mirror of
https://github.com/JimLiu/baoyu-skills.git
synced 2026-07-15 06:59:48 +08:00
Compare commits
5 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Jim Liu 宝玉
|
6cd709b9e7 | ||
|
Jim Liu 宝玉
|
aaf0f188dd | ||
|
Jim Liu 宝玉
|
b6bf8ecd06 | ||
|
Jim Liu 宝玉
|
7a0ffd9533 | ||
|
Jim Liu 宝玉
|
69355b4ee1 |
@@ -6,7 +6,7 @@
|
||||
},
|
||||
"metadata": {
|
||||
"description": "Skills shared by Baoyu for improving daily work efficiency",
|
||||
"version": "1.83.0"
|
||||
"version": "1.85.0"
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
@@ -23,6 +23,7 @@
|
||||
"./skills/baoyu-danger-x-to-markdown",
|
||||
"./skills/baoyu-format-markdown",
|
||||
"./skills/baoyu-image-gen",
|
||||
"./skills/baoyu-imagine",
|
||||
"./skills/baoyu-infographic",
|
||||
"./skills/baoyu-markdown-to-html",
|
||||
"./skills/baoyu-post-to-weibo",
|
||||
|
||||
@@ -2,6 +2,17 @@
|
||||
|
||||
English | [中文](./CHANGELOG.zh.md)
|
||||
|
||||
## 1.85.0 - 2026-03-25
|
||||
|
||||
### Features
|
||||
- `baoyu-imagine`: auto-migrate legacy `baoyu-image-gen` EXTEND.md config path at runtime
|
||||
- Add `baoyu-image-gen` deprecation redirect skill to guide users to install `baoyu-imagine` and remove the old skill
|
||||
|
||||
## 1.84.0 - 2026-03-25
|
||||
|
||||
### Features
|
||||
- Rename `baoyu-image-gen` skill to `baoyu-imagine` — shorter command name, all references updated across docs, configs, and dependent skills
|
||||
|
||||
## 1.83.0 - 2026-03-25
|
||||
|
||||
### Features
|
||||
|
||||
@@ -2,6 +2,17 @@
|
||||
|
||||
[English](./CHANGELOG.md) | 中文
|
||||
|
||||
## 1.85.0 - 2026-03-25
|
||||
|
||||
### 新功能
|
||||
- `baoyu-imagine`：运行时自动迁移旧版 `baoyu-image-gen` 的 EXTEND.md 配置路径
|
||||
- 新增 `baoyu-image-gen` 废弃重定向技能，引导用户安装 `baoyu-imagine` 并移除旧技能
|
||||
|
||||
## 1.84.0 - 2026-03-25
|
||||
|
||||
### 新功能
|
||||
- 将 `baoyu-image-gen` 技能重命名为 `baoyu-imagine` — 更简短的命令名，所有文档、配置和依赖技能中的引用已同步更新
|
||||
|
||||
## 1.83.0 - 2026-03-25
|
||||
|
||||
### 新功能
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# CLAUDE.md
|
||||
|
||||
Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.83.0**.
|
||||
Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.84.0**.
|
||||
|
||||
## Architecture
|
||||
|
||||
@@ -31,7 +31,7 @@ Execute: `${BUN_X} skills/<skill>/scripts/main.ts [options]`
|
||||
|
||||
- **Bun**: TypeScript runtime (`bun` preferred, fallback `npx -y bun`)
|
||||
- **Chrome**: Required for CDP-based skills (gemini-web, post-to-x/wechat/weibo, url-to-markdown). All CDP skills share a single profile, override via `BAOYU_CHROME_PROFILE_DIR` env var. Platform paths: [docs/chrome-profile.md](docs/chrome-profile.md)
|
||||
- **Image generation APIs**: `baoyu-image-gen` requires API key (OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, or Replicate) configured in EXTEND.md
|
||||
- **Image generation APIs**: `baoyu-imagine` requires API key (OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, or Replicate) configured in EXTEND.md
|
||||
- **Gemini Web auth**: Browser cookies (first run opens Chrome for login, `--login` to refresh)
|
||||
|
||||
## Security
|
||||
@@ -46,7 +46,7 @@ Execute: `${BUN_X} skills/<skill>/scripts/main.ts [options]`
|
||||
| Rule | Description |
|
||||
|------|-------------|
|
||||
| **Load project skills first** | Project skills override system/user-level skills with same name |
|
||||
| **Default image generation** | Use `skills/baoyu-image-gen/SKILL.md` unless user specifies otherwise |
|
||||
| **Default image generation** | Use `skills/baoyu-imagine/SKILL.md` unless user specifies otherwise |
|
||||
|
||||
Priority: project `skills/` → `$HOME/.baoyu-skills/` → system-level.
|
||||
|
||||
|
||||
@@ -32,7 +32,7 @@ This repository now supports publishing each `skills/baoyu-*` directory as an in
|
||||
ClawHub installs skills individually, not as one marketplace bundle. After publishing, users can install specific skills such as:
|
||||
|
||||
```bash
|
||||
clawhub install baoyu-image-gen
|
||||
clawhub install baoyu-imagine
|
||||
clawhub install baoyu-markdown-to-html
|
||||
```
|
||||
|
||||
@@ -661,58 +661,58 @@ Post content to Weibo (微博). Supports regular posts with text, images, and vi
|
||||
|
||||
AI-powered generation backends.
|
||||
|
||||
#### baoyu-image-gen
|
||||
#### baoyu-imagine
|
||||
|
||||
AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, DashScope (Aliyun Tongyi Wanxiang), MiniMax, Jimeng (即梦), Seedream (豆包), and Replicate APIs. Supports text-to-image, reference images, aspect ratios, custom sizes, batch generation, and quality presets.
