mirror of
https://github.com/JimLiu/baoyu-skills.git
synced 2026-07-12 22:09:48 +08:00
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Jim Liu 宝玉
|
b15a95e73d |
@@ -6,7 +6,7 @@
|
||||
},
|
||||
"metadata": {
|
||||
"description": "Skills shared by Baoyu for improving daily work efficiency",
|
||||
"version": "1.18.3"
|
||||
"version": "1.19.0"
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
|
||||
@@ -2,6 +2,21 @@
|
||||
|
||||
English | [中文](./CHANGELOG.zh.md)
|
||||
|
||||
## 1.19.0 - 2026-01-24
|
||||
|
||||
### Features
|
||||
- `baoyu-comic`: adds partial workflow options—`--storyboard-only`, `--prompts-only`, `--images-only`, and `--regenerate N` for flexible workflow control.
|
||||
- `baoyu-image-gen`: adds `--imageSize` parameter for Google providers (1K/2K/4K), changes default quality to 2k.
|
||||
- `baoyu-image-gen`: adds `GEMINI_API_KEY` as alias for `GOOGLE_API_KEY`.
|
||||
|
||||
### Refactor
|
||||
- `baoyu-comic`: extracts detailed workflow to `references/workflow.md`, reduces SKILL.md by ~400 lines while preserving functionality.
|
||||
- `baoyu-comic`: extracts content signal analysis to `references/auto-selection.md` and partial workflow docs to `references/partial-workflows.md`.
|
||||
- `baoyu-image-gen`: modularizes code—extracts types to `types.ts`, provider implementations to `providers/google.ts` and `providers/openai.ts`.
|
||||
|
||||
### Documentation
|
||||
- `baoyu-comic`: improves ohmsha preset documentation with explicit default Doraemon character definitions and visual descriptions.
|
||||
|
||||
## 1.18.3 - 2026-01-23
|
||||
|
||||
### Documentation
|
||||
|
||||
@@ -2,6 +2,21 @@
|
||||
|
||||
[English](./CHANGELOG.md) | 中文
|
||||
|
||||
## 1.19.0 - 2026-01-24
|
||||
|
||||
### 新功能
|
||||
- `baoyu-comic`：新增部分工作流选项——`--storyboard-only`、`--prompts-only`、`--images-only` 和 `--regenerate N`，实现灵活的工作流控制。
|
||||
- `baoyu-image-gen`：新增 `--imageSize` 参数用于 Google 提供商（1K/2K/4K），默认质量改为 2k。
|
||||
- `baoyu-image-gen`：新增 `GEMINI_API_KEY` 作为 `GOOGLE_API_KEY` 的别名。
|
||||
|
||||
### 重构
|
||||
- `baoyu-comic`：将详细工作流提取至 `references/workflow.md`，SKILL.md 减少约 400 行，功能完整保留。
|
||||
- `baoyu-comic`：将内容信号分析提取至 `references/auto-selection.md`，部分工作流文档提取至 `references/partial-workflows.md`。
|
||||
- `baoyu-image-gen`：代码模块化——类型定义提取至 `types.ts`，provider 实现提取至 `providers/google.ts` 和 `providers/openai.ts`。
|
||||
|
||||
### 文档
|
||||
- `baoyu-comic`：改进 ohmsha 预设文档，明确默认哆啦A梦角色定义和视觉描述。
|
||||
|
||||
## 1.18.3 - 2026-01-23
|
||||
|
||||
### 文档
|
||||
|
||||
+128
-381
@@ -27,6 +27,17 @@ Create original knowledge comics with flexible art style × tone combinations.
|
||||
| `--aspect` | 3:4 (default, portrait), 4:3 (landscape), 16:9 (widescreen) | Page aspect ratio |
|
||||
| `--lang` | auto (default), zh, en, ja, etc. | Output language |
|
||||
|
||||
### Partial Workflow Options
|
||||
|
||||
| Option | Description |
|
||||
|--------|-------------|
|
||||
| `--storyboard-only` | Generate storyboard only, skip prompts and images |
|
||||
| `--prompts-only` | Generate storyboard + prompts, skip images |
|
||||
| `--images-only` | Generate images from existing prompts directory |
|
||||
| `--regenerate N` | Regenerate specific page(s) only (e.g., `3` or `2,5,8`) |
|
||||
|
||||
Details: [references/partial-workflows.md](references/partial-workflows.md)
|
||||
|
||||
### Art Styles (画风)
|
||||
|
||||
| Style | 中文 | Description |
|
||||
@@ -69,27 +80,25 @@ Presets with special rules beyond art+tone:
|
||||
| ink-brush | neutral, dramatic, action, vintage | warm | romantic, energetic |
|
||||
| chalk | neutral, warm, energetic | vintage | dramatic, action, romantic |
|
||||
|
||||
Art Style × Tone × Layout can be freely combined. Incompatible combinations work but may produce unexpected results.
|
||||
Details: [references/auto-selection.md](references/auto-selection.md)
|
||||
|
||||
## Auto Selection
|
||||
|
||||
Content signals determine default art + tone + layout (or preset):
|
||||
|
||||
| Content Signals | Art Style | Tone | Layout | Preset |
|
||||
|-----------------|-----------|------|--------|--------|
|
||||
| Tutorial, how-to, beginner | manga | neutral | webtoon | **ohmsha** |
|
||||
| Computing, AI, programming | manga | neutral | dense | **ohmsha** |
|
||||
| Technical explanation, educational | manga | neutral | webtoon | **ohmsha** |
|
||||
| Pre-1950, classical, ancient | realistic | vintage | cinematic | - |
|
||||
| Personal story, mentor | ligne-claire | warm | standard | - |
|
||||
| Conflict, breakthrough | (inherit) | dramatic | splash | - |
|
||||
| Wine, food, business, lifestyle | realistic | neutral | cinematic | - |
|
||||
| Martial arts, wuxia, xianxia | ink-brush | action | splash | **wuxia** |
|
||||
| Romance, love, school life | manga | romantic | standard | **shoujo** |
|
||||
| Biography, balanced | ligne-claire | neutral | mixed | - |
|
||||
| Content Signals | Recommended |
|
||||
|-----------------|-------------|
|
||||
| Tutorial, how-to, programming, educational | **ohmsha** preset |
|
||||
| Pre-1950, classical, ancient | realistic + vintage |
|
||||
| Personal story, mentor | ligne-claire + warm |
|
||||
| Martial arts, wuxia | **wuxia** preset |
|
||||
| Romance, school life | **shoujo** preset |
|
||||
| Biography, balanced | ligne-claire + neutral |
|
||||
|
||||
**When preset is recommended**: Load `references/presets/{preset}.md` and apply all special rules.
|
||||
|
||||
Details: [references/auto-selection.md](references/auto-selection.md)
|
||||
|
||||
## Script Directory
|
||||
|
||||
**Important**: All scripts are located in the `scripts/` subdirectory of this skill.
|
||||
@@ -111,409 +120,147 @@ Output directory: `comic/{topic-slug}/`
|
||||
- Conflict: append timestamp (e.g., `turing-story-20260118-143052`)
|
||||
|
||||
**Contents**:
|
||||
- `source-{slug}.{ext}` - Source files
|
||||
- `analysis.md` - Content analysis
|
||||
- `storyboard.md` - Storyboard with panel breakdown
|
||||
- `characters/characters.md` - Character definitions
|
||||
- `characters/characters.png` - Character reference sheet
|
||||
- `prompts/NN-{cover|page}-[slug].md` - Generation prompts
|
||||
- `NN-{cover|page}-[slug].png` - Generated images
|
||||
- `{topic-slug}.pdf` - Final merged PDF
|
||||
| File | Description |
|
||||
|------|-------------|
|
||||
| `source-{slug}.{ext}` | Source files |
|
||||
| `analysis.md` | Content analysis |
|
||||
| `storyboard.md` | Storyboard with panel breakdown |
|
||||
| `characters/characters.md` | Character definitions |
|
||||
| `characters/characters.png` | Character reference sheet |
|
||||
| `prompts/NN-{cover\|page}-[slug].md` | Generation prompts |
|
||||
| `NN-{cover\|page}-[slug].png` | Generated images |
|
||||
| `{topic-slug}.pdf` | Final merged PDF |
|
||||
|
||||
## Language Handling
|
||||
|
||||
**Detection Priority**:
|
||||
1. `--lang` flag (explicit)
|
||||
2. EXTEND.md `language` setting
|
||||
3. User's conversation language
|
||||
4. Source content language
|
||||
|
||||
**Rule**: Use user's input language or saved language preference for ALL interactions:
|
||||
- Storyboard outlines and scene descriptions
|
||||
- Image generation prompts
|
||||
- User selection options and confirmations
|
||||
- Progress updates, questions, errors, summaries
|
||||
|
||||
Technical terms remain in English.
|
||||
|
||||
## Workflow
|
||||
|
||||
### Progress Checklist
|
||||
|
||||
Copy and track progress:
|
||||
|
||||
```
|
||||
Comic Progress:
|
||||
- [ ] Step 1: Load preferences + Analyze content
|
||||
- [ ] Step 2: Confirmation 1 - Style & options ⚠️ REQUIRED
|
||||
- [ ] Step 1: Setup & Analyze (1.1 Preferences, 1.2 Analyze, 1.3 Check existing)
|
||||
- [ ] Step 2: Confirmation - Style & options ⚠️ REQUIRED
|
||||
- [ ] Step 3: Generate storyboard + characters
|
||||
- [ ] Step 4: Confirmation 2 - Review outline (if requested)
|
||||
- [ ] Step 5: Generate images (sequential)
|
||||
- [ ] Step 6: Merge to PDF
|
||||
- [ ] Step 7: Completion report
|
||||
- [ ] Step 4: Review outline (conditional)
|
||||
- [ ] Step 5: Generate prompts
|
||||
- [ ] Step 6: Review prompts (conditional)
|
||||
- [ ] Step 7: Generate images ⚠️ CHARACTER REF REQUIRED
|
||||
- [ ] 7.1 Generate character sheet FIRST → characters/characters.png
|
||||
- [ ] 7.2 Generate pages WITH --ref characters/characters.png
|
||||
- [ ] Step 8: Merge to PDF
|
||||
- [ ] Step 9: Completion report
|
||||
```
|
||||
|
||||
### Flow
|
||||
|
||||
```
|
||||
Input → Preferences → Analyze → [Confirm 1: Style + Skip?] → Storyboard → [Confirm 2: if needed] → Generate → PDF → Complete
|
||||
Input → Preferences → Analyze → [Check Existing?] → [Confirm: Style + Reviews] → Storyboard → [Review?] → Prompts → [Review?] → Images → PDF → Complete
|
||||
```
|
||||
|
||||
### Step 1: Setup & Analyze
|
||||
### Step Summary
|
||||
|
||||
**1.1 Load Preferences (EXTEND.md)**
|
||||
| Step | Action | Key Output |
|
||||
|------|--------|------------|
|
||||
| 1.1 | Load EXTEND.md preferences | Config loaded |
|
||||
| 1.2 | Analyze content | `analysis.md` |
|
||||
| 1.3 | Check existing directory | Handle conflicts |
|
||||
| 2 | Confirm style, focus, audience, reviews | User preferences |
|
||||
| 3 | Generate storyboard + characters | `storyboard.md`, `characters/` |
|
||||
| 4 | Review outline (if requested) | User approval |
|
||||
| 5 | Generate prompts | `prompts/*.md` |
|
||||
| 6 | Review prompts (if requested) | User approval |
|
||||
| **7.1** | **Generate character sheet FIRST** | `characters/characters.png` |
|
||||
| **7.2** | Generate pages **with character ref** | `*.png` files |
|
||||
| 8 | Merge to PDF | `{slug}.pdf` |
|
||||
| 9 | Completion report | Summary |
|
||||
|
||||
Use Bash to check EXTEND.md existence (priority order):
|
||||
### Step 7: Image Generation ⚠️ CRITICAL
|
||||
|
||||
**Character reference is MANDATORY for visual consistency.**
|
||||
|
||||
**7.1 Generate character sheet first**:
|
||||
```bash
|
||||
# Use Reference Sheet Prompt from characters/characters.md
|
||||
npx -y bun ${SKILL_DIR}/../baoyu-image-gen/scripts/main.ts \
|
||||
--promptfiles characters/characters.md \
|
||||
--image characters/characters.png --ar 4:3
|
||||
```
|
||||
|
||||
**7.2 Generate each page WITH character reference**:
|
||||
|
||||
| Skill Capability | Strategy |
|
||||
|------------------|----------|
|
||||
| Supports `--ref` | Pass `characters/characters.png` with EVERY page |
|
||||
| No `--ref` support | Prepend character descriptions to EVERY prompt file |
|
||||
|
||||
```bash
|
||||
# Check project-level first
|
||||
test -f .baoyu-skills/baoyu-comic/EXTEND.md && echo "project"
|
||||
|
||||
# Then user-level (cross-platform: $HOME works on macOS/Linux/WSL)
|
||||
test -f "$HOME/.baoyu-skills/baoyu-comic/EXTEND.md" && echo "user"
|
||||
```
|
||||
|
||||
┌──────────────────────────────────────────────┬───────────────────┐
|
||||
│ Path │ Location │
|
||||
├──────────────────────────────────────────────┼───────────────────┤
|
||||
│ .baoyu-skills/baoyu-comic/EXTEND.md │ Project directory │
|
||||
├──────────────────────────────────────────────┼───────────────────┤
|
||||
│ $HOME/.baoyu-skills/baoyu-comic/EXTEND.md │ User home │
|
||||
└──────────────────────────────────────────────┴───────────────────┘
|
||||
|
||||
**When EXTEND.md Found** → Read, parse, **output summary to user**:
|
||||
|
||||
```
|
||||
📋 Loaded preferences from [full path]
|
||||
├─ Watermark: [enabled/disabled] [content if enabled]
|
||||
├─ Art Style: [style name or "auto-select"]
|
||||
├─ Tone: [tone name or "auto-select"]
|
||||
├─ Layout: [layout or "auto-select"]
|
||||
├─ Language: [language or "auto-detect"]
