided | Copy to `refs/` subdirectory → can use `--ref` |
|
||||
| Image in conversation (no path) | **ASK user for file path** with AskUserQuestion |
|
||||
| User can't provide path | Extract style/palette verbally → append to prompt (NO frontmatter references) |
|
||||
|
||||
**CRITICAL**: Only add `references` to prompt frontmatter if files are ACTUALLY SAVED to `refs/` directory.
|
||||
|
||||
**If user provides file path**:
|
||||
1. Copy to `refs/ref-NN-{slug}.{ext}` (NN = 01, 02, ...)
|
||||
2. Create description: `refs/ref-NN-{slug}.md`
|
||||
3. Verify files exist before proceeding
|
||||
|
||||
**If user can't provide path** (extracted verbally):
|
||||
1. Analyze image visually, extract: colors, style, composition
|
||||
2. Create `refs/extracted-style.md` with extracted info
|
||||
3. DO NOT add `references` to prompt frontmatter
|
||||
4. Instead, append extracted style/colors directly to prompt text
|
||||
|
||||
**Description File Format** (only when file saved):
|
||||
```yaml
|
||||
---
|
||||
ref_id: NN
|
||||
filename: ref-NN-{slug}.{ext}
|
||||
usage: direct | style | palette
|
||||
---
|
||||
[User's description or auto-generated description]
|
||||
```
|
||||
|
||||
| Usage | When to Use |
|
||||
|-------|-------------|
|
||||
| `direct` | Reference matches desired output closely |
|
||||
| `style` | Extract visual style characteristics only |
|
||||
| `palette` | Extract color scheme only |
|
||||
|
||||
**Verification** (only for saved files):
|
||||
```
|
||||
Reference Images Saved:
|
||||
- ref-01-{slug}.png ✓ (can use --ref)
|
||||
- ref-02-{slug}.png ✓ (can use --ref)
|
||||
```
|
||||
|
||||
**Or for extracted style**:
|
||||
```
|
||||
Reference Style Extracted (no file):
|
||||
- Colors: #E8756D coral, #7ECFC0 mint...
|
||||
- Style: minimal flat vector, clean lines...
|
||||
→ Will append to prompt text (not --ref)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**1.1 Save Source Content**
|
||||
- If pasted, save to `source.md` in target directory; if file path, use as-is
|
||||
- **Backup rule**: If `source.md` exists, rename to `source-backup-YYYYMMDD-HHMMSS.md`
|
||||
|
||||
**1.2 Content Analysis**
|
||||
- Extract topic, core message, tone, keywords
|
||||
- Identify visual metaphors
|
||||
- Detect content type
|
||||
|
||||
**1.3 Reference Image Analysis** (if provided in Step 1.0)
|
||||
|
||||
For each reference image:
|
||||
|
||||
| Analysis | Description |
|
||||
|----------|-------------|
|
||||
| Visual characteristics | Style, colors, composition |
|
||||
| Content/subject | What the reference depicts |
|
||||
| Style match | Which type/palette/rendering align |
|
||||
| Usage recommendation | `direct` / `style` / `palette` |
|
||||
|
||||
**1.4 Language Detection**
|
||||
- Detect source language
|
||||
- Note user's input language
|
||||
- Compare with EXTEND.md preference
|
||||
|
||||
**1.5 Determine Output Directory**
|
||||
- Per File Structure rules
|
||||
- If no `default_output_dir` preference + file path input, include in Step 2 Q4
|
||||
1. **Save reference images** (if provided) → [references/workflow/reference-images.md](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 (see reference-images.md)
|
||||
5. **Detect language**: Compare source, user input, EXTEND.md preference
|
||||
6. **Determine output directory**: Per File Structure rules
|
||||
|
||||
### Step 2: Confirm Options ⚠️
|
||||
|
||||
Validate all 6 dimensions + aspect ratio. Full confirmation flow: [references/workflow/confirm-options.md](references/workflow/confirm-options.md)
|
||||
|
||||
**Skip Conditions**:
|
||||
Full confirmation flow: [references/workflow/confirm-options.md](references/workflow/confirm-options.md)
|
||||
|
||||
| Condition | Skipped | Still Asked |
|
||||
|-----------|---------|-------------|
|
||||
@@ -350,92 +159,24 @@ Validate all 6 dimensions + aspect ratio. Full confirmation flow: [references/wo
|
||||
|
||||
### Step 3: Create Prompt
|
||||
|
||||
**Backup rule**: If `prompts/cover.md` exists, rename to `prompts/cover-backup-YYYYMMDD-HHMMSS.md`
|
||||
Save to `prompts/cover.md`. Template: [references/workflow/prompt-template.md](references/workflow/prompt-template.md)
|
||||
|
||||
Save to `prompts/cover.md`. Full template: [references/workflow/prompt-template.md](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}`
|
||||
|
||||
**CRITICAL - References in YAML Frontmatter**:
|
||||
|
||||
When reference files are saved to `refs/`, **MUST add `references` field in frontmatter**:
|
||||
|
||||
```yaml
|
||||
---
|
||||
type: cover
|
||||
palette: warm
|
||||
rendering: flat-vector
|
||||
references:
|
||||
- ref_id: 01
|
||||
filename: refs/ref-01-podcast-thumbnail.jpg
|
||||
usage: style
|
||||
---
|
||||
```
|
||||
|
||||
| Rule | Action |
|
||||
|------|--------|
|
||||
| Files saved to `refs/` | Add to frontmatter `references` list |
|
||||
| Style extracted verbally (no file) | Omit `references` field, describe in body |
|
||||
| Before writing | Verify: `test -f refs/ref-NN-{slug}.{ext}` |
|
||||
|
||||
**Reference Embedding**:
|
||||
|
||||
| Situation | Frontmatter | Body |
|
||||
|-----------|-------------|------|
|
||||
| Reference file saved to `refs/` | Add to `references` ✓ | Brief style note |
|
||||
| Style extracted verbally (no file) | Omit `references` | Full style description |