|
||||
|
||||
```bash
|
||||
# Basic generation (auto-detect provider)
|
||||
/baoyu-image-gen --prompt "A cute cat" --image cat.png
|
||||
/baoyu-imagine --prompt "A cute cat" --image cat.png
|
||||
|
||||
# With aspect ratio
|
||||
/baoyu-image-gen --prompt "A landscape" --image landscape.png --ar 16:9
|
||||
/baoyu-imagine --prompt "A landscape" --image landscape.png --ar 16:9
|
||||
|
||||
# High quality (2k)
|
||||
/baoyu-image-gen --prompt "A banner" --image banner.png --quality 2k
|
||||
/baoyu-imagine --prompt "A banner" --image banner.png --quality 2k
|
||||
|
||||
# Specific provider
|
||||
/baoyu-image-gen --prompt "A cat" --image cat.png --provider openai
|
||||
/baoyu-imagine --prompt "A cat" --image cat.png --provider openai
|
||||
|
||||
# Azure OpenAI (model = deployment name)
|
||||
/baoyu-image-gen --prompt "A cat" --image cat.png --provider azure --model gpt-image-1.5
|
||||
/baoyu-imagine --prompt "A cat" --image cat.png --provider azure --model gpt-image-1.5
|
||||
|
||||
# OpenRouter
|
||||
/baoyu-image-gen --prompt "A cat" --image cat.png --provider openrouter
|
||||
/baoyu-imagine --prompt "A cat" --image cat.png --provider openrouter
|
||||
|
||||
# OpenRouter with reference images
|
||||
/baoyu-image-gen --prompt "Make it blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
|
||||
/baoyu-imagine --prompt "Make it blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
|
||||
|
||||
# DashScope (Aliyun Tongyi Wanxiang)
|
||||
/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider dashscope
|
||||
/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider dashscope
|
||||
|
||||
# DashScope with custom size
|
||||
/baoyu-image-gen --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image banner.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
|
||||
/baoyu-imagine --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image banner.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
|
||||
|
||||
# MiniMax
|
||||
/baoyu-image-gen --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
|
||||
/baoyu-imagine --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
|
||||
|
||||
# MiniMax with subject reference
|
||||
/baoyu-image-gen --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
|
||||
/baoyu-imagine --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
|
||||
|
||||
# Replicate
|
||||
/baoyu-image-gen --prompt "A cat" --image cat.png --provider replicate
|
||||
/baoyu-imagine --prompt "A cat" --image cat.png --provider replicate
|
||||
|
||||
# Jimeng (即梦)
|
||||
/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider jimeng
|
||||
/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider jimeng
|
||||
|
||||
# Seedream (豆包)
|
||||
/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
|
||||
/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider seedream
|
||||
|
||||
# With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 5.0/4.5/4.0)
|
||||
/baoyu-image-gen --prompt "Make it blue" --image out.png --ref source.png
|
||||
/baoyu-imagine --prompt "Make it blue" --image out.png --ref source.png
|
||||
|
||||
# Batch mode
|
||||
/baoyu-image-gen --batchfile batch.json --jobs 4 --json
|
||||
/baoyu-imagine --batchfile batch.json --jobs 4 --json
|
||||
```
|
||||
|
||||
**Options**:
|
||||
@@ -1045,7 +1045,7 @@ Custom style descriptions are also accepted, e.g., `--style "poetic and lyrical"
|
||||
Some skills require API keys or custom configuration. Environment variables can be set in `.env` files:
|
||||
|
||||
**Load Priority** (higher priority overrides lower):
|
||||
1. CLI environment variables (e.g., `OPENAI_API_KEY=xxx /baoyu-image-gen ...`)
|
||||
1. CLI environment variables (e.g., `OPENAI_API_KEY=xxx /baoyu-imagine ...`)
|
||||
2. `process.env` (system environment)
|
||||
3. `<cwd>/.baoyu-skills/.env` (project-level)
|
||||
4. `~/.baoyu-skills/.env` (user-level)
|
||||
|
||||
+19
-19
@@ -32,7 +32,7 @@ npx skills add jimliu/baoyu-skills
|
||||
ClawHub 按“单个 skill”安装，不是把整个 marketplace 一次性装进去。发布后，用户可以按需安装：
|
||||
|
||||
```bash
|
||||
clawhub install baoyu-image-gen
|
||||
clawhub install baoyu-imagine
|
||||
clawhub install baoyu-markdown-to-html
|
||||
```
|
||||
|
||||
@@ -661,58 +661,58 @@ accounts:
|
||||
|
||||
AI 驱动的生成后端。
|
||||
|
||||
#### baoyu-image-gen
|
||||
#### baoyu-imagine
|
||||
|
||||
基于 AI SDK 的图像生成，支持 OpenAI、Azure OpenAI、Google、OpenRouter、DashScope（阿里通义万相）、MiniMax、即梦（Jimeng）、豆包（Seedream）和 Replicate API。支持文生图、参考图、宽高比、自定义尺寸、批量生成和质量预设。
|
||||
|
||||
```bash
|
||||
# 基础生成（自动检测服务商）
|
||||
/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png
|
||||
/baoyu-imagine --prompt "一只可爱的猫" --image cat.png
|
||||
|
||||
# 指定宽高比
|
||||
/baoyu-image-gen --prompt "风景图" --image landscape.png --ar 16:9
|
||||
/baoyu-imagine --prompt "风景图" --image landscape.png --ar 16:9
|
||||
|
||||
# 高质量（2k 分辨率）
|
||||
/baoyu-image-gen --prompt "横幅图" --image banner.png --quality 2k
|
||||
/baoyu-imagine --prompt "横幅图" --image banner.png --quality 2k
|
||||
|
||||
# 指定服务商
|
||||
/baoyu-image-gen --prompt "一只猫" --image cat.png --provider openai
|
||||
/baoyu-imagine --prompt "一只猫" --image cat.png --provider openai
|
||||
|
||||
# Azure OpenAI（model 为部署名称）
|
||||
/baoyu-image-gen --prompt "一只猫" --image cat.png --provider azure --model gpt-image-1.5
|
||||
/baoyu-imagine --prompt "一只猫" --image cat.png --provider azure --model gpt-image-1.5
|
||||
|
||||
# OpenRouter
|
||||
/baoyu-image-gen --prompt "一只猫" --image cat.png --provider openrouter
|
||||
/baoyu-imagine --prompt "一只猫" --image cat.png --provider openrouter
|
||||
|
||||
# OpenRouter + 参考图
|
||||
/baoyu-image-gen --prompt "把它变成蓝色" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
|
||||
/baoyu-imagine --prompt "把它变成蓝色" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
|
||||
|
||||
# DashScope（阿里通义万相）
|
||||
/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider dashscope
|
||||
/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider dashscope
|
||||
|
||||
# DashScope 自定义尺寸
|
||||
/baoyu-image-gen --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image banner.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
|
||||
/baoyu-imagine --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image banner.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
|
||||
|
||||
# MiniMax
|
||||
/baoyu-image-gen --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
|
||||
/baoyu-imagine --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
|
||||
|
||||
# MiniMax + 角色参考图
|
||||
/baoyu-image-gen --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
|
||||
/baoyu-imagine --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
|
||||
|
||||
# Replicate
|
||||
/baoyu-image-gen --prompt "一只猫" --image cat.png --provider replicate
|
||||
/baoyu-imagine --prompt "一只猫" --image cat.png --provider replicate
|
||||
|
||||
# 即梦（Jimeng）
|
||||
/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider jimeng
|
||||
/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider jimeng
|
||||
|
||||
# 豆包（Seedream）
|
||||
/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
|
||||
/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider seedream
|
||||
|
||||
# 带参考图（Google、OpenAI、Azure OpenAI、OpenRouter、Replicate、MiniMax 或 Seedream 5.0/4.5/4.0）
|
||||
/baoyu-image-gen --prompt "把它变成蓝色" --image out.png --ref source.png
|
||||
/baoyu-imagine --prompt "把它变成蓝色" --image out.png --ref source.png
|
||||
|
||||
# 批量模式
|
||||
/baoyu-image-gen --batchfile batch.json --jobs 4 --json
|
||||
/baoyu-imagine --batchfile batch.json --jobs 4 --json
|
||||
```
|
||||
|
||||
**选项**：
|
||||
@@ -1045,7 +1045,7 @@ AI 驱动的生成后端。
|
||||
部分技能需要 API 密钥或自定义配置。环境变量可以在 `.env` 文件中设置：
|
||||
|
||||
**加载优先级**（高优先级覆盖低优先级）：
|
||||
1. 命令行环境变量（如 `OPENAI_API_KEY=xxx /baoyu-image-gen ...`）
|
||||
1. 命令行环境变量（如 `OPENAI_API_KEY=xxx /baoyu-imagine ...`）
|
||||
2. `process.env`（系统环境变量）
|
||||
3. `<cwd>/.baoyu-skills/.env`（项目级）
|
||||
4. `~/.baoyu-skills/.env`（用户级）
|
||||
|
||||
@@ -4,7 +4,7 @@ Skills that require image generation MUST delegate to available image generation