|
||||
└─ Character presets: [count] defined
|
||||
```
|
||||
|
||||
**MUST output this summary** so user knows their current configuration. Do not skip or silently load.
|
||||
|
||||
**When EXTEND.md Not Found** → First-time setup:
|
||||
|
||||
1. Inform user: "No preferences found. Let's set up your defaults."
|
||||
2. Use AskUserQuestion to collect preferences (see `references/config/first-time-setup.md`)
|
||||
3. Create EXTEND.md at user-chosen location
|
||||
4. Confirm: "✓ Preferences saved to [path]"
|
||||
|
||||
**EXTEND.md Supports**: Watermark | Preferred art/tone/layout | Custom style definitions | Character presets | Language preference
|
||||
|
||||
Schema: `references/config/preferences-schema.md`
|
||||
|
||||
**Important**: Once EXTEND.md exists, watermark, language, and style defaults are NOT asked again in Confirmation 1 or 2. These are session-persistent settings.
|
||||
|
||||
**1.2 Analyze Content → `analysis.md`**
|
||||
|
||||
Read source content, save it if needed, and perform deep analysis.
|
||||
|
||||
**Actions**:
|
||||
1. **Save source content** (if not already a file):
|
||||
- If user provides a file path: use as-is
|
||||
- If user pastes content: save to `source.md` in target directory
|
||||
2. Read source content
|
||||
3. **Deep analysis** following `references/analysis-framework.md`:
|
||||
- Target audience identification
|
||||
- Value proposition for readers
|
||||
- Core themes and narrative potential
|
||||
- Key figures and their story arcs
|
||||
4. Detect source language
|
||||
5. **Determine language**:
|
||||
- If EXTEND.md has `language` → use it
|
||||
- Else if `--lang` option provided → use it
|
||||
- Else → use detected source language
|
||||
6. Determine recommended page count:
|
||||
- Short story: 5-8 pages
|
||||
- Medium complexity: 9-15 pages
|
||||
- Full biography: 16-25 pages
|
||||
7. Analyze content signals for art/tone/layout recommendations
|
||||
8. **Save to `analysis.md`**
|
||||
|
||||
**analysis.md Format**: YAML front matter (title, topic, time_span, source_language, user_language, aspect_ratio, recommended_page_count, recommended_art, recommended_tone) + sections for Target Audience, Value Proposition, Core Themes, Key Figures & Story Arcs, Content Signals, Recommended Approaches. See `references/analysis-framework.md` for full template.
|
||||
|
||||
### Step 2: Confirmation 1 - Style & Options ⚠️
|
||||
|
||||
**Purpose**: Select visual style + decide whether to review outline before generation. **Do NOT skip.**
|
||||
|
||||
**Note**: Watermark and language already configured in EXTEND.md (Step 1).
|
||||
|
||||
**Display summary**:
|
||||
- Content type + topic identified
|
||||
- Key figures extracted
|
||||
- Time span detected
|
||||
- Recommended page count
|
||||
- Language: [from EXTEND.md or detected]
|
||||
- **Recommended style**: [art] + [tone] (based on content signals)
|
||||
|
||||
**Use AskUserQuestion** for:
|
||||
|
||||
**Question 1: Visual Style**
|
||||
|
||||
If a preset is recommended (see Auto Selection), show it first:
|
||||
|
||||
```
|
||||
header: "Style"
|
||||
question: "Which visual style for this comic?"
|
||||
options:
|
||||
- label: "[preset name] preset (Recommended)" # If preset recommended
|
||||
description: "[preset description] - includes special rules"
|
||||
- label: "[recommended art] + [recommended tone] (Recommended)" # If no preset
|
||||
description: "Best match for your content based on analysis"
|
||||
- label: "ligne-claire + neutral"
|
||||
description: "Classic educational, Logicomix style"
|
||||
- label: "ohmsha preset"
|
||||
description: "Educational manga with visual metaphors, gadgets, NO talking heads"
|
||||
- label: "Custom"
|
||||
description: "Specify your own art + tone or preset"
|
||||
```
|
||||
|
||||
**Preset vs Art+Tone**: Presets include special rules beyond art+tone. `ohmsha` = manga + neutral + visual metaphor rules + character roles + NO talking heads. Plain `manga + neutral` does NOT include these rules.
|
||||
|
||||
**Question 2: Narrative Focus** (multiSelect: true)
|
||||
```
|
||||
header: "Focus"
|
||||
question: "What should the comic emphasize? (Select all that apply)"
|
||||
options:
|
||||
- label: "Biography/life story"
|
||||
description: "Follow a person's journey through key life events"
|
||||
- label: "Concept explanation"
|
||||
description: "Break down complex ideas visually"
|
||||
- label: "Historical event"
|
||||
description: "Dramatize important historical moments"
|
||||
- label: "Tutorial/how-to"
|
||||
description: "Step-by-step educational guide"
|
||||
```
|
||||
|
||||
**Question 3: Target Audience**
|
||||
```
|
||||
header: "Audience"
|
||||
question: "Who is the primary reader?"
|
||||
options:
|
||||
- label: "General readers"
|
||||
description: "Broad appeal, accessible content"
|
||||
- label: "Students/learners"
|
||||
description: "Educational focus, clear explanations"
|
||||
- label: "Industry professionals"
|
||||
description: "Technical depth, domain knowledge"
|
||||
- label: "Children/young readers"
|
||||
description: "Simplified language, engaging visuals"
|
||||
```
|
||||
|
||||
**Question 4: Outline Review**
|
||||
```
|
||||
header: "Review"
|
||||
question: "Do you want to review the outline before image generation?"
|
||||
options:
|
||||
- label: "Yes, let me review (Recommended)"
|
||||
description: "Review storyboard and characters before generating images"
|
||||
- label: "No, generate directly"
|
||||
description: "Skip outline review, start generating immediately"
|
||||
```
|
||||
|
||||
**After response**:
|
||||
1. Update `analysis.md` with user preferences
|
||||
2. **Store `skip_outline_review`** flag based on Question 4 response
|
||||
3. → Step 3
|
||||
|
||||
### Step 3: Generate Storyboard + Characters
|
||||
|
||||
Create storyboard and character definitions using the confirmed style from Step 2.
|
||||
|
||||
**Loading Style References**:
|
||||
- Art style: `references/art-styles/{art}.md`
|
||||
- Tone: `references/tones/{tone}.md`
|
||||
- If preset (ohmsha/wuxia/shoujo): also load `references/presets/{preset}.md`
|
||||
|
||||
**Generate**:
|
||||
|
||||
1. **Storyboard** (`storyboard.md`):
|
||||
- YAML front matter with art_style, tone, layout, aspect_ratio
|
||||
- Cover design
|
||||
- Each page: layout, panel breakdown, visual prompts
|
||||
- **Written in user's preferred language** (from Step 1)
|
||||
- Reference: `references/storyboard-template.md`
|
||||
- **If using preset**: Load and apply preset rules from `references/presets/`
|
||||
|
||||
2. **Character definitions** (`characters/characters.md`):
|
||||
- Visual specs matching the art style (in user's preferred language)
|
||||
- Include Reference Sheet Prompt for later image generation
|
||||
- Reference: `references/character-template.md`
|
||||
|
||||
**After generation**:
|
||||
- If `skip_outline_review` is true → Skip Step 4, go directly to Step 5
|
||||
- If `skip_outline_review` is false → Continue to Step 4
|
||||
|
||||
### Step 4: Confirmation 2 - Review Outline (Conditional)
|
||||
|
||||
**Skip this step** if user selected "No, generate directly" in Step 2.
|
||||
|
||||
**Purpose**: User reviews and confirms storyboard + characters before generation.
|
||||
|
||||
**Display**:
|
||||
- Page count and structure
|
||||
- Art style + Tone combination
|
||||
- Page-by-page summary (Cover → P1 → P2...)
|
||||
- Character list with brief descriptions
|
||||
|
||||
**Use AskUserQuestion**:
|
||||
|
||||
```
|
||||
header: "Confirm"
|
||||
question: "Ready to generate images with this outline?"