|
||||
| File in frontmatter but doesn't exist | ERROR - fix or remove | — |
|
||||
**Reference elements in body** MUST be detailed, prefixed with "MUST"/"REQUIRED", with integration approach.
|
||||
|
||||
### Step 4: Generate Image
|
||||
|
||||
**4.1 Backup existing** `cover.png` → `cover-backup-YYYYMMDD-HHMMSS.png` (if regenerating)
|
||||
|
||||
**4.2 Check available image generation skills**; if multiple, ask user preference
|
||||
|
||||
**4.3 Process References** ⚠️ REQUIRED if references in frontmatter
|
||||
|
||||
**Read `references` from prompt frontmatter** and process each entry:
|
||||
|
||||
1. **Parse frontmatter** to get references list:
|
||||
```yaml
|
||||
references:
|
||||
- ref_id: 01
|
||||
filename: refs/ref-01-podcast-thumbnail.jpg
|
||||
usage: style
|
||||
```
|
||||
|
||||
2. **VERIFY each file exists**:
|
||||
```bash
|
||||
test -f refs/ref-NN-{slug}.{ext} && echo "exists" || echo "MISSING"
|
||||
```
|
||||
- If file MISSING → ERROR, fix prompt or remove from references
|
||||
- If file exists → proceed with processing
|
||||
|
||||
3. Process based on `usage` type:
|
||||
|
||||
| Usage | Action | Example |
|
||||
|-------|--------|---------|
|
||||
| `direct` | Add reference path to `--ref` parameter | `--ref refs/ref-01-brand.png` |
|
||||
| `style` | Analyze reference, append style traits to prompt | "Style: clean lines, gradient backgrounds..." |
|
||||
| `palette` | Extract colors from reference, append to prompt | "Colors: #E8756D coral, #7ECFC0 mint..." |
|
||||
|
||||
3. Check image generation skill capability:
|
||||
|
||||
| Skill Supports `--ref` | Action |
|
||||
|------------------------|--------|
|
||||
| Yes (e.g., baoyu-image-gen with Google) | Pass reference images via `--ref` |
|
||||
| No | Convert to text description, append to prompt |
|
||||
|
||||
**Verification**: Before generating, confirm reference processing:
|
||||
```
|
||||
Reference Processing:
|
||||
- ref-01-brand.png: using as direct reference ✓
|
||||
- ref-02-style.png: extracted palette ✓
|
||||
```
|
||||
|
||||
**4.4 Generate**
|
||||
|
||||
1. Call selected skill with prompt file path, output path (`cover.png`), aspect ratio
|
||||
2. If references with `direct` usage AND skill supports `--ref`: include `--ref` parameter
|
||||
3. On failure: auto-retry once before reporting error
|
||||
1. **Backup existing** `cover.png` if regenerating
|
||||
2. **Check image generation skills**; if multiple, ask preference
|
||||
3. **Process references** from prompt frontmatter:
|
||||
- `direct` usage → pass via `--ref` (use ref-capable backend)
|
||||
- `style`/`palette` → extract traits, append to prompt
|
||||
4. **Generate**: Call skill with prompt file, output path, aspect ratio
|
||||
5. On failure: auto-retry once
|
||||
|
||||
### Step 5: Completion Report
|
||||
|
||||
@@ -445,66 +186,48 @@ Cover Generated!