|
||||
|
||||
## Skill Selection
|
||||
|
||||
**Default**: `skills/baoyu-image-gen/SKILL.md` (unless user specifies otherwise).
|
||||
**Default**: `skills/baoyu-imagine/SKILL.md` (unless user specifies otherwise).
|
||||
|
||||
1. Read skill's SKILL.md for parameters and capabilities
|
||||
2. If user requests different skill, check `skills/` for alternatives
|
||||
@@ -16,7 +16,7 @@ Skills that require image generation MUST delegate to available image generation
|
||||
### Step N: Generate Images
|
||||
|
||||
**Skill Selection**:
|
||||
1. Check available skills (`baoyu-image-gen` default, or `baoyu-danger-gemini-web`)
|
||||
1. Check available skills (`baoyu-imagine` default, or `baoyu-danger-gemini-web`)
|
||||
2. Read selected skill's SKILL.md for parameters
|
||||
3. If multiple skills available, ask user to choose
|
||||
|
||||
@@ -27,7 +27,7 @@ Skills that require image generation MUST delegate to available image generation
|
||||
4. On failure, auto-retry once before reporting error
|
||||
```
|
||||
|
||||
**Batch Parallel** (`baoyu-image-gen` only): concurrent workers with per-provider throttling via `batch.max_workers` in EXTEND.md.
|
||||
**Batch Parallel** (`baoyu-imagine` only): concurrent workers with per-provider throttling via `batch.max_workers` in EXTEND.md.
|
||||
|
||||
## Output Path Convention
|
||||
|
||||
|
||||
@@ -118,7 +118,7 @@ Full template: [references/workflow.md](references/workflow.md#step-4-generate-o
|
||||
|
||||
⛔ **BLOCKING: Prompt files MUST be saved before ANY image generation.**
|
||||
|
||||
**Execution strategy**: When multiple illustrations have saved prompt files and the task is now plain generation, prefer `baoyu-image-gen` batch mode (`build-batch.ts` → `--batchfile`) over spawning subagents. Use subagents only when each image still needs separate prompt iteration or creative exploration.
|
||||
**Execution strategy**: When multiple illustrations have saved prompt files and the task is now plain generation, prefer `baoyu-imagine` batch mode (`build-batch.ts` → `--batchfile`) over spawning subagents. Use subagents only when each image still needs separate prompt iteration or creative exploration.
|
||||
|
||||
1. For each illustration, create a prompt file per [references/prompt-construction.md](references/prompt-construction.md)
|
||||
2. Save to `prompts/NN-{type}-{slug}.md` with YAML frontmatter
|
||||
|
||||
@@ -316,7 +316,7 @@ Prompt Files:
|
||||
**DO NOT** pass ad-hoc inline text to `--prompt` without first saving prompt files. The generation command should either use `--promptfiles prompts/NN-{type}-{slug}.md` or read the saved file content for `--prompt`.
|
||||
|
||||
**Execution choice**:
|
||||
- If multiple illustrations already have saved prompt files and the task is now plain generation, prefer `baoyu-image-gen` batch mode (`build-batch.ts` -> `main.ts --batchfile`)
|
||||
- If multiple illustrations already have saved prompt files and the task is now plain generation, prefer `baoyu-imagine` batch mode (`build-batch.ts` -> `main.ts --batchfile`)
|
||||
- Use subagents only when each illustration still needs separate prompt rewriting, style exploration, or other per-image reasoning before generation
|
||||
|
||||
**CRITICAL - References in Frontmatter**:
|
||||
@@ -352,7 +352,7 @@ Check available skills. If multiple, ask user.
|
||||
|
||||
| Skill Supports `--ref` | Action |
|
||||
|------------------------|--------|
|
||||
| Yes (e.g., baoyu-image-gen with Google) | Pass reference images via `--ref` |
|
||||
| Yes (e.g., baoyu-imagine with Google) | Pass reference images via `--ref` |
|
||||
| No | Convert to text description, append to prompt |
|
||||
|
||||
**Verification**: Before generating, confirm reference processing:
|
||||
|
||||
@@ -29,8 +29,8 @@ Options:
|
||||
--prompts <path> Path to prompts directory
|
||||
--output <path> Path to output batch.json
|
||||
--images-dir <path> Directory for generated images
|
||||
--provider <name> Provider for baoyu-image-gen batch tasks (default: replicate)
|
||||
--model <id> Model for baoyu-image-gen batch tasks (default: google/nano-banana-pro)
|
||||
--provider <name> Provider for baoyu-imagine batch tasks (default: replicate)
|
||||
--model <id> Model for baoyu-imagine batch tasks (default: google/nano-banana-pro)
|
||||
--ar <ratio> Aspect ratio for all tasks (default: 16:9)
|
||||
--quality <level> Quality for all tasks (default: 2k)
|
||||
--jobs <count> Recommended worker count metadata (optional)
|
||||
|
||||
@@ -216,7 +216,7 @@ Analyze → [Check Existing?] → [Confirm: Style + Reviews] → Storyboard →
|
||||
|
||||
**7.1 Generate character sheet first**:
|
||||
- **Backup rule**: If `characters/characters.png` exists, rename to `characters/characters-backup-YYYYMMDD-HHMMSS.png`
|
||||
- Invoke an installed image generation skill such as `baoyu-image-gen`
|
||||
- Invoke an installed image generation skill such as `baoyu-imagine`
|
||||
- Read that skill's `SKILL.md` and follow its documented interface rather than calling its scripts directly
|
||||
- Use `characters/characters.md` as the prompt-file input
|
||||
- Save output to `characters/characters.png`
|
||||
|
||||
@@ -433,7 +433,7 @@ With confirmed prompts from Step 5/6:
|
||||
| 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)
|
||||
**Strategy A: Using `--ref` parameter** (e.g., baoyu-imagine)
|
||||
|
||||
- Read the chosen image generation skill's `SKILL.md`
|
||||
- Invoke that installed skill via its documented interface, not by calling its scripts directly
|
||||
|
||||
@@ -1,406 +1,19 @@
|
||||
---
|
||||
name: baoyu-image-gen
|
||||
description: AI image generation with OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
|
||||
version: 1.56.4
|
||||
metadata:
|
||||
openclaw:
|
||||
homepage: https://github.com/JimLiu/baoyu-skills#baoyu-image-gen
|
||||
requires:
|
||||
anyBins:
|
||||
- bun
|
||||
- npx
|
||||
description: "[DEPRECATED] This skill has been renamed to baoyu-imagine. Triggers on any reference to 'baoyu-image-gen' so users can be guided to upgrade. Use this whenever you detect the old skill name in user prompts, EXTEND.md, or installed skill lists."