|
||||
options:
|
||||
- label: "Yes, proceed (Recommended)"
|
||||
description: "Generate character sheet and comic pages"
|
||||
- label: "Edit storyboard first"
|
||||
description: "I'll modify storyboard.md before continuing"
|
||||
- label: "Edit characters first"
|
||||
description: "I'll modify characters/characters.md before continuing"
|
||||
- label: "Edit both"
|
||||
description: "I'll modify both files before continuing"
|
||||
```
|
||||
|
||||
**After response**:
|
||||
1. If user wants to edit → Wait for user to finish editing, then ask again
|
||||
2. If user confirms → Continue to Step 5
|
||||
|
||||
### Step 5: Generate Images
|
||||
|
||||
With confirmed storyboard + art style + tone + aspect ratio:
|
||||
|
||||
**Style Reference Loading**:
|
||||
- Read `references/art-styles/{art}.md` for rendering guidelines
|
||||
- Read `references/tones/{tone}.md` for mood/color adjustments
|
||||
- If preset: Read `references/presets/{preset}.md` for special rules
|
||||
|
||||
**5.1 Generate Character Reference Sheet** (first):
|
||||
1. Use Reference Sheet Prompt from `characters/characters.md`
|
||||
2. Generate → `characters/characters.png`
|
||||
3. This ensures visual consistency for all subsequent pages
|
||||
|
||||
**5.2 Generate Comic Pages**:
|
||||
|
||||
**CRITICAL: Character Reference is MANDATORY** for visual consistency across all pages.
|
||||
|
||||
**Before generating any page**:
|
||||
1. Read the image generation skill's SKILL.md
|
||||
2. Check if it supports reference image input (`--ref`, `--reference`, etc.)
|
||||
3. Choose the appropriate strategy below
|
||||
|
||||
**Character Reference Strategy**:
|
||||
|
||||
| Skill Capability | Strategy | Action |
|
||||
|------------------|----------|--------|
|
||||
| Supports `--ref` | **Strategy A** | Pass `characters/characters.png` with EVERY page |
|
||||
| Does NOT support `--ref` | **Strategy B** | Prepend character descriptions to EVERY prompt |
|
||||
|
||||
**Strategy A: Using `--ref` parameter** (e.g., baoyu-image-gen)
|
||||
|
||||
```bash
|
||||
# Each page generation MUST include --ref
|
||||
# Example: ALWAYS include --ref for consistency
|
||||
npx -y bun ${SKILL_DIR}/../baoyu-image-gen/scripts/main.ts \
|
||||
--promptfiles prompts/01-page-xxx.md \
|
||||
--image 01-page-xxx.png \
|
||||
--ar 3:4 \
|
||||
--image 01-page-xxx.png --ar 3:4 \
|
||||
--ref characters/characters.png
|
||||
```
|
||||
|
||||
**Strategy B: Embedding character descriptions in prompt**
|
||||
**Full workflow details**: [references/workflow.md](references/workflow.md)
|
||||
|
||||
When skill does NOT support reference images, create combined prompt files:
|
||||
### EXTEND.md Paths
|
||||
|
||||
```markdown
|
||||
# prompts/01-page-xxx.md (with embedded character reference)
|
||||
| Path | Location |
|
||||
|------|----------|
|
||||
| `.baoyu-skills/baoyu-comic/EXTEND.md` | Project directory |
|
||||
| `$HOME/.baoyu-skills/baoyu-comic/EXTEND.md` | User home |
|
||||
|
||||
## Character Reference (maintain consistency)
|
||||
[Copy relevant sections from characters/characters.md here]
|
||||
- 大雄: Japanese boy, round glasses, yellow shirt, navy shorts...
|
||||
- 哆啦A梦: Round blue robot cat, white belly, red nose, golden bell...
|
||||
**EXTEND.md Supports**: Watermark | Preferred art/tone/layout | Custom style definitions | Character presets | Language preference
|
||||
|
||||
## Page Content
|
||||
[Original page prompt here]
|
||||
```
|
||||
|
||||
**For each page (cover + pages)**:
|
||||
1. Save prompt to `prompts/NN-{cover|page}-[slug].md`
|
||||
2. Generate image using Strategy A or B (based on skill capability)
|
||||
3. Report progress after each generation
|
||||
|
||||
**Watermark Application** (if enabled in preferences):
|
||||
Add to each image generation prompt:
|
||||
```
|
||||
Include a subtle watermark "[content]" positioned at [position]
|
||||
with approximately [opacity*100]% visibility. The watermark should
|
||||
be legible but not distracting from the comic panels and storytelling.
|
||||
Ensure watermark does not overlap speech bubbles or key action.
|
||||
```
|
||||
Reference: `references/config/watermark-guide.md`
|
||||
|
||||
**Session Management**:
|
||||
If image generation skill supports `--sessionId`:
|
||||
1. Generate unique session ID: `comic-{topic-slug}-{timestamp}`
|
||||
2. Use same session ID for all pages
|
||||
3. Ensures visual consistency across generated images
|
||||
|
||||
### Step 6: Merge to PDF
|
||||
|
||||
After all images generated:
|
||||
|
||||
```bash
|
||||
npx -y bun ${SKILL_DIR}/scripts/merge-to-pdf.ts <comic-dir>
|
||||
```
|
||||
|
||||
Creates `{topic-slug}.pdf` with all pages as full-page images.
|
||||
|
||||
### Step 7: Completion Report
|
||||
|
||||
```
|
||||
Comic Complete!
|
||||
Title: [title] | Art: [art] | Tone: [tone] | Pages: [count] | Aspect: [ratio] | Language: [lang]
|
||||
Watermark: [enabled/disabled]
|
||||
Location: [path]
|
||||
✓ analysis.md
|
||||
✓ characters.png
|
||||
✓ 00-cover-[slug].png ... NN-page-[slug].png
|
||||
✓ {topic-slug}.pdf
|
||||
```
|
||||
|
||||
## Page Modification
|
||||
|
||||
| Action | Steps |
|
||||
|--------|-------|
|
||||
| **Edit** | Update prompt → Regenerate image → Regenerate PDF |
|
||||
| **Add** | Create prompt at position → Generate image → Renumber subsequent (NN+1) → Update storyboard → Regenerate PDF |
|
||||
| **Delete** | Remove files → Renumber subsequent (NN-1) → Update storyboard → Regenerate PDF |
|
||||
|
||||
**File naming**: `NN-{cover|page}-[slug].png` (e.g., `03-page-enigma-machine.png`)
|
||||
- Slugs: kebab-case, unique, derived from content
|
||||
- Renumbering: Update NN prefix only, slugs unchanged
|
||||
|
||||
## Preset: Ohmsha
|
||||
|
||||
Default: Use Doraemon characters (大雄=learner, 哆啦A梦=mentor, 胖虎=challenge, 静香=support). Custom characters via `--characters "Student:小明,Mentor:教授"` or character presets in EXTEND.md.
|
||||
|
||||
Requirements: Visual metaphors, NO talking heads, narrative page titles.
|
||||
|
||||
See `references/presets/ohmsha.md` and `references/ohmsha-guide.md` for details.
|
||||
Schema: [references/config/preferences-schema.md](references/config/preferences-schema.md)
|
||||
|
||||
## References
|
||||
|
||||
Detailed templates and guidelines in `references/` directory:
|
||||
|
||||
**Core Templates**:
|
||||
- `analysis-framework.md` - Deep content analysis for comic adaptation
|
||||
- `character-template.md` - Character definition format and examples
|
||||
- `storyboard-template.md` - Storyboard structure and panel breakdown
|
||||
- `ohmsha-guide.md` - Ohmsha manga style specifics
|
||||
- [analysis-framework.md](references/analysis-framework.md) - Deep content analysis
|
||||
- [character-template.md](references/character-template.md) - Character definition format
|
||||
- [storyboard-template.md](references/storyboard-template.md) - Storyboard structure
|
||||
- [ohmsha-guide.md](references/ohmsha-guide.md) - Ohmsha manga specifics
|
||||
|
||||
**Style Definitions** (new 3-dimension system):
|
||||
- `art-styles/` - Art style definitions (ligne-claire, manga, realistic, ink-brush, chalk)
|
||||
- `tones/` - Tone definitions (neutral, warm, dramatic, romantic, energetic, vintage, action)
|
||||
- `presets/` - Preset shortcuts with special rules (ohmsha, wuxia, shoujo)
|
||||
- `layouts/` - Layout definitions (standard, cinematic, dense, splash, mixed, webtoon)
|
||||
**Style Definitions**:
|
||||
- `references/art-styles/` - Art styles (ligne-claire, manga, realistic, ink-brush, chalk)
|
||||
- `references/tones/` - Tones (neutral, warm, dramatic, romantic, energetic, vintage, action)
|
||||
- `references/presets/` - Presets with special rules (ohmsha, wuxia, shoujo)
|
||||
- `references/layouts/` - Layouts (standard, cinematic, dense, splash, mixed, webtoon)
|
||||
|
||||
**Workflow**:
|
||||
- [workflow.md](references/workflow.md) - Full workflow details
|
||||
- [auto-selection.md](references/auto-selection.md) - Content signal analysis
|
||||
- [partial-workflows.md](references/partial-workflows.md) - Partial workflow options
|
||||
|
||||
**Config**:
|
||||
- `config/preferences-schema.md` - EXTEND.md schema
|
||||
- `config/first-time-setup.md` - First-time setup flow
|
||||
- `config/watermark-guide.md` - Watermark configuration
|
||||
- [config/preferences-schema.md](references/config/preferences-schema.md) - EXTEND.md schema
|
||||
- [config/first-time-setup.md](references/config/first-time-setup.md) - First-time setup
|
||||
- [config/watermark-guide.md](references/config/watermark-guide.md) - Watermark configuration
|
||||
|
||||
## Notes
|
||||
|
||||
- Auto-retry once on failure | Cartoon alternatives for sensitive figures
|
||||
- Use confirmed language preference | Maintain style consistency
|
||||
- **Step 2 confirmation required** - do not skip (style selection + outline review option)
|
||||
- **Step 4 conditional** - only if user requested outline review in Step 2
|
||||
- Watermark/language configured once in EXTEND.md, not asked in confirmations
|
||||
|
||||
## Extension Support
|
||||
|
||||
Custom configurations via EXTEND.md. See **Step 1.1** for paths and supported options.
|
||||
- Image generation: 10-30 seconds per page
|
||||
- Auto-retry once on generation failure
|
||||
- Use stylized alternatives for sensitive public figures
|
||||
- Maintain style consistency via session ID
|
||||
- **Step 2 confirmation required** - do not skip
|
||||
- **Steps 4/6 conditional** - only if user requested in Step 2
|
||||
- **Step 7.1 character sheet MUST be generated before pages** - ensures consistency
|
||||
- **Step 7.2 EVERY page MUST reference characters** - use `--ref` or embed descriptions
|
||||
- Watermark/language configured once in EXTEND.md
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
# Auto Selection
|
||||
|
||||
Content signals determine default art + tone + layout (or preset).
|
||||
|
||||
## Content Signal Matrix
|
||||
|
||||
| Content Signals | Art Style | Tone | Layout | Preset |
|
||||
|-----------------|-----------|------|--------|--------|
|
||||
| Tutorial, how-to, beginner | manga | neutral | webtoon | **ohmsha** |
|
||||
| Computing, AI, programming | manga | neutral | dense | **ohmsha** |
|
||||
| Technical explanation, educational | manga | neutral | webtoon | **ohmsha** |
|
||||
| Pre-1950, classical, ancient | realistic | vintage | cinematic | - |
|
||||
| Personal story, mentor | ligne-claire | warm | standard | - |
|
||||
| Conflict, breakthrough | (inherit) | dramatic | splash | - |
|
||||
| Wine, food, business, lifestyle | realistic | neutral | cinematic | - |
|
||||
| Martial arts, wuxia, xianxia | ink-brush | action | splash | **wuxia** |
|
||||
| Romance, love, school life | manga | romantic | standard | **shoujo** |
|
||||
| Biography, balanced | ligne-claire | neutral | mixed | - |
|
||||
|
||||
## Preset Recommendation Rules
|
||||
|
||||
**When preset is recommended**: Load `presets/{preset}.md` and apply all special rules.
|
||||
|
||||
### ohmsha
|
||||
- **Triggers**: Tutorial, technical, educational, computing, programming, how-to, beginner
|
||||
- **Special rules**: Visual metaphors, NO talking heads, gadget reveals, Doraemon-style characters
|
||||
- **Base**: manga + neutral + webtoon/dense
|
||||
|
||||
### wuxia
|
||||
- **Triggers**: Martial arts, wuxia, xianxia, cultivation, swordplay
|
||||
- **Special rules**: Qi effects, combat visuals, atmospheric elements
|
||||
- **Base**: ink-brush + action + splash
|
||||
|
||||
### shoujo
|
||||
- **Triggers**: Romance, love story, school life, emotional drama
|
||||
- **Special rules**: Decorative elements, eye details, romantic beats
|
||||
- **Base**: manga + romantic + standard
|
||||
|
||||
## Compatibility Matrix
|
||||
|
||||
Art Style × Tone combinations work best when matched appropriately:
|
||||
|
||||
| Art Style | ✓✓ Best | ✓ Works | ✗ Avoid |
|
||||
|-----------|---------|---------|---------|
|
||||
| ligne-claire | neutral, warm | dramatic, vintage, energetic | romantic, action |
|
||||
| manga | neutral, romantic, energetic, action | warm, dramatic | vintage |
|
||||
| realistic | neutral, warm, dramatic, vintage | action | romantic, energetic |
|
||||
| ink-brush | neutral, dramatic, action, vintage | warm | romantic, energetic |
|
||||
| chalk | neutral, warm, energetic | vintage | dramatic, action, romantic |
|
||||
|
||||
**Note**: Art Style × Tone × Layout can be freely combined. Incompatible combinations work but may produce unexpected results.