|
||||
Topic: [topic]
|
||||
Type: [type] | Palette: [palette] | Rendering: [rendering]
|
||||
Text: [text] | Mood: [mood] | Font: [font] | Aspect: [ratio]
|
||||
Title: [title text or "visual only"]
|
||||
Title: [title or "visual only"]
|
||||
Language: [lang] | Watermark: [enabled/disabled]
|
||||
References: [N images (direct/style/palette) or "extracted style" or "none"]
|
||||
References: [N images or "extracted style" or "none"]
|
||||
Location: [directory path]
|
||||
|
||||
Files:
|
||||
✓ source-{slug}.{ext}
|
||||
[✓ refs/ref-01-{slug}.{ext} ... (if references saved)]
|
||||
[✓ refs/ref-01-{slug}.md ... (description files)]
|
||||
[✓ refs/extracted-style.md (if style extracted verbally)]
|
||||
✓ prompts/cover.md
|
||||
✓ cover.png
|
||||
[✓ cover-backup-{timestamp}.png (if regenerated)]
|
||||
```
|
||||
|
||||
## Image Modification
|
||||
|
||||
| Action | Steps |
|
||||
|--------|-------|
|
||||
| **Regenerate** | Backup existing → **Update prompt file FIRST** → Regenerate with same settings |
|
||||
| **Change dimension** | Backup existing → Confirm new value → **Update prompt file FIRST** → Regenerate |
|
||||
| **Regenerate** | Backup → Update prompt file FIRST → Regenerate |
|
||||
| **Change dimension** | Backup → Confirm new value → Update prompt → Regenerate |
|
||||
|
||||
**IMPORTANT**: When regenerating, ALWAYS update the prompt file (`prompts/cover.md`) FIRST before regenerating. This ensures changes are documented and reproducible.
|
||||
## Composition Principles
|
||||
|
||||
All modifications automatically backup existing `cover.png` before regenerating.
|
||||
- **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
|
||||
|
||||
## Notes
|
||||
## Extension Support
|
||||
|
||||
- Cover must be readable at small preview sizes
|
||||
- Visual metaphors > literal representations
|
||||
- Title: readable, impactful
|
||||
- Two confirmation points: Step 0 (first-time setup) + Step 2 (6 dimensions) - skip Step 2 with `--quick`
|
||||
- Use confirmed language for title text
|
||||
- Maintain watermark consistency if enabled
|
||||
- Check compatibility matrices when selecting combinations
|
||||
- `--no-title` is alias for `--text none`
|
||||
- `--style` presets are backward-compatible; explicit `--palette`/`--rendering` override preset values
|
||||
Custom configurations via EXTEND.md. See **Step 0** for paths.
|
||||
|
||||
### Composition Principles
|
||||
Supports: Watermark | Preferred dimensions | Default aspect/output | Quick mode | Custom palettes | Language
|
||||
|
||||
- **Generous whitespace**: 40-60% breathing room; avoid cluttered layouts
|
||||
- **Visual anchor**: Main element centered or offset left (reserve right for title)
|
||||
- **Character handling**: Simplified silhouettes or icon-style figures; NO realistic humans
|
||||
- **Icon vocabulary**: Use simple, recognizable symbols (see [references/visual-elements.md](references/visual-elements.md))
|
||||
|
||||
### Title Handling
|
||||
|
||||
- **Source**: Use the exact title provided by user, or extract from source content
|
||||
- **Do NOT invent titles**: Stay faithful to the original
|
||||
- If no title in source and user doesn't provide one, ask user to specify
|
||||
Schema: [references/config/preferences-schema.md](references/config/preferences-schema.md)
|
||||
|
||||
## References
|
||||
|
||||
**Dimensions**: [text.md](references/dimensions/text.md) | [mood.md](references/dimensions/mood.md) | [font.md](references/dimensions/font.md)
|
||||
**Palettes**: [references/palettes/](references/palettes/)
|
||||
**Renderings**: [references/renderings/](references/renderings/)
|
||||
**Types**: [references/types.md](references/types.md)
|
||||
**Auto-Selection**: [references/auto-selection.md](references/auto-selection.md)
|
||||
**Style Presets**: [references/style-presets.md](references/style-presets.md)
|
||||
**Compatibility**: [references/compatibility.md](references/compatibility.md)
|
||||
**Types**: [references/types.md](references/types.md)
|
||||
**Visual Elements**: [references/visual-elements.md](references/visual-elements.md)
|
||||
**Workflow**: [confirm-options.md](references/workflow/confirm-options.md) | [prompt-template.md](references/workflow/prompt-template.md)
|
||||
**Workflow**: [confirm-options.md](references/workflow/confirm-options.md) | [prompt-template.md](references/workflow/prompt-template.md) | [reference-images.md](references/workflow/reference-images.md)
|
||||
**Config**: [preferences-schema.md](references/config/preferences-schema.md) | [first-time-setup.md](references/config/first-time-setup.md) | [watermark-guide.md](references/config/watermark-guide.md)
|
||||
|
||||
@@ -68,9 +68,15 @@ Palette notes: [key characteristics from palette definition]
|
||||
|
||||
[Watermark section if enabled]
|
||||
|
||||
[Reference images section if provided — see below]
|
||||
[Reference images section if provided — REQUIRED, see below]
|
||||
```
|
||||
|
||||
## Reference-Driven Design ⚠️ HIGH PRIORITY
|
||||
|
||||
When reference images are provided, they are the **primary visual input** and MUST strongly influence the output. The cover should look like it belongs to the same visual family as the references.