|
||||
---
|
||||
|
||||
# Image Generation (AI SDK)
|
||||
# baoyu-image-gen is now baoyu-imagine
|
||||
|
||||
Official API-based image generation. Supports OpenAI, Azure OpenAI, Google, OpenRouter, DashScope (阿里通义万象), MiniMax, Jimeng (即梦), Seedream (豆包) and Replicate providers.
|
||||
This skill has been renamed to **baoyu-imagine** with new features and providers.
|
||||
|
||||
## Script Directory
|
||||
## What to do
|
||||
|
||||
**Agent Execution**:
|
||||
1. `{baseDir}` = this SKILL.md file's directory
|
||||
2. Script path = `{baseDir}/scripts/main.ts`
|
||||
3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun
|
||||
When this skill is triggered, inform the user that `baoyu-image-gen` has been renamed to `baoyu-imagine` with new features and providers, and ask for their confirmation to:
|
||||
|
||||
## Step 0: Load Preferences ⛔ BLOCKING
|
||||
1. **Install the new skill** from: `https://github.com/JimLiu/baoyu-skills/blob/main/skills/baoyu-imagine/SKILL.md`
|
||||
2. **Remove the old `baoyu-image-gen` skill**
|
||||
|
||||
**CRITICAL**: This step MUST complete BEFORE any image generation. Do NOT skip or defer.
|
||||
No config changes are needed — `baoyu-imagine` reads the same EXTEND.md settings (API keys, default provider, etc.).
|
||||
|
||||
Check EXTEND.md existence (priority: project → user):
|
||||
|
||||
```bash
|
||||
# macOS, Linux, WSL, Git Bash
|
||||
test -f .baoyu-skills/baoyu-image-gen/EXTEND.md && echo "project"
|
||||
test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-image-gen/EXTEND.md" && echo "xdg"
|
||||
test -f "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md" && echo "user"
|
||||
```
|
||||
|
||||
```powershell
|
||||
# PowerShell (Windows)
|
||||
if (Test-Path .baoyu-skills/baoyu-image-gen/EXTEND.md) { "project" }
|
||||
$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
|
||||
if (Test-Path "$xdg/baoyu-skills/baoyu-image-gen/EXTEND.md") { "xdg" }
|
||||
if (Test-Path "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md") { "user" }
|
||||
```
|
||||
|
||||
| Result | Action |
|
||||
|--------|--------|
|
||||
| Found | Load, parse, apply settings. If `default_model.[provider]` is null → ask model only (Flow 2) |
|
||||
| Not found | ⛔ Run first-time setup ([references/config/first-time-setup.md](references/config/first-time-setup.md)) → Save EXTEND.md → Then continue |
|
||||
|
||||
**CRITICAL**: If not found, complete the full setup (provider + model + quality + save location) using AskUserQuestion BEFORE generating any images. Generation is BLOCKED until EXTEND.md is created.
|
||||
|
||||
| Path | Location |
|
||||
|------|----------|
|
||||
| `.baoyu-skills/baoyu-image-gen/EXTEND.md` | Project directory |
|
||||
| `$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md` | User home |
|
||||
|
||||
**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models | Batch worker cap | Provider-specific batch limits
|
||||
|
||||
Schema: `references/config/preferences-schema.md`
|
||||
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
# Basic
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image cat.png
|
||||
|
||||
# With aspect ratio
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A landscape" --image out.png --ar 16:9
|
||||
|
||||
# High quality
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --quality 2k
|
||||
|
||||
# From prompt files
|
||||
${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png
|
||||
|
||||
# With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 4.0/4.5/5.0)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
|
||||
|
||||
# With reference images (explicit provider/model)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png
|
||||
|
||||
# Azure OpenAI (model means deployment name)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider azure --model gpt-image-1.5
|
||||
|
||||
# OpenRouter (recommended default model)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openrouter
|
||||
|
||||
# OpenRouter with reference images
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
|
||||
|
||||
# Specific provider
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openai
|
||||
|
||||
# DashScope (阿里通义万象)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "一只可爱的猫" --image out.png --provider dashscope
|
||||
|
||||
# DashScope Qwen-Image 2.0 Pro (recommended for custom sizes and text rendering)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image out.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
|
||||
|
||||
# DashScope legacy Qwen fixed-size model
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "一张电影感海报" --image out.png --provider dashscope --model qwen-image-max --size 1664x928
|
||||
|
||||
# MiniMax
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
|
||||
|
||||
# MiniMax with subject reference (best for character/portrait consistency)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
|
||||
|
||||
# MiniMax with custom size (documented for image-01)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cinematic poster" --image out.jpg --provider minimax --model image-01 --size 1536x1024
|
||||
|
||||
# Replicate (google/nano-banana-pro)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
|
||||
|
||||
# Replicate with specific model
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
|
||||
|
||||
# Batch mode with saved prompt files
|
||||
${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json
|
||||
|
||||
# Batch mode with explicit worker count
|
||||
${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json --jobs 4 --json
|
||||
```
|
||||
|
||||
### Batch File Format
|
||||
|
||||
```json
|
||||
{
|
||||
"jobs": 4,
|
||||
"tasks": [
|
||||
{
|
||||
"id": "hero",
|
||||
"promptFiles": ["prompts/hero.md"],
|
||||
"image": "out/hero.png",
|
||||
"provider": "replicate",
|
||||
"model": "google/nano-banana-pro",
|
||||
"ar": "16:9",
|
||||
"quality": "2k"
|
||||
},
|
||||
{
|
||||
"id": "diagram",
|
||||
"promptFiles": ["prompts/diagram.md"],
|
||||
"image": "out/diagram.png",
|
||||
"ref": ["references/original.png"]
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch file's directory. `jobs` is optional (overridden by CLI `--jobs`). Top-level array format (without `jobs` wrapper) is also accepted.