|
||||
|
||||
## Priority Order
|
||||
|
||||
1. User-specified options (`--art`, `--tone`, `--style`)
|
||||
2. EXTEND.md defaults
|
||||
3. Content signal analysis → auto-selection
|
||||
4. Fallback: ligne-claire + neutral + standard
|
||||
@@ -0,0 +1,123 @@
|
||||
# Partial Workflows
|
||||
|
||||
Options to run specific parts of the workflow.
|
||||
|
||||
## Options Summary
|
||||
|
||||
| Option | Steps Executed | Output |
|
||||
|--------|----------------|--------|
|
||||
| `--storyboard-only` | 1-3 | `storyboard.md` + `characters/` |
|
||||
| `--prompts-only` | 1-5 | + `prompts/*.md` |
|
||||
| `--images-only` | 7-9 | + images + PDF |
|
||||
| `--regenerate N` | 7 (partial) | Specific page(s) + PDF |
|
||||
|
||||
---
|
||||
|
||||
## Using `--storyboard-only`
|
||||
|
||||
Generate storyboard and characters without prompts or images:
|
||||
|
||||
```bash
|
||||
/baoyu-comic content.md --storyboard-only
|
||||
```
|
||||
|
||||
**Workflow**: Steps 1-3 only (stop after storyboard + characters)
|
||||
|
||||
**Output**:
|
||||
- `analysis.md`
|
||||
- `storyboard.md`
|
||||
- `characters/characters.md`
|
||||
|
||||
**Use case**: Review and edit the storyboard before generating images. Useful for:
|
||||
- Getting feedback on the narrative structure
|
||||
- Making manual adjustments to panel layouts
|
||||
- Defining custom characters
|
||||
|
||||
---
|
||||
|
||||
## Using `--prompts-only`
|
||||
|
||||
Generate storyboard, characters, and prompts without images:
|
||||
|
||||
```bash
|
||||
/baoyu-comic content.md --prompts-only
|
||||
```
|
||||
|
||||
**Workflow**: Steps 1-5 (generate prompts, skip images)
|
||||
|
||||
**Output**:
|
||||
- `analysis.md`
|
||||
- `storyboard.md`
|
||||
- `characters/characters.md`
|
||||
- `prompts/*.md`
|
||||
|
||||
**Use case**: Review and edit prompts before image generation. Useful for:
|
||||
- Fine-tuning image generation prompts
|
||||
- Ensuring visual consistency before committing to generation
|
||||
- Making style adjustments at the prompt level
|
||||
|
||||
---
|
||||
|
||||
## Using `--images-only`
|
||||
|
||||
Generate images from existing prompts (starts at Step 7):
|
||||
|
||||
```bash
|
||||
/baoyu-comic comic/topic-slug/ --images-only
|
||||
```
|
||||
|
||||
**Workflow**: Skip to Step 7, then 8-9
|
||||
|
||||
**Prerequisites** (must exist in directory):
|
||||
- `prompts/` directory with page prompt files
|
||||
- `storyboard.md` with style information
|
||||
- `characters/characters.md` with character definitions
|
||||
|
||||
**Output**:
|
||||
- `characters/characters.png` (if not exists)
|
||||
- `NN-{cover|page}-[slug].png` images
|
||||
- `{topic-slug}.pdf`
|
||||
|
||||
**Use case**: Re-generate images after editing prompts. Useful for:
|
||||
- Recovering from failed image generation
|
||||
- Trying different image generation settings
|
||||
- Regenerating after manual prompt edits
|
||||
|
||||
---
|
||||
|
||||
## Using `--regenerate`
|
||||
|
||||
Regenerate specific pages only:
|
||||
|
||||
```bash
|
||||
# Single page
|
||||
/baoyu-comic comic/topic-slug/ --regenerate 3
|
||||
|
||||
# Multiple pages
|
||||
/baoyu-comic comic/topic-slug/ --regenerate 2,5,8
|
||||
|
||||
# Cover page
|
||||
/baoyu-comic comic/topic-slug/ --regenerate 0
|
||||
```
|
||||
|
||||
**Workflow**:
|
||||
1. Read existing prompts for specified pages
|
||||
2. Regenerate images only for those pages
|
||||
3. Regenerate PDF
|
||||
|
||||
**Prerequisites** (must exist):
|
||||
- `prompts/NN-{cover|page}-[slug].md` for specified pages
|
||||
- `characters/characters.png` (for reference)
|
||||
|
||||
**Output**:
|
||||
- Regenerated `NN-{cover|page}-[slug].png` for specified pages
|
||||
- Updated `{topic-slug}.pdf`
|
||||
|
||||
**Use case**: Fix specific pages without regenerating entire comic. Useful for:
|
||||
- Fixing a single problematic page
|
||||
- Iterating on specific visuals
|
||||
- Regenerating pages after prompt edits
|
||||
|
||||
**Page numbering**:
|
||||
- `0` = Cover page
|
||||
- `1-N` = Content pages
|
||||
@@ -41,16 +41,18 @@ Every technical concept MUST be visualized as a metaphor:
|
||||
|
||||
### Character Roles (Required)
|
||||
|
||||
Define characters before generating:
|
||||
**DEFAULT: Use Doraemon characters** unless user explicitly specifies `--characters` or has character presets in EXTEND.md.
|
||||
|
||||
| Role | Default | Traits |
|
||||
|------|---------|--------|
|
||||
| Student (Role A) | 大雄 | Confused, asks basic but crucial questions, represents reader |
|
||||
| Mentor (Role B) | 哆啦A梦 | Knowledgeable, patient, uses gadgets as technical metaphors |
|
||||
| Challenge (Role C, optional) | 胖虎 | Represents misunderstanding, or "noise" in the data |
|
||||
| Support (Role D, optional) | 静香 | Asks clarifying questions, provides alternative perspectives |
|
||||
| Role | Default Character | Visual | Traits |
|
||||
|------|-------------------|--------|--------|
|
||||
| Student (Role A) | 大雄 (Nobita) | Boy, 10yo, round glasses, black hair, yellow shirt, navy shorts | Confused, asks basic but crucial questions, represents reader |
|
||||
| Mentor (Role B) | 哆啦A梦 (Doraemon) | Blue robot cat, white belly, 4D pocket, red nose, golden bell | Knowledgeable, patient, uses gadgets as technical metaphors |
|
||||
| Challenge (Role C) | 胖虎 (Gian) | Stocky boy, small eyes, orange shirt | Represents misunderstanding, or "noise" in the data |
|
||||
| Support (Role D) | 静香 (Shizuka) | Cute girl, black short hair, pink dress | Asks clarifying questions, provides alternative perspectives |
|
||||
|
||||
Custom characters via `--characters "Student:小明,Mentor:教授"` or EXTEND.md presets.
|
||||
**IMPORTANT**: These Doraemon characters ARE the default for ohmsha preset. Generate character definitions using these exact characters unless user requests otherwise.
|
||||
|
||||
To use custom characters: `--characters "Student:小明,Mentor:教授"` or define in EXTEND.md.
|
||||
|
||||
### Page Title Convention
|
||||
|
||||
|
||||
@@ -0,0 +1,505 @@
|
||||
# Complete Workflow
|
||||
|
||||
Full workflow for generating knowledge comics.
|
||||
|
||||
## Progress Checklist
|
||||
|
||||
Copy and track progress:
|
||||
|
||||
```
|
||||
Comic Progress:
|
||||
- [ ] Step 1: Setup & Analyze
|
||||
- [ ] 1.1 Load preferences
|
||||
- [ ] 1.2 Analyze content
|
||||
- [ ] 1.3 Check existing ⚠️ REQUIRED
|
||||
- [ ] Step 2: Confirmation 1 - Style & options ⚠️ REQUIRED
|
||||
- [ ] Step 3: Generate storyboard + characters
|
||||
- [ ] Step 4: Review outline (conditional)
|
||||
- [ ] Step 5: Generate prompts
|
||||
- [ ] Step 6: Review prompts (conditional)
|
||||
- [ ] Step 7: Generate images
|
||||
- [ ] Step 8: Merge to PDF
|
||||
- [ ] Step 9: Completion report
|
||||
```
|
||||
|
||||
## Flow Diagram
|
||||
|
||||
```
|
||||
Input → Preferences → Analyze → [Check Existing?] → [Confirm 1: Style + Reviews] → Storyboard → [Review Outline?] → Prompts → [Review Prompts?] → Images → PDF → Complete
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Step 1: Setup & Analyze
|
||||
|
||||
### 1.1 Load Preferences (EXTEND.md)
|
||||
|
||||
Use Bash to check EXTEND.md existence (priority order):
|
||||
|
||||
```bash
|
||||
# Check project-level first
|
||||
test -f .baoyu-skills/baoyu-comic/EXTEND.md && echo "project"
|
||||
|
||||
# Then user-level (cross-platform: $HOME works on macOS/Linux/WSL)
|
||||
test -f "$HOME/.baoyu-skills/baoyu-comic/EXTEND.md" && echo "user"
|
||||
```
|
||||
|
||||
| Path | Location |
|
||||
|------|----------|
|
||||
| `.baoyu-skills/baoyu-comic/EXTEND.md` | Project directory |
|
||||
| `$HOME/.baoyu-skills/baoyu-comic/EXTEND.md` | User home |
|
||||
|
||||
**When EXTEND.md Found** → Read, parse, **output summary to user**:
|
||||
|
||||
```
|
||||
📋 Loaded preferences from [full path]
|
||||
├─ Watermark: [enabled/disabled] [content if enabled]
|
||||
├─ Art Style: [style name or "auto-select"]
|
||||
├─ Tone: [tone name or "auto-select"]
|
||||
├─ Layout: [layout or "auto-select"]
|
||||
├─ Language: [language or "auto-detect"]
|
||||
└─ Character presets: [count] defined
|
||||
```
|
||||
|
||||
**MUST output this summary** so user knows their current configuration. Do not skip or silently load.
|
||||
|
||||
**When EXTEND.md Not Found** → First-time setup:
|
||||
|
||||
1. Inform user: "No preferences found. Let's set up your defaults."
|
||||
2. Use AskUserQuestion to collect preferences (see `config/first-time-setup.md`)
|
||||
3. Create EXTEND.md at user-chosen location
|
||||
4. Confirm: "✓ Preferences saved to [path]"
|
||||
|
||||
**EXTEND.md Supports**: Watermark | Preferred art/tone/layout | Custom style definitions | Character presets | Language preference
|
||||
|
||||
Schema: `config/preferences-schema.md`
|
||||
|
||||
**Important**: Once EXTEND.md exists, watermark, language, and style defaults are NOT asked again in Confirmation 1 or 2. These are session-persistent settings.