|
||||
|
||||
**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.
|
||||
|
||||
## Content-Driven Design
|
||||
|
||||
- Article title and summary inform the visual metaphor choice
|
||||
@@ -175,63 +181,67 @@ For each reference image, extract:
|
||||
- **Color mood**: Palette characteristics (without specific colors)
|
||||
- **Elements**: Key visual elements and symbols used
|
||||
|
||||
### Step 2: Embed in Prompt
|
||||
### Step 2: Embed in Prompt ⚠️ CRITICAL
|
||||
|
||||
**If file saved AND skill supports `--ref`** (e.g., baoyu-image-gen with Google):
|
||||
- Pass ref images directly via `--ref` parameter
|
||||
- Add brief style note in prompt:
|
||||
**Passing `--ref` alone is NOT enough.** Image generation models frequently ignore reference images unless the prompt text explicitly and forcefully describes what to reproduce. You MUST always write detailed textual instructions regardless of whether `--ref` is used.
|
||||
|
||||
**If file saved (with or without `--ref` support)**:
|
||||
- Pass ref images via `--ref` parameter if skill supports it
|
||||
- **ALWAYS** add a detailed mandatory section in the prompt body:
|
||||
|
||||
```
|
||||
# Reference Style
|
||||
Follow the visual style of the attached reference image(s):
|
||||
- [1-2 sentence style summary from analysis]
|
||||
# Reference Style — MUST INCORPORATE
|
||||
|
||||
CRITICAL: The generated cover MUST visually reference the provided images. The cover must feel like it belongs to the same visual family.
|
||||
|
||||
## From Ref 1 ([filename]) — REQUIRED elements:
|
||||
- [Brand element]: [Specific description of logo/wordmark treatment, e.g., "The logo uses vertical parallel lines (|||) for the letter 'm'. Reproduce this exact treatment."]
|
||||
- [Signature pattern]: [Specific description, e.g., "Woven intersecting curves forming a diamond/lozenge grid pattern. This MUST appear prominently as a banner, border, or background section."]
|
||||
- [Colors]: [Exact hex values, e.g., "Dark teal #2D4A3E background, cream #F5F0E0 text"]
|
||||
- [Typography]: [Specific treatment, e.g., "Uppercase text with wide letter-spacing"]
|
||||
- [Layout element]: [Specific spatial element, e.g., "Bottom banner strip in dark color"]
|
||||
|
||||
## From Ref 2 ([filename]) — REQUIRED elements:
|
||||
[Same detailed breakdown]
|
||||
|
||||
## Integration approach:
|
||||
[Specific layout instruction describing how reference elements combine with the cover content, e.g., "Use a SPLIT LAYOUT: main illustration area (warm cream background) occupies ~65% of the image, while a dark teal BANNER STRIP (with the woven line pattern from Ref 2) runs along the bottom ~35%, containing branding elements from Ref 1."]
|
||||
```
|
||||
|
||||
**If file saved BUT skill does NOT support `--ref`**:
|
||||
- Embed detailed text description in prompt:
|
||||
|
||||
```
|
||||
# Reference Style (Text Description)
|
||||
Emulate the following visual style from reference image(s):
|
||||
|
||||
Reference 1: [filename]
|
||||
- Style: [detailed rendering technique description]
|
||||
- Composition: [layout and hierarchy description]
|
||||
- Elements: [key visual elements used]
|
||||
- Mood: [emotional tone and visual weight]
|
||||
|
||||
[Repeat for additional references]
|
||||
|
||||
Apply these style characteristics to the cover design while maintaining the specified Type, Palette, and Rendering dimensions.
|
||||
```
|
||||
**Key rules**:
|
||||
- Each visual element gets its own bullet with "MUST" or "REQUIRED"
|
||||
- Descriptions must be **specific enough to reproduce** — not vague ("clean style")
|
||||
- The integration approach must describe **exact spatial arrangement**
|
||||
- After generation, verify reference elements are visible; if not, strengthen and regenerate
|
||||
|
||||
**If style/palette extracted verbally (NO file saved)**:
|
||||
- DO NOT add references metadata to prompt
|
||||
- Append extracted info directly to prompt body:
|
||||
- Append extracted info directly to prompt body using the same MUST INCORPORATE format above:
|
||||
|
||||
```
|
||||
# Extracted Style (from reference)
|
||||
# Reference Style — MUST INCORPORATE (extracted from visual analysis)
|
||||
|
||||
COLORS (from reference):
|
||||
- Primary: #E8756D coral
|
||||
- Secondary: #7ECFC0 mint
|
||||
...
|
||||
CRITICAL: Apply these specific visual elements extracted from the reference images.
|
||||
|
||||
STYLE (from reference):
|
||||
- Clean lines, minimal shadows
|
||||
- Gradient backgrounds
|
||||
- Flat vector icons
|
||||
...
|
||||
## REQUIRED elements:
|
||||
- [Same detailed bullet format as above]
|
||||
|
||||
## Integration approach:
|
||||
[Same spatial layout instruction]
|
||||
```
|
||||
|
||||
### Reference Analysis Template
|
||||
|
||||
Use this format when analyzing reference images:
|
||||
Use this format when analyzing reference images. Extract **specific, concrete, reproducible** details — not vague summaries.