|
||||
|
||||
## Options
|
||||
|
||||
| Option | Description |
|
||||
|--------|-------------|
|
||||
| `--prompt <text>`, `-p` | Prompt text |
|
||||
| `--promptfiles <files...>` | Read prompt from files (concatenated) |
|
||||
| `--image <path>` | Output image path (required in single-image mode) |
|
||||
| `--batchfile <path>` | JSON batch file for multi-image generation |
|
||||
| `--jobs <count>` | Worker count for batch mode (default: auto, max from config, built-in default 10) |
|
||||
| `--provider google\|openai\|azure\|openrouter\|dashscope\|minimax\|jimeng\|seedream\|replicate` | Force provider (default: auto-detect) |
|
||||
| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`; OpenAI: `gpt-image-1.5`; Azure: deployment name such as `gpt-image-1.5` or `image-prod`; OpenRouter: `google/gemini-3.1-flash-image-preview`; DashScope: `qwen-image-2.0-pro`; MiniMax: `image-01`) |
|
||||
| `--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/OpenRouter (default: from quality) |
|
||||
| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, Azure OpenAI edits (PNG/JPG only), OpenRouter multimodal models, Replicate, MiniMax subject-reference, and Seedream 5.0/4.5/4.0. Not supported by Jimeng, Seedream 3.0, or removed SeedEdit 3.0 |
|
||||
| `--n <count>` | Number of images |
|
||||
| `--json` | JSON output |
|
||||
|
||||
## Environment Variables
|
||||
|
||||
| Variable | Description |
|
||||
|----------|-------------|
|
||||
| `OPENAI_API_KEY` | OpenAI API key |
|
||||
| `AZURE_OPENAI_API_KEY` | Azure OpenAI API key |
|
||||
| `OPENROUTER_API_KEY` | OpenRouter API key |
|
||||
| `GOOGLE_API_KEY` | Google API key |
|
||||
| `DASHSCOPE_API_KEY` | DashScope API key (阿里云) |
|
||||
| `MINIMAX_API_KEY` | MiniMax API key |
|
||||
| `REPLICATE_API_TOKEN` | Replicate API token |
|
||||
| `JIMENG_ACCESS_KEY_ID` | Jimeng (即梦) Volcengine access key |
|
||||
| `JIMENG_SECRET_ACCESS_KEY` | Jimeng (即梦) Volcengine secret key |
|
||||
| `ARK_API_KEY` | Seedream (豆包) Volcengine ARK API key |
|
||||
| `OPENAI_IMAGE_MODEL` | OpenAI model override |
|
||||
| `AZURE_OPENAI_DEPLOYMENT` | Azure default deployment name |
|
||||
| `AZURE_OPENAI_IMAGE_MODEL` | Backward-compatible alias for Azure default deployment/model name |
|
||||
| `OPENROUTER_IMAGE_MODEL` | OpenRouter model override (default: `google/gemini-3.1-flash-image-preview`) |
|
||||
| `GOOGLE_IMAGE_MODEL` | Google model override |
|
||||
| `DASHSCOPE_IMAGE_MODEL` | DashScope model override (default: `qwen-image-2.0-pro`) |
|
||||
| `MINIMAX_IMAGE_MODEL` | MiniMax model override (default: `image-01`) |
|
||||
| `REPLICATE_IMAGE_MODEL` | Replicate model override (default: google/nano-banana-pro) |
|
||||
| `JIMENG_IMAGE_MODEL` | Jimeng model override (default: jimeng_t2i_v40) |
|
||||
| `SEEDREAM_IMAGE_MODEL` | Seedream model override (default: doubao-seedream-5-0-260128) |
|
||||
| `OPENAI_BASE_URL` | Custom OpenAI endpoint |
|
||||
| `AZURE_OPENAI_BASE_URL` | Azure resource endpoint or deployment endpoint |
|
||||
| `AZURE_API_VERSION` | Azure image API version (default: `2025-04-01-preview`) |
|
||||
| `OPENROUTER_BASE_URL` | Custom OpenRouter endpoint (default: `https://openrouter.ai/api/v1`) |
|
||||
| `OPENROUTER_HTTP_REFERER` | Optional app/site URL for OpenRouter attribution |
|
||||
| `OPENROUTER_TITLE` | Optional app name for OpenRouter attribution |
|
||||
| `GOOGLE_BASE_URL` | Custom Google endpoint |
|
||||
| `DASHSCOPE_BASE_URL` | Custom DashScope endpoint |
|
||||
| `MINIMAX_BASE_URL` | Custom MiniMax endpoint (default: `https://api.minimax.io`) |
|
||||
| `REPLICATE_BASE_URL` | Custom Replicate endpoint |
|
||||
| `JIMENG_BASE_URL` | Custom Jimeng endpoint (default: `https://visual.volcengineapi.com`) |
|
||||
| `JIMENG_REGION` | Jimeng region (default: `cn-north-1`) |
|
||||
| `SEEDREAM_BASE_URL` | Custom Seedream endpoint (default: `https://ark.cn-beijing.volces.com/api/v3`) |
|
||||
| `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap |
|
||||
| `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Override provider concurrency, e.g. `BAOYU_IMAGE_GEN_REPLICATE_CONCURRENCY` |
|
||||
| `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Override provider start gap, e.g. `BAOYU_IMAGE_GEN_REPLICATE_START_INTERVAL_MS` |
|
||||
|
||||
**Load Priority**: CLI args > EXTEND.md > env vars > `<cwd>/.baoyu-skills/.env` > `~/.baoyu-skills/.env`
|
||||
|
||||
## Model Resolution
|
||||
|
||||
Model priority (highest → lowest), applies to all providers:
|
||||
|
||||
1. CLI flag: `--model <id>`
|
||||
2. EXTEND.md: `default_model.[provider]`
|
||||
3. Env var: `<PROVIDER>_IMAGE_MODEL` (e.g., `GOOGLE_IMAGE_MODEL`)
|
||||
4. Built-in default
|
||||
|
||||
For Azure, `--model` / `default_model.azure` should be the Azure deployment name. `AZURE_OPENAI_DEPLOYMENT` is the preferred env var, and `AZURE_OPENAI_IMAGE_MODEL` remains as a backward-compatible alias.