|
||||
|
||||
### 1.2 Analyze Content → `analysis.md`
|
||||
|
||||
Read source content, save it if needed, and perform deep analysis.
|
||||
|
||||
**Actions**:
|
||||
1. **Save source content** (if not already a file):
|
||||
- If user provides a file path: use as-is
|
||||
- If user pastes content: save to `source.md` in target directory
|
||||
2. Read source content
|
||||
3. **Deep analysis** following `analysis-framework.md`:
|
||||
- Target audience identification
|
||||
- Value proposition for readers
|
||||
- Core themes and narrative potential
|
||||
- Key figures and their story arcs
|
||||
4. Detect source language
|
||||
5. **Determine language**:
|
||||
- If EXTEND.md has `language` → use it
|
||||
- Else if `--lang` option provided → use it
|
||||
- Else → use detected source language
|
||||
6. Determine recommended page count:
|
||||
- Short story: 5-8 pages
|
||||
- Medium complexity: 9-15 pages
|
||||
- Full biography: 16-25 pages
|
||||
7. Analyze content signals for art/tone/layout recommendations
|
||||
8. **Save to `analysis.md`**
|
||||
|
||||
**analysis.md Format**: YAML front matter (title, topic, time_span, source_language, user_language, aspect_ratio, recommended_page_count, recommended_art, recommended_tone) + sections for Target Audience, Value Proposition, Core Themes, Key Figures & Story Arcs, Content Signals, Recommended Approaches. See `analysis-framework.md` for full template.
|
||||
|
||||
### 1.3 Check Existing Content ⚠️ REQUIRED
|
||||
|
||||
**MUST execute before proceeding to Step 2.**
|
||||
|
||||
Use Bash to check if output directory exists:
|
||||
|
||||
```bash
|
||||
test -d "comic/{topic-slug}" && echo "exists"
|
||||
```
|
||||
|
||||
**If directory exists**, use AskUserQuestion:
|
||||
|
||||
```
|
||||
header: "Existing"
|
||||
question: "Existing content found. How to proceed?"
|
||||
options:
|
||||
- label: "Regenerate storyboard"
|
||||
description: "Keep images, regenerate storyboard and characters only"
|
||||
- label: "Regenerate images"
|
||||
description: "Keep storyboard, regenerate images only"
|
||||
- label: "Backup and regenerate"
|
||||
description: "Backup to {slug}-backup-{timestamp}, then regenerate all"
|
||||
- label: "Exit"
|
||||
description: "Cancel, keep existing content unchanged"
|
||||
```
|
||||
|
||||
Save result and handle accordingly:
|
||||
- **Regenerate storyboard**: Skip to Step 3, preserve `prompts/` and images
|
||||
- **Regenerate images**: Skip to Step 7, use existing prompts
|
||||
- **Backup and regenerate**: Move directory, start fresh from Step 2
|
||||
- **Exit**: End workflow immediately
|
||||
|
||||
---
|
||||
|
||||
## Step 2: Confirmation 1 - Style & Options ⚠️
|
||||
|
||||
**Purpose**: Select visual style + decide whether to review outline before generation. **Do NOT skip.**
|
||||
|
||||
**Note**: Watermark and language already configured in EXTEND.md (Step 1).
|
||||
|
||||
**Display summary**:
|
||||
- Content type + topic identified
|
||||
- Key figures extracted
|
||||
- Time span detected
|
||||
- Recommended page count
|
||||
- Language: [from EXTEND.md or detected]
|
||||
- **Recommended style**: [art] + [tone] (based on content signals)
|
||||
|
||||
**Use AskUserQuestion** for:
|
||||
|
||||
### Question 1: Visual Style
|
||||
|
||||
If a preset is recommended (see `auto-selection.md`), show it first:
|
||||
|
||||
```
|
||||
header: "Style"
|
||||
question: "Which visual style for this comic?"
|
||||
options:
|
||||
- label: "[preset name] preset (Recommended)" # If preset recommended
|
||||
description: "[preset description] - includes special rules"
|
||||
- label: "[recommended art] + [recommended tone] (Recommended)" # If no preset
|
||||
description: "Best match for your content based on analysis"
|
||||
- label: "ligne-claire + neutral"
|
||||
description: "Classic educational, Logicomix style"
|
||||
- label: "ohmsha preset"
|
||||
description: "Educational manga with visual metaphors, gadgets, NO talking heads"
|
||||
- label: "Custom"
|
||||
description: "Specify your own art + tone or preset"
|
||||
```
|
||||
|
||||
**Preset vs Art+Tone**: Presets include special rules beyond art+tone. `ohmsha` = manga + neutral + visual metaphor rules + character roles + NO talking heads. Plain `manga + neutral` does NOT include these rules.
|
||||
|
||||
### Question 2: Narrative Focus (multiSelect: true)
|
||||
|
||||
```
|
||||
header: "Focus"
|
||||
question: "What should the comic emphasize? (Select all that apply)"
|
||||
options:
|
||||
- label: "Biography/life story"
|
||||
description: "Follow a person's journey through key life events"
|
||||
- label: "Concept explanation"
|
||||
description: "Break down complex ideas visually"
|
||||
- label: "Historical event"
|
||||
description: "Dramatize important historical moments"
|
||||
- label: "Tutorial/how-to"
|
||||
description: "Step-by-step educational guide"
|
||||
```
|
||||
|
||||
### Question 3: Target Audience
|
||||
|
||||
```
|
||||
header: "Audience"
|
||||
question: "Who is the primary reader?"
|
||||
options:
|
||||
- label: "General readers"
|
||||
description: "Broad appeal, accessible content"
|
||||
- label: "Students/learners"
|
||||
description: "Educational focus, clear explanations"
|
||||
- label: "Industry professionals"
|
||||
description: "Technical depth, domain knowledge"
|
||||
- label: "Children/young readers"
|
||||
description: "Simplified language, engaging visuals"
|
||||
```
|
||||
|
||||
### Question 4: Outline Review
|
||||
|
||||
```
|
||||
header: "Review"
|
||||
question: "Do you want to review the outline before image generation?"
|
||||
options:
|
||||
- label: "Yes, let me review (Recommended)"
|
||||
description: "Review storyboard and characters before generating images"
|
||||
- label: "No, generate directly"
|
||||
description: "Skip outline review, start generating immediately"
|
||||
```
|
||||
|
||||
### Question 5: Prompt Review
|
||||
|
||||
```
|
||||
header: "Prompts"
|
||||
question: "Review prompts before generating images?"
|
||||
options:
|
||||
- label: "Yes, review prompts (Recommended)"
|
||||
description: "Review image generation prompts before generating"
|
||||
- label: "No, skip prompt review"
|
||||
description: "Proceed directly to image generation"
|
||||
```
|
||||
|
||||
**After response**:
|
||||
1. Update `analysis.md` with user preferences
|
||||
2. **Store `skip_outline_review`** flag based on Question 4 response
|
||||
3. **Store `skip_prompt_review`** flag based on Question 5 response
|
||||
4. → Step 3
|
||||
|
||||
---
|
||||
|
||||
## Step 3: Generate Storyboard + Characters
|
||||
|
||||
Create storyboard and character definitions using the confirmed style from Step 2.
|
||||
|
||||
**Loading Style References**:
|
||||
- Art style: `art-styles/{art}.md`
|
||||
- Tone: `tones/{tone}.md`
|
||||
- If preset (ohmsha/wuxia/shoujo): also load `presets/{preset}.md`
|
||||
|
||||
**Generate**:
|
||||
|
||||
1. **Storyboard** (`storyboard.md`):
|
||||
- YAML front matter with art_style, tone, layout, aspect_ratio
|
||||
- Cover design
|
||||
- Each page: layout, panel breakdown, visual prompts
|
||||
- **Written in user's preferred language** (from Step 1)
|
||||
- Reference: `storyboard-template.md`
|
||||
- **If using preset**: Load and apply preset rules from `presets/`
|
||||
|
||||
2. **Character definitions** (`characters/characters.md`):
|
||||
- Visual specs matching the art style (in user's preferred language)
|
||||
- Include Reference Sheet Prompt for later image generation
|
||||
- Reference: `character-template.md`
|
||||
- **If using ohmsha preset**: Use default Doraemon characters (see below)
|
||||
|
||||
**Ohmsha Default Characters** (use these unless user specifies `--characters`):
|
||||
|
||||
| Role | Character | Visual Description |
|
||||
|------|-----------|-------------------|
|
||||
| Student | 大雄 (Nobita) | Japanese boy, 10yo, round glasses, black hair parted in middle, yellow shirt, navy shorts |
|
||||
| Mentor | 哆啦A梦 (Doraemon) | Round blue robot cat, big white eyes, red nose, whiskers, white belly with 4D pocket, golden bell, no ears |
|
||||
| Challenge | 胖虎 (Gian) | Stocky boy, rough features, small eyes, orange shirt |
|
||||
| Support | 静香 (Shizuka) | Cute girl, black short hair, pink dress, gentle expression |
|
||||
|
||||
These are the canonical ohmsha-style characters. Do NOT create custom characters for ohmsha unless explicitly requested.
|
||||
|
||||
**After generation**:
|
||||
- If `skip_outline_review` is true → Skip Step 4, go directly to Step 5
|
||||
- If `skip_outline_review` is false → Continue to Step 4
|
||||
|
||||
---
|
||||
|
||||
## Step 4: Review Outline (Conditional)
|
||||
|
||||
**Skip this step** if user selected "No, generate directly" in Step 2.
|
||||
|
||||
**Purpose**: User reviews and confirms storyboard + characters before generation.
|
||||
|
||||
**Display**:
|
||||
- Page count and structure
|
||||
- Art style + Tone combination
|
||||
- Page-by-page summary (Cover → P1 → P2...)
|
||||
- Character list with brief descriptions
|
||||
|
||||
**Use AskUserQuestion**:
|
||||
|
||||
```
|
||||
header: "Confirm"
|
||||
question: "Ready to generate images with this outline?"
|
||||
options:
|
||||
- label: "Yes, proceed (Recommended)"
|
||||
description: "Generate character sheet and comic pages"
|
||||
- label: "Edit storyboard first"
|
||||
description: "I'll modify storyboard.md before continuing"
|
||||
- label: "Edit characters first"
|
||||
description: "I'll modify characters/characters.md before continuing"
|
||||
- label: "Edit both"
|
||||
description: "I'll modify both files before continuing"
|
||||
```
|
||||
|
||||
**After response**:
|
||||
1. If user wants to edit → Wait for user to finish editing, then ask again
|
||||
2. If user confirms → Continue to Step 5
|
||||
|
||||
---
|
||||
|
||||
## Step 5: Generate Prompts
|
||||
|
||||
Create image generation prompts for all pages.