|
||||
|
||||
| Aspect | Analysis Points |
|
||||
|--------|-----------------|
|
||||
| **Rendering** | Line quality (clean/sketchy/painted), texture presence, depth treatment |
|
||||
| **Composition** | Element placement, whitespace ratio, visual flow |
|
||||
| **Typography** | Font style, text placement, hierarchy (if present) |
|
||||
| **Elements** | Icon vocabulary, decorative motifs, character style |
|
||||
| **Mood** | Contrast level, saturation, visual weight |
|
||||
| Aspect | Analysis Points | Good Example | Bad Example |
|
||||
|--------|-----------------|--------------|-------------|
|
||||
| **Brand elements** | Logos, wordmarks, distinctive typography | "Logo 'm' formed by 3 vertical lines" | "Has a logo" |
|
||||
| **Signature patterns** | Unique motifs, textures, geometric patterns | "Woven curves forming diamond grid" | "Has patterns" |
|
||||
| **Colors** | Exact hex values or close approximations | "#2D4A3E dark teal, #F5F0E0 cream" | "Dark and light" |
|
||||
| **Layout** | Spatial zones, banner placement, proportions | "Bottom 30% is dark banner with branding" | "Has a banner" |
|
||||
| **Typography** | Font style, weight, case, spacing, position | "Uppercase, wide letter-spacing, right-aligned" | "Has text" |
|
||||
| **Rendering** | Line quality, texture, depth treatment | "Topographic contour lines as background texture" | "Clean style" |
|
||||
| **Elements** | Icon vocabulary, decorative motifs | "Geometric intersecting line ornaments at corners" | "Has decorations" |
|
||||
|
||||
**Output**: Each extracted element should be written as a **copy-pasteable prompt instruction** prefixed with "MUST" or "REQUIRED".
|
||||
|
||||
@@ -0,0 +1,86 @@
|
||||
# Reference Image Handling
|
||||
|
||||
Guide for processing user-provided reference images in cover generation.
|
||||
|
||||
## Input Detection
|
||||
|
||||
| Input Type | Action |
|
||||
|------------|--------|
|
||||
| Image file path provided | Copy to `refs/` → can use `--ref` |
|
||||
| Image in conversation (no path) | **ASK user for file path** with AskUserQuestion |
|
||||
| User can't provide path | Extract style/palette verbally → append to prompt (NO frontmatter references) |
|
||||
|
||||
**CRITICAL**: Only add `references` to prompt frontmatter if files are ACTUALLY SAVED to `refs/` directory.
|
||||
|
||||
## File Saving
|
||||
|
||||
**If user provides file path**:
|
||||
1. Copy to `refs/ref-NN-{slug}.{ext}` (NN = 01, 02, ...)
|
||||
2. Create description: `refs/ref-NN-{slug}.md`
|
||||
3. Verify files exist before proceeding
|
||||
|
||||
**Description File Format**:
|
||||
```yaml
|
||||
---
|
||||
ref_id: NN
|
||||
filename: ref-NN-{slug}.{ext}
|
||||
usage: direct | style | palette
|
||||
---
|
||||
[User's description or auto-generated description]
|
||||
```
|
||||
|
||||
| Usage | When to Use |
|
||||
|-------|-------------|
|
||||
| `direct` | Reference matches desired output closely |
|
||||
| `style` | Extract visual style characteristics only |
|
||||
| `palette` | Extract color scheme only |
|
||||
|
||||
## Verbal Extraction (No File)
|
||||
|
||||
When user can't provide file path:
|
||||
1. Analyze image visually, extract: colors, style, composition
|
||||
2. Create `refs/extracted-style.md` with extracted info
|
||||
3. DO NOT add `references` to prompt frontmatter
|
||||
4. Append extracted style/colors directly to prompt text
|
||||
|
||||
## Deep Analysis ⚠️ CRITICAL
|
||||
|
||||
References are high-priority inputs. Extract **specific, concrete, reproducible** elements:
|
||||
|
||||
| Analysis | Description | Example (good vs bad) |
|
||||
|----------|-------------|----------------------|
|
||||
| **Brand elements** | Logos, wordmarks, specific typography | Good: "Logo uses vertical parallel lines for 'm'" / Bad: "Has a logo" |
|
||||
| **Signature patterns** | Unique decorative motifs, textures | Good: "Woven intersecting curves forming diamond grid" / Bad: "Has patterns" |
|
||||
| **Color palette** | Exact hex values for key colors | Good: "#2D4A3E dark teal, #F5F0E0 cream" / Bad: "Dark and light colors" |
|
||||
| **Layout structure** | Specific spatial arrangement | Good: "Bottom 30% dark banner with branding" / Bad: "Has a banner" |
|
||||
| **Typography** | Font style, weight, spacing, case | Good: "Uppercase, wide letter-spacing" / Bad: "Has text" |
|
||||
| **Content/subject** | What the reference depicts | Factual description |
|
||||
| **Usage recommendation** | `direct` / `style` / `palette` | Based on analysis |
|
||||
|
||||
**Output format**: List each element as bullet that can be copy-pasted into prompt as mandatory instruction.
|
||||
|
||||
## Verification Output
|
||||
|
||||
**For saved files**:
|
||||
```
|
||||
Reference Images Saved:
|
||||
- ref-01-{slug}.png ✓ (can use --ref)
|
||||
- ref-02-{slug}.png ✓ (can use --ref)
|
||||
```
|
||||
|
||||
**For extracted style**:
|
||||
```
|
||||
Reference Style Extracted (no file):
|
||||
- Colors: #E8756D coral, #7ECFC0 mint...