|
||||
|
||||
**EXTEND.md overrides env vars**. If both EXTEND.md `default_model.google: "gemini-3-pro-image-preview"` and env var `GOOGLE_IMAGE_MODEL=gemini-3.1-flash-image-preview` exist, EXTEND.md wins.
|
||||
|
||||
**Agent MUST display model info** before each generation:
|
||||
- Show: `Using [provider] / [model]`
|
||||
- Show switch hint: `Switch model: --model <id> | EXTEND.md default_model.[provider] | env <PROVIDER>_IMAGE_MODEL`
|
||||
|
||||
### DashScope Models
|
||||
|
||||
Use `--model qwen-image-2.0-pro` or set `default_model.dashscope` / `DASHSCOPE_IMAGE_MODEL` when the user wants official Qwen-Image behavior.
|
||||
|
||||
Official DashScope model families:
|
||||
|
||||
- `qwen-image-2.0-pro`, `qwen-image-2.0-pro-2026-03-03`, `qwen-image-2.0`, `qwen-image-2.0-2026-03-03`
|
||||
- Free-form `size` in `宽*高` format
|
||||
- Total pixels must stay between `512*512` and `2048*2048`
|
||||
- Default size is approximately `1024*1024`
|
||||
- Best choice for custom ratios such as `21:9` and text-heavy Chinese/English layouts
|
||||
- `qwen-image-max`, `qwen-image-max-2025-12-30`, `qwen-image-plus`, `qwen-image-plus-2026-01-09`, `qwen-image`
|
||||
- Fixed sizes only: `1664*928`, `1472*1104`, `1328*1328`, `1104*1472`, `928*1664`
|
||||
- Default size is `1664*928`
|
||||
- `qwen-image` currently has the same capability as `qwen-image-plus`
|
||||
- Legacy DashScope models such as `z-image-turbo`, `z-image-ultra`, `wanx-v1`
|
||||
- Keep using them only when the user explicitly asks for legacy behavior or compatibility
|
||||
|
||||
When translating CLI args into DashScope behavior:
|
||||
|
||||
- `--size` wins over `--ar`
|
||||
- For `qwen-image-2.0*`, prefer explicit `--size`; otherwise infer from `--ar` and use the official recommended resolutions below
|
||||
- For `qwen-image-max/plus/image`, only use the five official fixed sizes; if the requested ratio is not covered, switch to `qwen-image-2.0-pro`
|
||||
- `--quality` is a baoyu-image-gen compatibility preset, not a native DashScope API field. Mapping `normal` / `2k` onto the `qwen-image-2.0*` table below is an implementation inference, not an official API guarantee
|
||||
|
||||
Recommended `qwen-image-2.0*` sizes for common aspect ratios:
|
||||
|
||||
| Ratio | `normal` | `2k` |
|
||||
|-------|----------|------|
|
||||
| `1:1` | `1024*1024` | `1536*1536` |
|
||||
| `2:3` | `768*1152` | `1024*1536` |
|
||||
| `3:2` | `1152*768` | `1536*1024` |
|
||||
| `3:4` | `960*1280` | `1080*1440` |
|
||||
| `4:3` | `1280*960` | `1440*1080` |
|
||||
| `9:16` | `720*1280` | `1080*1920` |
|
||||
| `16:9` | `1280*720` | `1920*1080` |
|
||||
| `21:9` | `1344*576` | `2048*872` |
|
||||
|
||||
DashScope official APIs also expose `negative_prompt`, `prompt_extend`, and `watermark`, but `baoyu-image-gen` does not expose them as dedicated CLI flags today.
|
||||
|
||||
Official references:
|
||||
|
||||
- [Qwen-Image API](https://help.aliyun.com/zh/model-studio/qwen-image-api)
|
||||
- [Text-to-image guide](https://help.aliyun.com/zh/model-studio/text-to-image)
|
||||
- [Qwen-Image Edit API](https://help.aliyun.com/zh/model-studio/qwen-image-edit-api)
|
||||
|
||||
### MiniMax Models
|
||||
|
||||
Use `--model image-01` or set `default_model.minimax` / `MINIMAX_IMAGE_MODEL` when the user wants MiniMax image generation.
|
||||
|
||||
Official MiniMax image model options currently documented in the API reference:
|
||||
|
||||
- `image-01` (recommended default)
|
||||
- Supports text-to-image and subject-reference image generation
|
||||
- Supports official `aspect_ratio` values: `1:1`, `16:9`, `4:3`, `3:2`, `2:3`, `3:4`, `9:16`, `21:9`
|
||||
- Supports documented custom `width` / `height` output sizes when using `--size <WxH>`
|
||||
- `width` and `height` must both be between `512` and `2048`, and both must be divisible by `8`
|
||||
- `image-01-live`
|
||||
- Lower-latency variant
|
||||
- Use `--ar` for sizing; MiniMax documents custom `width` / `height` as only effective for `image-01`
|
||||
|
||||
MiniMax subject reference notes:
|
||||
|
||||
- `--ref` files are sent as MiniMax `subject_reference`
|
||||
- MiniMax docs currently describe `subject_reference[].type` as `character`
|
||||
- Official docs say `image_file` supports public URLs or Base64 Data URLs; `baoyu-image-gen` sends local refs as Data URLs
|
||||
- Official docs recommend front-facing portrait references in JPG/JPEG/PNG under 10MB
|
||||
|
||||
Official references:
|
||||
|
||||
- [MiniMax Image Generation Guide](https://platform.minimax.io/docs/guides/image-generation)
|
||||
- [MiniMax Text-to-Image API](https://platform.minimax.io/docs/api-reference/image-generation-t2i)
|
||||
- [MiniMax Image-to-Image API](https://platform.minimax.io/docs/api-reference/image-generation-i2i)
|
||||
|
||||
### OpenRouter Models
|
||||
|
||||
Use full OpenRouter model IDs, e.g.:
|
||||
|
||||
- `google/gemini-3.1-flash-image-preview` (recommended, supports image output and reference-image workflows)
|
||||
- `google/gemini-2.5-flash-image-preview`
|
||||
- `black-forest-labs/flux.2-pro`
|
||||
- Other OpenRouter image-capable model IDs
|
||||
|
||||
Notes:
|
||||
|
||||
- OpenRouter image generation uses `/chat/completions`, not the OpenAI `/images` endpoints
|
||||
- If `--ref` is used, choose a multimodal model that supports image input and image output
|
||||
- `--imageSize` maps to OpenRouter `imageGenerationOptions.size`; `--size <WxH>` is converted to the nearest OpenRouter size and inferred aspect ratio when possible
|
||||
|
||||
### 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:
|
||||
|
||||
```bash
|
||||
# Use Replicate default model
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
|
||||
|
||||
# Override model explicitly
|
||||
${BUN_X} {baseDir}/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 Azure, then OpenRouter, then Replicate, then Seedream, then MiniMax (MiniMax subject reference is more specialized toward character/portrait consistency)
|
||||
2. `--provider` specified → use it (if `--ref`, must be `google`, `openai`, `azure`, `openrouter`, `replicate`, `seedream`, or `minimax`)
|
||||
3. Only one API key available → use that provider
|
||||
4. Multiple available → default to Google
|
||||
|
||||
## Quality Presets
|
||||
|
||||
| Preset | Google imageSize | OpenAI Size | OpenRouter size | Replicate resolution | Use Case |
|
||||
|--------|------------------|-------------|-----------------|----------------------|----------|
|
||||
| `normal` | 1K | 1024px | 1K | 1K | Quick previews |
|
||||
| `2k` (default) | 2K | 2048px | 2K | 2K | Covers, illustrations, infographics |
|
||||
|
||||
**Google/OpenRouter 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`
|
||||
- OpenAI: maps to closest supported size
|
||||
- OpenRouter: sends `imageGenerationOptions.aspect_ratio`; if only `--size <WxH>` is given, aspect ratio is inferred automatically
|
||||
- Replicate: passes `aspect_ratio` to model; when `--ref` is provided without `--ar`, defaults to `match_input_image`
|
||||
- MiniMax: sends official `aspect_ratio` values directly; if `--size <WxH>` is given without `--ar`, `width` / `height` are sent for `image-01`