|
||||
|
||||
**Style Reference Loading**:
|
||||
- Read `art-styles/{art}.md` for rendering guidelines
|
||||
- Read `tones/{tone}.md` for mood/color adjustments
|
||||
- If preset: Read `presets/{preset}.md` for special rules
|
||||
|
||||
**For each page (cover + pages)**:
|
||||
1. Create prompt following art style + tone guidelines
|
||||
2. Include character visual descriptions for consistency
|
||||
3. Save to `prompts/NN-{cover|page}-[slug].md`
|
||||
|
||||
**Prompt File Format**:
|
||||
```markdown
|
||||
# Page NN: [Title]
|
||||
|
||||
## Visual Style
|
||||
Art: [art style] | Tone: [tone] | Layout: [layout type]
|
||||
|
||||
## Character Reference
|
||||
[Character descriptions from characters/characters.md]
|
||||
|
||||
## Panel Breakdown
|
||||
[From storyboard.md - panel descriptions, actions, dialogue]
|
||||
|
||||
## Generation Prompt
|
||||
[Combined prompt for image generation skill]
|
||||
```
|
||||
|
||||
**Watermark Application** (if enabled in preferences):
|
||||
Add to each prompt:
|
||||
```
|
||||
Include a subtle watermark "[content]" positioned at [position]
|
||||
with approximately [opacity*100]% visibility. The watermark should
|
||||
be legible but not distracting from the comic panels and storytelling.
|
||||
Ensure watermark does not overlap speech bubbles or key action.
|
||||
```
|
||||
Reference: `config/watermark-guide.md`
|
||||
|
||||
**After generation**:
|
||||
- If `skip_prompt_review` is true → Skip Step 6, go directly to Step 7
|
||||
- If `skip_prompt_review` is false → Continue to Step 6
|
||||
|
||||
---
|
||||
|
||||
## Step 6: Review Prompts (Conditional)
|
||||
|
||||
**Skip this step** if user selected "No, skip prompt review" in Step 2.
|
||||
|
||||
**Purpose**: User reviews and confirms prompts before image generation.
|
||||
|
||||
**Display prompt summary table**:
|
||||
|
||||
| Page | Title | Key Elements |
|
||||
|------|-------|--------------|
|
||||
| Cover | [title] | [main visual] |
|
||||
| P1 | [title] | [key elements] |
|
||||
| ... | ... | ... |
|
||||
|
||||
**Use AskUserQuestion**:
|
||||
|
||||
```
|
||||
header: "Confirm"
|
||||
question: "Ready to generate images with these prompts?"
|
||||
options:
|
||||
- label: "Yes, proceed (Recommended)"
|
||||
description: "Generate all comic page images"
|
||||
- label: "Edit prompts first"
|
||||
description: "I'll modify prompts/*.md before continuing"
|
||||
- label: "Regenerate prompts"
|
||||
description: "Regenerate all prompts with different approach"
|
||||
```
|
||||
|
||||
**After response**:
|
||||
1. If user wants to edit → Wait for user to finish editing, then ask again
|
||||
2. If user wants to regenerate → Go back to Step 5
|
||||
3. If user confirms → Continue to Step 7
|
||||
|
||||
---
|
||||
|
||||
## Step 7: Generate Images
|
||||
|
||||
With confirmed prompts from Step 5/6:
|
||||
|
||||
### 7.1 Generate Character Reference Sheet (first)
|
||||
|
||||
1. Use Reference Sheet Prompt from `characters/characters.md`
|
||||
2. Generate → `characters/characters.png`
|
||||
3. This ensures visual consistency for all subsequent pages
|
||||
|
||||
### 7.2 Generate Comic Pages
|
||||
|
||||
**CRITICAL: Character Reference is MANDATORY** for visual consistency across all pages.
|
||||
|
||||
**Before generating any page**:
|
||||
1. Read the image generation skill's SKILL.md
|
||||
2. Check if it supports reference image input (`--ref`, `--reference`, etc.)
|
||||
3. Choose the appropriate strategy below
|
||||
|
||||
**Character Reference Strategy**:
|
||||
|
||||
| Skill Capability | Strategy | Action |
|
||||
|------------------|----------|--------|
|
||||
| Supports `--ref` | **Strategy A** | Pass `characters/characters.png` with EVERY page |
|
||||
| Does NOT support `--ref` | **Strategy B** | Prepend character descriptions to EVERY prompt |
|
||||
|
||||
**Strategy A: Using `--ref` parameter** (e.g., baoyu-image-gen)
|
||||
|
||||
```bash
|
||||
# Each page generation MUST include --ref
|
||||
npx -y bun ${SKILL_DIR}/../baoyu-image-gen/scripts/main.ts \
|
||||
--promptfiles prompts/01-page-xxx.md \
|
||||
--image 01-page-xxx.png \
|
||||
--ar 3:4 \
|
||||
--ref characters/characters.png
|
||||
```
|
||||
|
||||
**Strategy B: Embedding character descriptions in prompt**
|
||||
|
||||
When skill does NOT support reference images, create combined prompt files:
|
||||
|
||||
```markdown
|
||||
# prompts/01-page-xxx.md (with embedded character reference)
|
||||
|
||||
## Character Reference (maintain consistency)
|
||||
[Copy relevant sections from characters/characters.md here]
|
||||
- 大雄: Japanese boy, round glasses, yellow shirt, navy shorts...
|
||||
- 哆啦A梦: Round blue robot cat, white belly, red nose, golden bell...
|
||||
|
||||
## Page Content
|
||||
[Original page prompt here]
|
||||
```
|
||||
|
||||
**For each page (cover + pages)**:
|
||||
1. Read prompt from `prompts/NN-{cover|page}-[slug].md`
|
||||
2. Generate image using Strategy A or B (based on skill capability)
|
||||
3. Save to `NN-{cover|page}-[slug].png`
|
||||
4. Report progress after each generation: "Generated X/N: [page title]"
|
||||
|
||||
**Session Management**:
|
||||
If image generation skill supports `--sessionId`:
|
||||
1. Generate unique session ID: `comic-{topic-slug}-{timestamp}`
|
||||
2. Use same session ID for all pages
|
||||
3. Ensures visual consistency across generated images
|
||||
|
||||
---
|
||||
|
||||
## Step 8: Merge to PDF
|
||||
|
||||
After all images generated:
|
||||
|
||||
```bash
|
||||
npx -y bun ${SKILL_DIR}/scripts/merge-to-pdf.ts <comic-dir>
|
||||
```
|
||||
|
||||
Creates `{topic-slug}.pdf` with all pages as full-page images.
|
||||
|
||||
---
|
||||
|
||||
## Step 9: Completion Report
|
||||
|
||||
```
|
||||
Comic Complete!
|
||||
Title: [title] | Art: [art] | Tone: [tone] | Pages: [count] | Aspect: [ratio] | Language: [lang]
|
||||
Watermark: [enabled/disabled]
|
||||
Location: [path]
|
||||
✓ analysis.md
|
||||
✓ characters.png
|
||||
✓ 00-cover-[slug].png ... NN-page-[slug].png
|
||||
✓ {topic-slug}.pdf
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Page Modification
|
||||
|
||||
| Action | Steps |
|
||||
|--------|-------|
|
||||
| **Edit** | Update prompt → Regenerate image → Regenerate PDF |
|
||||
| **Add** | Create prompt at position → Generate image → Renumber subsequent (NN+1) → Update storyboard → Regenerate PDF |
|
||||
| **Delete** | Remove files → Renumber subsequent (NN-1) → Update storyboard → Regenerate PDF |
|
||||
|
||||
**File naming**: `NN-{cover|page}-[slug].png` (e.g., `03-page-enigma-machine.png`)
|
||||
- Slugs: kebab-case, unique, derived from content
|
||||
- Renumbering: Update NN prefix only, slugs unchanged
|
||||
@@ -76,7 +76,8 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provi
|
||||
| `--model <id>`, `-m` | Model ID |
|
||||
| `--ar <ratio>` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
|
||||
| `--size <WxH>` | Size (e.g., `1024x1024`) |
|
||||
| `--quality normal\|2k` | Quality preset (default: normal) |
|
||||
| `--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) |
|
||||
| `--n <count>` | Number of images |
|
||||
| `--json` | JSON output |
|
||||
@@ -102,17 +103,20 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provi
|
||||
|
||||
## Quality Presets
|
||||
|
||||
| Preset | Resolution | Use Case |
|
||||
|--------|------------|----------|
|
||||
| `normal` | ~1024px | Covers, illustrations |
|
||||
| `2k` | ~2048px | Infographics, slides |
|
||||
| Preset | Google imageSize | OpenAI Size | Use Case |
|
||||
|--------|------------------|-------------|----------|
|
||||
| `normal` | 1K | 1024px | Quick previews |
|
||||
| `2k` (default) | 2K | 2048px | Covers, illustrations, infographics |
|
||||
|
||||
**Google imageSize**: Can be overridden with `--imageSize 1K|2K|4K`
|
||||
|
||||
## Aspect Ratios
|
||||
|
||||
Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
|
||||
|
||||
- Multimodal models: embedded in prompt
|
||||
- Image-only models: uses `aspectRatio` or `size` parameter
|
||||
- Google multimodal: uses `imageConfig.aspectRatio`
|
||||
- Google Imagen: uses `aspectRatio` parameter
|
||||
- OpenAI: maps to closest supported size
|
||||
|
||||
## Error Handling
|
||||
|
||||
|
||||
@@ -1,34 +1,8 @@
|
||||
import fs from "node:fs";
|
||||
import path from "node:path";
|
||||
import process from "node:process";
|
||||
import { homedir } from "node:os";
|
||||
import { mkdir, readFile, writeFile } from "node:fs/promises";
|
||||
|
||||
type Provider = "google" | "openai";
|
||||
type Quality = "normal" | "2k";
|
||||
|
||||
type CliArgs = {
|
||||
prompt: string | null;
|
||||
promptFiles: string[];
|
||||
imagePath: string | null;
|
||||
provider: Provider | null;
|
||||
model: string | null;
|
||||
aspectRatio: string | null;
|
||||
size: string | null;
|
||||
quality: Quality;
|
||||
referenceImages: string[];
|
||||
n: number;
|
||||
json: boolean;
|
||||
help: boolean;
|
||||
};
|
||||
|
||||
const GOOGLE_MULTIMODAL_MODELS = [
|
||||
"gemini-3-pro-image-preview",
|
||||
];
|
||||
|
||||
const GOOGLE_IMAGEN_MODELS = ["imagen-3.0-generate-002", "imagen-3.0-generate-001"];
|
||||
|
||||
const OPENAI_IMAGE_MODELS = ["gpt-image-1.5", "gpt-image-1", "dall-e-3", "dall-e-2"];
|
||||
import type { CliArgs, Provider } from "./types";
|
||||
|
||||
function printUsage(): void {
|
||||
console.log(`Usage:
|
||||
@@ -44,7 +18,8 @@ Options:
|
||||
-m, --model <id> Model ID
|
||||
--ar <ratio> Aspect ratio (e.g., 16:9, 1:1, 4:3)
|
||||
--size <WxH> Size (e.g., 1024x1024)
|
||||
--quality normal|2k Quality preset (default: normal)
|
||||
--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)
|
||||
--n <count> Number of images (default: 1)
|
||||
--json JSON output
|
||||
@@ -53,6 +28,7 @@ Options:
|
||||
Environment variables:
|
||||
OPENAI_API_KEY OpenAI API key
|
||||
GOOGLE_API_KEY Google API key
|
||||
GEMINI_API_KEY Gemini API key (alias for GOOGLE_API_KEY)
|
||||
OPENAI_IMAGE_MODEL Default OpenAI model (gpt-image-1.5)
|
||||
GOOGLE_IMAGE_MODEL Default Google model (gemini-3-pro-image-preview)
|
||||
OPENAI_BASE_URL Custom OpenAI endpoint
|
||||
@@ -70,7 +46,8 @@ function parseArgs(argv: string[]): CliArgs {
|
||||
model: null,
|
||||
aspectRatio: null,
|
||||
size: null,
|
||||
quality: "normal",
|
||||
quality: "2k",
|
||||
imageSize: null,
|
||||
referenceImages: [],
|
||||
n: 1,
|
||||
json: false,
|
||||
@@ -161,6 +138,13 @@ function parseArgs(argv: string[]): CliArgs {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (a === "--imageSize") {
|
||||
const v = argv[++i]?.toUpperCase();
|
||||
if (v !== "1K" && v !== "2K" && v !== "4K") throw new Error(`Invalid imageSize: ${v}`);
|
||||
out.imageSize = v;
|
||||
continue;
|
||||
}
|
||||
|
||||
if (a === "--ref" || a === "--reference") {
|
||||
const { items, next } = takeMany(i);
|
||||
if (items.length === 0) throw new Error(`Missing files for ${a}`);
|
||||
@@ -257,7 +241,7 @@ function normalizeOutputImagePath(p: string): string {
|
||||
function detectProvider(args: CliArgs): Provider {
|
||||
if (args.provider) return args.provider;
|
||||
|
||||
const hasGoogle = !!process.env.GOOGLE_API_KEY;
|
||||
const hasGoogle = !!(process.env.GOOGLE_API_KEY || process.env.GEMINI_API_KEY);
|
||||
const hasOpenai = !!process.env.OPENAI_API_KEY;
|
||||
|
||||
if (hasGoogle && !hasOpenai) return "google";
|
||||
@@ -265,235 +249,21 @@ function detectProvider(args: CliArgs): Provider {
|
||||
if (hasGoogle && hasOpenai) return "google";
|
||||
|
||||
throw new Error(
|
||||
"No API key found. Set GOOGLE_API_KEY or OPENAI_API_KEY.\n" +
|
||||
"No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, or OPENAI_API_KEY.\n" +
|
||||
"Create ~/.baoyu-skills/.env or <cwd>/.baoyu-skills/.env with your keys."
