baoyu-image-gen（宝玉图像生成器）

Image Generation (AI SDK)

Official API-based image generation. Supports OpenAI, Google, DashScope (阿里通义万象) and Replicate providers.

Script Directory

Agent Execution:

1. SKILL_DIR = this SKILL.md file's directory
2. Script path = ${SKILL_DIR}/scripts/main.ts

Usage

# Basic
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "A cat" --image cat.png

# With aspect ratio
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "A landscape" --image out.png --ar 16:9

# High quality
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "A cat" --image out.png --quality 2k

# From prompt files
bun .agents/skills/baoyu-image-gen/scripts/main.ts --promptfiles system.md content.md --image out.png

# With reference images (Google multimodal or OpenAI edits)
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png

# With reference images (explicit provider/model)
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png

# Specific provider
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "A cat" --image out.png --provider openai

# DashScope (阿里通义万象)
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "一只可爱的猫" --image out.png --provider dashscope

# Replicate (google/nano-banana-pro)
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "A cat" --image out.png --provider replicate

# Replicate with specific model
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana

Options

Environment Variables

Load Priority: CLI args > env vars > .agents/skills/.env

Model Resolution

Model priority (highest → lowest), applies to all providers:

1. CLI flag: --model <id>
2. Env var: <PROVIDER>_IMAGE_MODEL (e.g., GOOGLE_IMAGE_MODEL)
3. Built-in default

Agent MUST display model info before each generation:

• Show: Using [provider] / [model]
• Show switch hint: Switch model: --model <id> | env <PROVIDER>_IMAGE_MODEL

Replicate Models

Supported model formats:

• owner/name (recommended for official models), e.g. google/nano-banana-pro
• owner/name:version (community models by version), e.g. stability-ai/sdxl:<version>

Examples:

# Use Replicate default model
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "A cat" --image out.png --provider replicate

# Override model explicitly
bun .agents/skills/baoyu-image-gen/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana

Provider Selection

1. --ref provided + no --provider → auto-select Google first, then OpenAI, then Replicate
2. --provider specified → use it (if --ref, must be google, openai, or replicate)
3. Only one API key available → use that provider
4. Multiple available → default to Google

Quality Presets

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

• Google multimodal: uses imageConfig.aspectRatio
• Google Imagen: uses aspectRatio parameter
• OpenAI: maps to closest supported size

Generation Mode

Default: Sequential generation (one image at a time). This ensures stable output and easier debugging.

Parallel Generation: Only use when user explicitly requests parallel/concurrent generation.

Parallel Settings (when requested):

Agent Implementation (parallel mode only):

# Launch multiple generations in parallel using Task tool
# Each Task runs as background subagent with run_in_background=true
# Collect results via TaskOutput when all complete

Error Handling

• Missing API key → error with setup instructions
• Generation failure → auto-retry once
• Invalid aspect ratio → warning, proceed with default
• Reference images with unsupported provider/model → error with fix hint (switch to Google multimodal: gemini-3-pro-image-preview, gemini-3.1-flash-image-preview; or OpenAI GPT Image edits)

Configuration

Use .agents/skills/.env for provider keys and defaults.