|
||||
|
||||
## Generation Mode
|
||||
|
||||
**Default**: Sequential generation.
|
||||
|
||||
**Batch Parallel Generation**: When `--batchfile` contains 2 or more pending tasks, the script automatically enables parallel generation.
|
||||
|
||||
| Mode | When to Use |
|
||||
|------|-------------|
|
||||
| Sequential (default) | Normal usage, single images, small batches |
|
||||
| Parallel batch | Batch mode with 2+ tasks |
|
||||
|
||||
Execution choice:
|
||||
|
||||
| Situation | Preferred approach | Why |
|
||||
|-----------|--------------------|-----|
|
||||
| One image, or 1-2 simple images | Sequential | Lower coordination overhead and easier debugging |
|
||||
| Multiple images already have saved prompt files | Batch (`--batchfile`) | Reuses finalized prompts, applies shared throttling/retries, and gives predictable throughput |
|
||||
| Each image still needs separate reasoning, prompt writing, or style exploration | Subagents | The work is still exploratory, so each image may need independent analysis before generation |
|
||||
| Output comes from `baoyu-article-illustrator` with `outline.md` + `prompts/` | Batch (`build-batch.ts` -> `--batchfile`) | That workflow already produces prompt files, so direct batch execution is the intended path |
|
||||
|
||||
Rule of thumb:
|
||||
|
||||
- Prefer batch over subagents once prompt files are already saved and the task is "generate all of these"
|
||||
- Use subagents only when generation is coupled with per-image thinking, rewriting, or divergent creative exploration
|
||||
|
||||
Parallel behavior:
|
||||
|
||||
- Default worker count is automatic, capped by config, built-in default 10
|
||||
- Provider-specific throttling is applied only in batch mode, and the built-in defaults are tuned for faster throughput while still avoiding obvious RPM bursts
|
||||
- You can override worker count with `--jobs <count>`
|
||||
- Each image retries automatically up to 3 attempts
|
||||
- Final output includes success count, failure count, and per-image failure reasons
|
||||
|
||||
## Error Handling
|
||||
|
||||
- Missing API key → error with setup instructions
|
||||
- Generation failure → auto-retry up to 3 attempts per image
|
||||
- Invalid aspect ratio → warning, proceed with default
|
||||
- Reference images with unsupported provider/model → error with fix hint
|
||||
|
||||
## Extension Support
|
||||
|
||||
Custom configurations via EXTEND.md. See **Preferences** section for paths and supported options.
|
||||
Once the user confirms, help them complete the installation and removal using whatever mechanism the current environment supports. If the user also has an image generation request, proceed with `baoyu-imagine` after migration.
|
||||
|
||||
@@ -0,0 +1,408 @@
|
||||
---
|
||||
name: baoyu-imagine
|
||||
description: AI image generation with OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
|
||||
version: 1.56.4
|
||||
metadata:
|
||||
openclaw:
|
||||
homepage: https://github.com/JimLiu/baoyu-skills#baoyu-imagine
|
||||
requires:
|
||||
anyBins:
|
||||
- bun
|
||||
- npx
|
||||
---
|
||||
|
||||
# Image Generation (AI SDK)
|
||||
|
||||
Official API-based image generation. Supports OpenAI, Azure OpenAI, Google, OpenRouter, DashScope (阿里通义万象), MiniMax, Jimeng (即梦), Seedream (豆包) and Replicate providers.
|
||||
|
||||
## Script Directory
|
||||
|
||||
**Agent Execution**:
|
||||
1. `{baseDir}` = this SKILL.md file's directory
|
||||
2. Script path = `{baseDir}/scripts/main.ts`
|
||||
3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun
|
||||
|
||||
## Step 0: Load Preferences ⛔ BLOCKING
|
||||
|
||||
**CRITICAL**: This step MUST complete BEFORE any image generation. Do NOT skip or defer.
|
||||
|
||||
Check EXTEND.md existence (priority: project → user):
|
||||
|
||||
```bash
|
||||
# macOS, Linux, WSL, Git Bash
|
||||
test -f .baoyu-skills/baoyu-imagine/EXTEND.md && echo "project"
|
||||
test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-imagine/EXTEND.md" && echo "xdg"
|
||||
test -f "$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md" && echo "user"
|
||||
```
|
||||
|
||||
```powershell
|
||||
# PowerShell (Windows)
|
||||
if (Test-Path .baoyu-skills/baoyu-imagine/EXTEND.md) { "project" }
|
||||
$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
|
||||
if (Test-Path "$xdg/baoyu-skills/baoyu-imagine/EXTEND.md") { "xdg" }
|
||||
if (Test-Path "$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md") { "user" }
|
||||
```
|
||||
|
||||
| Result | Action |
|
||||
|--------|--------|
|
||||
| Found | Load, parse, apply settings. If `default_model.[provider]` is null → ask model only (Flow 2) |
|
||||
| Not found | ⛔ Run first-time setup ([references/config/first-time-setup.md](references/config/first-time-setup.md)) → Save EXTEND.md → Then continue |
|
||||
|
||||
**CRITICAL**: If not found, complete the full setup (provider + model + quality + save location) using AskUserQuestion BEFORE generating any images. Generation is BLOCKED until EXTEND.md is created.