|
||||
);
|
||||
}
|
||||
|
||||
function getDefaultModel(provider: Provider): string {
|
||||
type ProviderModule = {
|
||||
getDefaultModel: () => string;
|
||||
generateImage: (prompt: string, model: string, args: CliArgs) => Promise<Uint8Array>;
|
||||
};
|
||||
|
||||
async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
|
||||
if (provider === "google") {
|
||||
return process.env.GOOGLE_IMAGE_MODEL || "gemini-3-pro-image-preview";
|
||||
return (await import("./providers/google")) as ProviderModule;
|
||||
}
|
||||
return process.env.OPENAI_IMAGE_MODEL || "gpt-image-1.5";
|
||||
}
|
||||
|
||||
function isGoogleMultimodal(model: string): boolean {
|
||||
return GOOGLE_MULTIMODAL_MODELS.some((m) => model.includes(m));
|
||||
}
|
||||
|
||||
function isGoogleImagen(model: string): boolean {
|
||||
return GOOGLE_IMAGEN_MODELS.some((m) => model.includes(m));
|
||||
}
|
||||
|
||||
function buildPromptWithAspect(prompt: string, ar: string | null, quality: Quality): string {
|
||||
let result = prompt;
|
||||
if (ar) {
|
||||
result += ` Aspect ratio: ${ar}.`;
|
||||
}
|
||||
if (quality === "2k") {
|
||||
result += " High resolution 2048px.";
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
function parseAspectRatio(ar: string): { width: number; height: number } | null {
|
||||
const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
|
||||
if (!match) return null;
|
||||
const w = parseFloat(match[1]!);
|
||||
const h = parseFloat(match[2]!);
|
||||
if (w <= 0 || h <= 0) return null;
|
||||
return { width: w, height: h };
|
||||
}
|
||||
|
||||
function getOpenAISize(ar: string | null, quality: Quality): string {
|
||||
const base = quality === "2k" ? 2048 : 1024;
|
||||
|
||||
if (!ar) return `${base}x${base}`;
|
||||
|
||||
const parsed = parseAspectRatio(ar);
|
||||
if (!parsed) return `${base}x${base}`;
|
||||
|
||||
const ratio = parsed.width / parsed.height;
|
||||
|
||||
if (Math.abs(ratio - 1) < 0.1) return `${base}x${base}`;
|
||||
if (ratio > 1.5) return quality === "2k" ? "2048x1024" : "1792x1024";
|
||||
if (ratio < 0.67) return quality === "2k" ? "1024x2048" : "1024x1792";
|
||||
return `${base}x${base}`;
|
||||
}
|
||||
|
||||
async function readImageAsBase64(p: string): Promise<{ data: string; mimeType: string }> {
|
||||
const buf = await readFile(p);
|
||||
const ext = path.extname(p).toLowerCase();
|
||||
let mimeType = "image/png";
|
||||
if (ext === ".jpg" || ext === ".jpeg") mimeType = "image/jpeg";
|
||||
else if (ext === ".gif") mimeType = "image/gif";
|
||||
else if (ext === ".webp") mimeType = "image/webp";
|
||||
return { data: buf.toString("base64"), mimeType };
|
||||
}
|
||||
|
||||
async function generateWithGoogleMultimodal(
|
||||
prompt: string,
|
||||
model: string,
|
||||
args: CliArgs
|
||||
): Promise<Uint8Array> {
|
||||
const { generateText } = await import("ai");
|
||||
const { createGoogleGenerativeAI } = await import("@ai-sdk/google");
|
||||
|
||||
const google = createGoogleGenerativeAI({
|
||||
apiKey: process.env.GOOGLE_API_KEY,
|
||||
baseURL: process.env.GOOGLE_BASE_URL,
|
||||
});
|
||||
|
||||
const fullPrompt = buildPromptWithAspect(prompt, args.aspectRatio, args.quality);
|
||||
|
||||
const messages: any[] = [];
|
||||
const content: any[] = [];
|
||||
|
||||
for (const refPath of args.referenceImages) {
|
||||
const { data, mimeType } = await readImageAsBase64(refPath);
|
||||
content.push({ type: "image", image: data, mimeType });
|
||||
}
|
||||
content.push({ type: "text", text: fullPrompt });
|
||||
|
||||
messages.push({ role: "user", content });
|
||||
|
||||
const result = await generateText({
|
||||
model: google(model, { useSearchGrounding: false }),
|
||||
messages,
|
||||
providerOptions: {
|
||||
google: {
|
||||
responseModalities: ["TEXT", "IMAGE"],
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const files = (result as any).files;
|
||||
if (!files || files.length === 0) {
|
||||
const expRes = (result as any).response?.body?.candidates?.[0]?.content?.parts;
|
||||
if (expRes) {
|
||||
for (const part of expRes) {
|
||||
if (part.inlineData?.data) {
|
||||
return Uint8Array.from(Buffer.from(part.inlineData.data, "base64"));
|
||||
}
|
||||
}
|
||||
}
|
||||
throw new Error("No image in response");
|
||||
}
|
||||
|
||||
const img = files[0];
|
||||
if (img.uint8Array) return img.uint8Array;
|
||||
if (img.base64) return Uint8Array.from(Buffer.from(img.base64, "base64"));
|
||||
|
||||
throw new Error("Cannot extract image data");
|
||||
}
|
||||
|
||||
async function generateWithGoogleImagen(
|
||||
prompt: string,
|
||||
model: string,
|
||||
args: CliArgs
|
||||
): Promise<Uint8Array> {
|
||||
const { experimental_generateImage: generateImage } = await import("ai");
|
||||
const { createGoogleGenerativeAI } = await import("@ai-sdk/google");
|
||||
|
||||
const google = createGoogleGenerativeAI({
|
||||
apiKey: process.env.GOOGLE_API_KEY,
|
||||
baseURL: process.env.GOOGLE_BASE_URL,
|
||||
});
|
||||
|
||||
const fullPrompt = buildPromptWithAspect(prompt, args.aspectRatio, args.quality);
|
||||
|
||||
const result = await generateImage({
|
||||
model: google.image(model),
|
||||
prompt: fullPrompt,
|
||||
n: args.n,
|
||||
aspectRatio: args.aspectRatio || undefined,
|
||||
});
|
||||
|
||||
const img = result.images[0];
|
||||
if (!img) throw new Error("No image in response");
|
||||
|
||||
if (img.uint8Array) return img.uint8Array;
|
||||
if (img.base64) return Uint8Array.from(Buffer.from(img.base64, "base64"));
|
||||
|
||||
throw new Error("Cannot extract image data");
|
||||
}
|
||||
|
||||
async function generateWithOpenAI(
|
||||
prompt: string,
|
||||
model: string,
|
||||
args: CliArgs
|
||||
): Promise<Uint8Array> {
|
||||
const baseURL = process.env.OPENAI_BASE_URL || "https://api.openai.com/v1";
|
||||
const apiKey = process.env.OPENAI_API_KEY;
|
||||
|
||||
if (!apiKey) throw new Error("OPENAI_API_KEY is required");
|
||||
|
||||
const size = args.size || getOpenAISize(args.aspectRatio, args.quality);
|
||||
|
||||
const body: Record<string, any> = {
|
||||
model,
|
||||
prompt,
|
||||
size,
|
||||
};
|
||||
|
||||
if (model.includes("dall-e-3")) {
|
||||
body.quality = args.quality === "2k" ? "hd" : "standard";
|
||||
}
|
||||
|
||||
const res = await fetch(`${baseURL}/images/generations`, {
|
||||
method: "POST",
|
||||
headers: {
|
||||
"Content-Type": "application/json",
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
});
|
||||
|
||||
if (!res.ok) {
|
||||
const err = await res.text();
|
||||
throw new Error(`OpenAI API error: ${err}`);
|
||||
}
|
||||
|
||||
const result = (await res.json()) as { data: Array<{ url?: string; b64_json?: string }> };
|
||||
const img = result.data[0];
|
||||
|
||||
if (img?.b64_json) {
|
||||
return Uint8Array.from(Buffer.from(img.b64_json, "base64"));
|
||||
}
|
||||
|
||||
if (img?.url) {
|
||||
const imgRes = await fetch(img.url);
|
||||
if (!imgRes.ok) throw new Error("Failed to download image");
|
||||
const buf = await imgRes.arrayBuffer();
|
||||
return new Uint8Array(buf);
|
||||
}
|
||||
|
||||
throw new Error("No image in response");
|
||||
}
|
||||
|
||||
async function generate(
|
||||
provider: Provider,
|
||||
model: string,
|
||||
prompt: string,
|
||||
args: CliArgs
|
||||
): Promise<Uint8Array> {
|
||||
if (provider === "google") {
|
||||
if (isGoogleMultimodal(model)) {
|
||||
return generateWithGoogleMultimodal(prompt, model, args);
|
||||
}
|
||||
if (isGoogleImagen(model)) {
|
||||
if (args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images not supported with Imagen models, ignoring.");
|
||||
}
|
||||
return generateWithGoogleImagen(prompt, model, args);
|
||||
}
|
||||
return generateWithGoogleMultimodal(prompt, model, args);
|
||||
}
|
||||
|
||||
if (args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images not supported with OpenAI, ignoring.");
|
||||
}
|
||||
return generateWithOpenAI(prompt, model, args);
|
||||
return (await import("./providers/openai")) as ProviderModule;
|
||||
}
|
||||
|
||||
async function main(): Promise<void> {
|
||||
@@ -525,7 +295,8 @@ async function main(): Promise<void> {
|
||||
}
|
||||
|
||||
const provider = detectProvider(args);
|
||||
const model = args.model || getDefaultModel(provider);
|
||||
const providerModule = await loadProviderModule(provider);
|
||||
const model = args.model || providerModule.getDefaultModel();
|
||||
const outputPath = normalizeOutputImagePath(args.imagePath);
|
||||
|
||||
let imageData: Uint8Array;
|
||||
@@ -533,7 +304,7 @@ async function main(): Promise<void> {
|
||||
|
||||
while (true) {
|
||||
try {
|
||||
imageData = await generate(provider, model, prompt, args);
|
||||
imageData = await providerModule.generateImage(prompt, model, args);
|
||||
break;
|
||||
} catch (e) {
|
||||
if (!retried) {
|
||||
|
||||
@@ -0,0 +1,149 @@
|
||||
import path from "node:path";