|
||||
- Style: minimal flat vector, clean lines...
|
||||
→ Will append to prompt text (not --ref)
|
||||
```
|
||||
|
||||
## Priority Rules
|
||||
|
||||
When user provides references, they are **HIGH PRIORITY**:
|
||||
|
||||
- **References override defaults**: If reference conflicts with preferred palette/rendering, reference takes precedence
|
||||
- **Concrete > abstract**: Extract specific elements — not vague "clean style"
|
||||
- **Mandatory language**: Use "MUST", "REQUIRED" in prompt for reference elements
|
||||
- **Visible in output**: Verify elements are present after generation; strengthen prompt if not
|
||||
@@ -60,9 +60,12 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --quali
|
||||
# From prompt files
|
||||
npx -y bun ${SKILL_DIR}/scripts/main.ts --promptfiles system.md content.md --image out.png
|
||||
|
||||
# With reference images (Google multimodal only)
|
||||
# With reference images (Google multimodal or OpenAI edits)
|
||||
npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
|
||||
|
||||
# With reference images (explicit provider/model)
|
||||
npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png
|
||||
|
||||
# Specific provider
|
||||
npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provider openai
|
||||
|
||||
@@ -78,12 +81,12 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "一只可爱的猫" --image ou
|
||||
| `--promptfiles <files...>` | Read prompt from files (concatenated) |
|
||||
| `--image <path>` | Output image path (required) |
|
||||
| `--provider google\|openai\|dashscope` | Force provider (default: google) |
|
||||
| `--model <id>`, `-m` | Model ID |
|
||||
| `--model <id>`, `-m` | Model ID (`--ref` with OpenAI requires GPT Image model, e.g. `gpt-image-1.5`) |
|
||||
| `--ar <ratio>` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
|
||||
| `--size <WxH>` | Size (e.g., `1024x1024`) |
|
||||
| `--quality normal\|2k` | Quality preset (default: 2k) |
|
||||
| `--imageSize 1K\|2K\|4K` | Image size for Google (default: from quality) |
|
||||
| `--ref <files...>` | Reference images (Google multimodal only) |
|
||||
| `--ref <files...>` | Reference images. Supported by Google multimodal and OpenAI edits (GPT Image models). If provider omitted: Google first, then OpenAI |
|
||||
| `--n <count>` | Number of images |
|
||||
| `--json` | JSON output |
|
||||
|
||||
@@ -105,9 +108,10 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "一只可爱的猫" --image ou
|
||||
|
||||
## Provider Selection
|
||||
|
||||
1. `--provider` specified → use it
|
||||
2. Only one API key available → use that provider
|
||||
3. Multiple available → default to Google
|
||||
1. `--ref` provided + no `--provider` → auto-select Google first, then OpenAI
|
||||
2. `--provider` specified → use it (if `--ref`, must be `google` or `openai`)
|
||||
3. Only one API key available → use that provider
|
||||
4. Multiple available → default to Google
|
||||
|
||||
## Quality Presets
|
||||
|
||||
@@ -157,7 +161,7 @@ Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
|
||||
- Missing API key → error with setup instructions
|
||||
- Generation failure → auto-retry once
|
||||
- Invalid aspect ratio → warning, proceed with default
|
||||
- Reference images with non-multimodal model → warning, ignore refs
|
||||
- Reference images with unsupported provider/model → error with fix hint (switch to Google multimodal or OpenAI GPT Image edits)
|
||||
|
||||
## Extension Support
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import path from "node:path";
|
||||
import process from "node:process";
|
||||
import { homedir } from "node:os";
|
||||
import { mkdir, readFile, writeFile } from "node:fs/promises";
|
||||
import { access, mkdir, readFile, writeFile } from "node:fs/promises";
|
||||
import type { CliArgs, Provider, ExtendConfig } from "./types";
|
||||
|
||||
function printUsage(): void {
|
||||
@@ -20,7 +20,7 @@ Options:
|
||||
--size <WxH> Size (e.g., 1024x1024)
|
||||
--quality normal|2k Quality preset (default: 2k)
|
||||
--imageSize 1K|2K|4K Image size for Google (default: from quality)
|
||||
--ref <files...> Reference images (Google multimodal only)
|
||||
--ref <files...> Reference images (Google multimodal or OpenAI edits)
|
||||
--n <count> Number of images (default: 1)
|
||||
--json JSON output
|
||||
-h, --help Show help
|
||||
@@ -323,12 +323,26 @@ function normalizeOutputImagePath(p: string): string {
|
||||
}
|
||||
|
||||
function detectProvider(args: CliArgs): Provider {
|
||||
if (args.referenceImages.length > 0 && args.provider && args.provider !== "google" && args.provider !== "openai") {
|
||||
throw new Error(
|
||||
"Reference images require a ref-capable provider. Use --provider google (Gemini multimodal) or --provider openai (GPT Image edits)."