|
||||
import { readFile } from "node:fs/promises";
|
||||
import type { CliArgs } from "../types";
|
||||
|
||||
const GOOGLE_MULTIMODAL_MODELS = ["gemini-3-pro-image-preview"];
|
||||
const GOOGLE_IMAGEN_MODELS = ["imagen-3.0-generate-002", "imagen-3.0-generate-001"];
|
||||
|
||||
export function getDefaultModel(): string {
|
||||
return process.env.GOOGLE_IMAGE_MODEL || "gemini-3-pro-image-preview";
|
||||
}
|
||||
|
||||
function isGoogleMultimodal(model: string): boolean {
|
||||
return GOOGLE_MULTIMODAL_MODELS.some((m) => model.includes(m));
|
||||
}
|
||||
|
||||
function isGoogleImagen(model: string): boolean {
|
||||
return GOOGLE_IMAGEN_MODELS.some((m) => model.includes(m));
|
||||
}
|
||||
|
||||
function getGoogleApiKey(): string | null {
|
||||
return process.env.GOOGLE_API_KEY || process.env.GEMINI_API_KEY || null;
|
||||
}
|
||||
|
||||
function getGoogleImageSize(args: CliArgs): "1K" | "2K" | "4K" {
|
||||
if (args.imageSize) return args.imageSize as "1K" | "2K" | "4K";
|
||||
return args.quality === "2k" ? "2K" : "1K";
|
||||
}
|
||||
|
||||
function buildPromptWithAspect(prompt: string, ar: string | null, quality: CliArgs["quality"]): string {
|
||||
let result = prompt;
|
||||
if (ar) {
|
||||
result += ` Aspect ratio: ${ar}.`;
|
||||
}
|
||||
if (quality === "2k") {
|
||||
result += " High resolution 2048px.";
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
async function readImageAsBase64(p: string): Promise<{ data: string; mimeType: string }> {
|
||||
const buf = await readFile(p);
|
||||
const ext = path.extname(p).toLowerCase();
|
||||
let mimeType = "image/png";
|
||||
if (ext === ".jpg" || ext === ".jpeg") mimeType = "image/jpeg";
|
||||
else if (ext === ".gif") mimeType = "image/gif";
|
||||
else if (ext === ".webp") mimeType = "image/webp";
|
||||
return { data: buf.toString("base64"), mimeType };
|
||||
}
|
||||
|
||||
async function generateWithGemini(
|
||||
prompt: string,
|
||||
model: string,
|
||||
args: CliArgs
|
||||
): Promise<Uint8Array> {
|
||||
const { GoogleGenAI } = await import("@google/genai");
|
||||
|
||||
const apiKey = getGoogleApiKey();
|
||||
if (!apiKey) throw new Error("GOOGLE_API_KEY or GEMINI_API_KEY is required");
|
||||
|
||||
const ai = new GoogleGenAI({
|
||||
apiKey,
|
||||
httpOptions: {
|
||||
baseUrl: process.env.GOOGLE_BASE_URL || undefined,
|
||||
},
|
||||
});
|
||||
|
||||
const input: Array<{ type: "text" | "image"; text?: string; data?: string; mime_type?: string }> = [];
|
||||
for (const refPath of args.referenceImages) {
|
||||
const { data, mimeType } = await readImageAsBase64(refPath);
|
||||
input.push({ type: "image", data, mime_type: mimeType });
|
||||
}
|
||||
input.push({ type: "text", text: prompt });
|
||||
|
||||
const imageConfig: { image_size: "1K" | "2K" | "4K"; aspect_ratio?: string } = {
|
||||
image_size: getGoogleImageSize(args),
|
||||
};
|
||||
if (args.aspectRatio) {
|
||||
imageConfig.aspect_ratio = args.aspectRatio;
|
||||
}
|
||||
|
||||
console.log("Generating image with Gemini...", imageConfig);
|
||||
const interaction = await ai.interactions.create({
|
||||
model,
|
||||
input,
|
||||
response_modalities: ["image"],
|
||||
generation_config: {
|
||||
image_config: imageConfig,
|
||||
},
|
||||
});
|
||||
console.log("Generation completed.");
|
||||
|
||||
for (const output of interaction.outputs || []) {
|
||||
if (output.type === "image" && output.data) {
|
||||
return Uint8Array.from(Buffer.from(output.data, "base64"));
|
||||
}
|
||||
}
|
||||
|
||||
throw new Error("No image in response");
|
||||
}
|
||||
|
||||
async function generateWithImagen(
|
||||
prompt: string,
|
||||
model: string,
|
||||
args: CliArgs
|
||||
): Promise<Uint8Array> {
|
||||
const { experimental_generateImage: generateImage } = await import("ai");
|
||||
const { createGoogleGenerativeAI } = await import("@ai-sdk/google");
|
||||
|
||||
const google = createGoogleGenerativeAI({
|
||||
apiKey: getGoogleApiKey() || undefined,
|
||||
baseURL: process.env.GOOGLE_BASE_URL,
|
||||
});
|
||||
|
||||
const fullPrompt = buildPromptWithAspect(prompt, args.aspectRatio, args.quality);
|
||||
|
||||
const result = await generateImage({
|
||||
model: google.image(model),
|
||||
prompt: fullPrompt,
|
||||
n: args.n,
|
||||
aspectRatio: args.aspectRatio || undefined,
|
||||
});
|
||||
|
||||
const img = result.images[0];
|
||||
if (!img) throw new Error("No image in response");
|
||||
|
||||
if (img.uint8Array) return img.uint8Array;
|
||||
if (img.base64) return Uint8Array.from(Buffer.from(img.base64, "base64"));
|
||||
|
||||
throw new Error("Cannot extract image data");
|
||||
}
|
||||
|
||||
export async function generateImage(
|
||||
prompt: string,
|
||||
model: string,
|
||||
args: CliArgs
|
||||
): Promise<Uint8Array> {
|
||||
if (isGoogleImagen(model)) {
|
||||
if (args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images not supported with Imagen models, ignoring.");
|
||||
}
|
||||
return generateWithImagen(prompt, model, args);
|
||||
}
|
||||
|
||||
if (!isGoogleMultimodal(model) && args.referenceImages.length > 0) {
|
||||
console.error("Warning: Reference images are only supported with Gemini multimodal models.");
|
||||
}
|
||||
|
||||
return generateWithGemini(prompt, model, args);
|
||||
}
|
||||
@@ -0,0 +1,114 @@
|
||||
import type { CliArgs } from "../types";
|
||||
|
||||
export function getDefaultModel(): string {
|
||||
return process.env.OPENAI_IMAGE_MODEL || "gpt-image-1.5";
|
||||
}
|
||||
|
||||
function parseAspectRatio(ar: string): { width: number; height: number } | null {
|
||||
const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
|
||||
if (!match) return null;
|
||||
const w = parseFloat(match[1]!);
|
||||
const h = parseFloat(match[2]!);
|
||||
if (w <= 0 || h <= 0) return null;
|
||||
return { width: w, height: h };
|
||||
}
|
||||
|
||||
type SizeMapping = {
|
||||
square: string;
|
||||
landscape: string;
|
||||
portrait: string;
|
||||
};
|
||||
|
||||
function getOpenAISize(
|
||||
model: string,
|
||||
ar: string | null,
|
||||
quality: CliArgs["quality"]
|
||||
): string {
|
||||
const isDalle3 = model.includes("dall-e-3");
|
||||
const isDalle2 = model.includes("dall-e-2");
|
||||
|
||||
if (isDalle2) {
|
||||
return "1024x1024";
|
||||
}
|
||||
|
||||
const sizes: SizeMapping = isDalle3
|
||||
? {
|
||||
square: "1024x1024",
|
||||
landscape: "1792x1024",
|
||||
portrait: "1024x1792",
|
||||
}
|
||||
: {
|
||||
square: "1024x1024",
|
||||
landscape: "1536x1024",
|
||||
portrait: "1024x1536",
|
||||
};
|
||||
|
||||
if (!ar) return sizes.square;
|
||||
|
||||
const parsed = parseAspectRatio(ar);
|
||||
if (!parsed) return sizes.square;
|
||||
|
||||
const ratio = parsed.width / parsed.height;
|
||||
|
||||
if (Math.abs(ratio - 1) < 0.1) return sizes.square;
|
||||
if (ratio > 1.5) return sizes.landscape;
|
||||
if (ratio < 0.67) return sizes.portrait;
|
||||
return sizes.square;
|
||||
}
|
||||
|
||||
export async function generateImage(
|
||||
prompt: string,
|
||||
model: string,
|
||||
args: CliArgs
|
||||
): Promise<Uint8Array> {
|
||||
const baseURL = process.env.OPENAI_BASE_URL || "https://api.openai.com/v1";
|
||||
const apiKey = process.env.OPENAI_API_KEY;
|
||||
|
||||
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 (model.includes("dall-e-3")) {
|
||||
body.quality = args.quality === "2k" ? "hd" : "standard";
|
||||
}
|
||||
|
||||
const res = await fetch(`${baseURL}/images/generations`, {
|
||||
method: "POST",
|
||||
headers: {
|
||||
"Content-Type": "application/json",
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
});
|
||||
|
||||
if (!res.ok) {
|
||||
const err = await res.text();
|
||||
throw new Error(`OpenAI API error: ${err}`);
|
||||
}
|
||||
|
||||
const result = (await res.json()) as { data: Array<{ url?: string; b64_json?: string }> };
|
||||
const img = result.data[0];
|
||||
|
||||
if (img?.b64_json) {
|
||||
return Uint8Array.from(Buffer.from(img.b64_json, "base64"));
|
||||
}
|
||||
|
||||
if (img?.url) {
|
||||
const imgRes = await fetch(img.url);
|
||||
if (!imgRes.ok) throw new Error("Failed to download image");
|
||||
const buf = await imgRes.arrayBuffer();
|
||||
return new Uint8Array(buf);
|
||||
}
|
||||
|
||||
throw new Error("No image in response");
|
||||
}
|
||||
@@ -0,0 +1,18 @@
|
||||
export type Provider = "google" | "openai";
|
||||
export type Quality = "normal" | "2k";
|
||||
|
||||
export type CliArgs = {
|
||||
prompt: string | null;
|
||||
promptFiles: string[];
|
||||
imagePath: string | null;
|
||||
provider: Provider | null;
|
||||
model: string | null;
|
||||
aspectRatio: string | null;
|
||||
size: string | null;
|
||||
quality: Quality;
|
||||
imageSize: string | null;
|
||||
referenceImages: string[];
|
||||
n: number;
|
||||
json: boolean;
|
||||
help: boolean;
|
||||
};
|
||||
Reference in New Issue
Block a user