|
||||
);
|
||||
}
|
||||
|
||||
if (args.provider) return args.provider;
|
||||
|
||||
const hasGoogle = !!(process.env.GOOGLE_API_KEY || process.env.GEMINI_API_KEY);
|
||||
const hasOpenai = !!process.env.OPENAI_API_KEY;
|
||||
const hasDashscope = !!process.env.DASHSCOPE_API_KEY;
|
||||
|
||||
if (args.referenceImages.length > 0) {
|
||||
if (hasGoogle) return "google";
|
||||
if (hasOpenai) return "openai";
|
||||
throw new Error(
|
||||
"Reference images require Google or OpenAI. Set GOOGLE_API_KEY/GEMINI_API_KEY or OPENAI_API_KEY, or remove --ref."
|
||||
);
|
||||
}
|
||||
|
||||
const available = [hasGoogle && "google", hasOpenai && "openai", hasDashscope && "dashscope"].filter(Boolean) as Provider[];
|
||||
|
||||
if (available.length === 1) return available[0]!;
|
||||
@@ -340,11 +354,34 @@ function detectProvider(args: CliArgs): Provider {
|
||||
);
|
||||
}
|
||||
|
||||
async function validateReferenceImages(referenceImages: string[]): Promise<void> {
|
||||
for (const refPath of referenceImages) {
|
||||
const fullPath = path.resolve(refPath);
|
||||
try {
|
||||
await access(fullPath);
|
||||
} catch {
|
||||
throw new Error(`Reference image not found: ${fullPath}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
type ProviderModule = {
|
||||
getDefaultModel: () => string;
|
||||
generateImage: (prompt: string, model: string, args: CliArgs) => Promise<Uint8Array>;
|
||||
};
|
||||
|
||||
function isRetryableGenerationError(error: unknown): boolean {
|
||||
const msg = error instanceof Error ? error.message : String(error);
|
||||
const nonRetryableMarkers = [
|
||||
"Reference image",
|
||||
"not supported",
|
||||
"only supported",
|
||||
"No API key found",
|
||||
"is required",
|
||||
];
|
||||
return !nonRetryableMarkers.some((marker) => msg.includes(marker));
|
||||
}
|
||||
|
||||
async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
|
||||
if (provider === "google") {
|
||||
return (await import("./providers/google")) as ProviderModule;
|
||||
@@ -387,6 +424,10 @@ async function main(): Promise<void> {
|
||||
return;
|
||||
}
|
||||
|
||||
if (mergedArgs.referenceImages.length > 0) {
|
||||
await validateReferenceImages(mergedArgs.referenceImages);
|
||||
}
|
||||
|
||||
const provider = detectProvider(mergedArgs);
|
||||
const providerModule = await loadProviderModule(provider);
|
||||
|
||||
@@ -408,7 +449,7 @@ async function main(): Promise<void> {
|
||||
imageData = await providerModule.generateImage(prompt, model, mergedArgs);
|
||||
break;
|
||||
} catch (e) {
|
||||
if (!retried) {
|
||||
if (!retried && isRetryableGenerationError(e)) {
|
||||
retried = true;
|
||||
console.error("Generation failed, retrying...");
|
||||
continue;
|
||||
|
||||
@@ -58,7 +58,9 @@ export async function generateImage(
|
||||
if (!apiKey) throw new Error("DASHSCOPE_API_KEY is required");
|
||||
|
||||
if (args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images not yet supported with DashScope, ignoring.");
|
||||
throw new Error(
|
||||
"Reference images are not supported with DashScope provider in baoyu-image-gen. Use --provider google with a Gemini multimodal model."
|
||||
);
|
||||
}
|
||||
|
||||
const size = args.size ? normalizeSize(args.size) : getSizeFromAspectRatio(args.aspectRatio, args.quality);
|
||||
|
||||
@@ -216,13 +216,17 @@ export async function generateImage(
|
||||
): Promise<Uint8Array> {
|
||||
if (isGoogleImagen(model)) {
|
||||
if (args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images not supported with Imagen models, ignoring.");
|
||||
throw new Error(
|
||||
"Reference images are not supported with Imagen models. Use gemini-3-pro-image-preview or gemini-3-flash-preview."
|
||||
);
|
||||
}
|
||||
return generateWithImagen(prompt, model, args);
|
||||
}
|
||||
|
||||
if (!isGoogleMultimodal(model) && args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images are only supported with Gemini multimodal models.");
|
||||
throw new Error(
|
||||
"Reference images are only supported with Gemini multimodal models. Use gemini-3-pro-image-preview or gemini-3-flash-preview."
|
||||
);
|
||||
}
|
||||
|
||||
return generateWithGemini(prompt, model, args);
|
||||
|
||||
@@ -1,9 +1,13 @@
|
||||
import path from "node:path";
|
||||
import { readFile } from "node:fs/promises";
|
||||
import type { CliArgs } from "../types";
|
||||
|
||||
export function getDefaultModel(): string {
|
||||
return process.env.OPENAI_IMAGE_MODEL || "gpt-image-1.5";
|
||||
}
|
||||
|
||||
type OpenAIImageResponse = { data: Array<{ url?: string; b64_json?: string }> };
|
||||
|
||||
function parseAspectRatio(ar: string): { width: number; height: number } | null {
|
||||
const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
|
||||
if (!match) return null;
|
||||
@@ -66,20 +70,32 @@ export async function generateImage(
|
||||
|
||||
if (!apiKey) throw new Error("OPENAI_API_KEY is required");
|
||||
|
||||
if (args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images not supported with OpenAI, ignoring.");
|
||||
}
|
||||
|
||||
const size = args.size || getOpenAISize(model, args.aspectRatio, args.quality);
|
||||
|
||||
const body: Record<string, any> = {
|
||||
model,
|
||||
prompt,
|
||||
size,
|
||||
};
|
||||
if (args.referenceImages.length > 0) {
|
||||
if (model.includes("dall-e-2") || model.includes("dall-e-3")) {
|
||||
throw new Error(
|
||||
"Reference images with OpenAI in this skill require GPT Image models. Use --model gpt-image-1.5 (or another gpt-image model)."
|
||||
);
|
||||
}
|
||||
return generateWithOpenAIEdits(baseURL, apiKey, prompt, model, size, args.referenceImages, args.quality);
|
||||
}
|
||||
|
||||
return generateWithOpenAIGenerations(baseURL, apiKey, prompt, model, size, args.quality);
|
||||
}
|
||||
|
||||
async function generateWithOpenAIGenerations(
|
||||
baseURL: string,
|
||||
apiKey: string,
|
||||
prompt: string,
|
||||
model: string,
|
||||
size: string,
|
||||
quality: CliArgs["quality"]
|
||||
): Promise<Uint8Array> {
|
||||
const body: Record<string, any> = { model, prompt, size };
|
||||
|
||||
if (model.includes("dall-e-3")) {
|
||||
body.quality = args.quality === "2k" ? "hd" : "standard";
|
||||
body.quality = quality === "2k" ? "hd" : "standard";
|
||||
}
|
||||
|
||||
const res = await fetch(`${baseURL}/images/generations`, {
|
||||
@@ -96,7 +112,62 @@ export async function generateImage(
|
||||
throw new Error(`OpenAI API error: ${err}`);
|
||||
}
|
||||
|
||||
const result = (await res.json()) as { data: Array<{ url?: string; b64_json?: string }> };
|
||||
const result = (await res.json()) as OpenAIImageResponse;
|
||||
return extractImageFromResponse(result);
|
||||
}
|
||||
|
||||
async function generateWithOpenAIEdits(
|
||||
baseURL: string,
|
||||
apiKey: string,
|
||||
prompt: string,
|
||||
model: string,
|
||||
size: string,
|
||||
referenceImages: string[],
|
||||
quality: CliArgs["quality"]
|
||||
): Promise<Uint8Array> {
|
||||
const form = new FormData();
|
||||
form.append("model", model);
|
||||
form.append("prompt", prompt);
|
||||
form.append("size", size);
|
||||
|
||||
if (model.includes("gpt-image")) {
|
||||
form.append("quality", quality === "2k" ? "high" : "medium");
|
||||
}
|
||||
|
||||
for (const refPath of referenceImages) {
|
||||
const bytes = await readFile(refPath);
|
||||
const filename = path.basename(refPath);
|
||||
const mimeType = getMimeType(filename);
|
||||
const blob = new Blob([bytes], { type: mimeType });
|
||||
form.append("image[]", blob, filename);
|
||||
}
|
||||
|
||||
const res = await fetch(`${baseURL}/images/edits`, {
|
||||
method: "POST",
|
||||
headers: {
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
},
|
||||
body: form,
|
||||
});
|
||||
|
||||
if (!res.ok) {
|
||||
const err = await res.text();
|
||||
throw new Error(`OpenAI edits API error: ${err}`);
|
||||
}
|
||||
|
||||
const result = (await res.json()) as OpenAIImageResponse;
|
||||
return extractImageFromResponse(result);
|
||||
}
|
||||
|
||||
function getMimeType(filename: string): string {
|
||||
const ext = path.extname(filename).toLowerCase();
|
||||
if (ext === ".jpg" || ext === ".jpeg") return "image/jpeg";
|
||||
if (ext === ".webp") return "image/webp";
|
||||
if (ext === ".gif") return "image/gif";
|
||||
return "image/png";
|
||||
}
|
||||
|
||||
async function extractImageFromResponse(result: OpenAIImageResponse): Promise<Uint8Array> {
|
||||
const img = result.data[0];
|
||||
|
||||
if (img?.b64_json) {
|
||||
|
||||
Reference in New Issue
Block a user