|
||||
|
||||
| Path | Location |
|
||||
|------|----------|
|
||||
| `.baoyu-skills/baoyu-imagine/EXTEND.md` | Project directory |
|
||||
| `$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md` | User home |
|
||||
|
||||
Legacy compatibility: if `.baoyu-skills/baoyu-image-gen/EXTEND.md` exists and the new path does not, runtime renames it to `baoyu-imagine`. If both files exist, runtime leaves them unchanged and uses the new path.
|
||||
|
||||
**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models | Batch worker cap | Provider-specific batch limits
|
||||
|
||||
Schema: `references/config/preferences-schema.md`
|
||||
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
# Basic
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image cat.png
|
||||
|
||||
# With aspect ratio
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A landscape" --image out.png --ar 16:9
|
||||
|
||||
# High quality
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --quality 2k
|
||||
|
||||
# From prompt files
|
||||
${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png
|
||||
|
||||
# With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 4.0/4.5/5.0)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
|
||||
|
||||
# With reference images (explicit provider/model)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png
|
||||
|
||||
# Azure OpenAI (model means deployment name)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider azure --model gpt-image-1.5
|
||||
|
||||
# OpenRouter (recommended default model)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openrouter
|
||||
|
||||
# OpenRouter with reference images
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
|
||||
|
||||
# Specific provider
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openai
|
||||
|
||||
# DashScope (阿里通义万象)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "一只可爱的猫" --image out.png --provider dashscope
|
||||
|
||||
# DashScope Qwen-Image 2.0 Pro (recommended for custom sizes and text rendering)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image out.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
|
||||
|
||||
# DashScope legacy Qwen fixed-size model
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "一张电影感海报" --image out.png --provider dashscope --model qwen-image-max --size 1664x928
|
||||
|
||||
# MiniMax
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
|
||||
|
||||
# MiniMax with subject reference (best for character/portrait consistency)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
|
||||
|
||||
# MiniMax with custom size (documented for image-01)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cinematic poster" --image out.jpg --provider minimax --model image-01 --size 1536x1024
|
||||
|
||||
# Replicate (google/nano-banana-pro)
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
|
||||
|
||||
# Replicate with specific model
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
|
||||
|
||||
# Batch mode with saved prompt files
|
||||
${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json
|
||||
|
||||
# Batch mode with explicit worker count
|
||||
${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json --jobs 4 --json
|
||||
```
|
||||
|
||||
### Batch File Format
|
||||
|
||||
```json
|
||||
{
|
||||
"jobs": 4,
|
||||
"tasks": [
|
||||
{
|
||||
"id": "hero",
|
||||
"promptFiles": ["prompts/hero.md"],
|
||||
"image": "out/hero.png",
|
||||
"provider": "replicate",
|
||||
"model": "google/nano-banana-pro",
|
||||
"ar": "16:9",
|
||||
"quality": "2k"
|
||||
},
|
||||
{
|
||||
"id": "diagram",
|
||||
"promptFiles": ["prompts/diagram.md"],
|
||||
"image": "out/diagram.png",
|
||||
"ref": ["references/original.png"]
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch file's directory. `jobs` is optional (overridden by CLI `--jobs`). Top-level array format (without `jobs` wrapper) is also accepted.
|
||||
|
||||
## Options
|
||||
|
||||
| Option | Description |
|
||||
|--------|-------------|
|
||||
| `--prompt <text>`, `-p` | Prompt text |
|
||||
| `--promptfiles <files...>` | Read prompt from files (concatenated) |
|
||||
| `--image <path>` | Output image path (required in single-image mode) |
|
||||
| `--batchfile <path>` | JSON batch file for multi-image generation |
|
||||
| `--jobs <count>` | Worker count for batch mode (default: auto, max from config, built-in default 10) |
|
||||
| `--provider google\|openai\|azure\|openrouter\|dashscope\|minimax\|jimeng\|seedream\|replicate` | Force provider (default: auto-detect) |
|
||||
| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`; OpenAI: `gpt-image-1.5`; Azure: deployment name such as `gpt-image-1.5` or `image-prod`; OpenRouter: `google/gemini-3.1-flash-image-preview`; DashScope: `qwen-image-2.0-pro`; MiniMax: `image-01`) |
|
||||
| `--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/OpenRouter (default: from quality) |
|
||||
| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, Azure OpenAI edits (PNG/JPG only), OpenRouter multimodal models, Replicate, MiniMax subject-reference, and Seedream 5.0/4.5/4.0. Not supported by Jimeng, Seedream 3.0, or removed SeedEdit 3.0 |
|
||||
| `--n <count>` | Number of images |
|
||||
| `--json` | JSON output |
|
||||
|
||||
## Environment Variables
|
||||
|
||||
| Variable | Description |
|
||||
|----------|-------------|
|
||||
| `OPENAI_API_KEY` | OpenAI API key |
|
||||
| `AZURE_OPENAI_API_KEY` | Azure OpenAI API key |
|
||||
| `OPENROUTER_API_KEY` | OpenRouter API key |
|
||||
| `GOOGLE_API_KEY` | Google API key |
|
||||
| `DASHSCOPE_API_KEY` | DashScope API key (阿里云) |
|
||||
| `MINIMAX_API_KEY` | MiniMax API key |
|
||||
| `REPLICATE_API_TOKEN` | Replicate API token |
|
||||
| `JIMENG_ACCESS_KEY_ID` | Jimeng (即梦) Volcengine access key |
|
||||
| `JIMENG_SECRET_ACCESS_KEY` | Jimeng (即梦) Volcengine secret key |
|
||||
| `ARK_API_KEY` | Seedream (豆包) Volcengine ARK API key |
|
||||
| `OPENAI_IMAGE_MODEL` | OpenAI model override |
|
||||
| `AZURE_OPENAI_DEPLOYMENT` | Azure default deployment name |
|
||||
| `AZURE_OPENAI_IMAGE_MODEL` | Backward-compatible alias for Azure default deployment/model name |
|
||||
| `OPENROUTER_IMAGE_MODEL` | OpenRouter model override (default: `google/gemini-3.1-flash-image-preview`) |
|
||||
| `GOOGLE_IMAGE_MODEL` | Google model override |
|
||||
| `DASHSCOPE_IMAGE_MODEL` | DashScope model override (default: `qwen-image-2.0-pro`) |
|
||||
| `MINIMAX_IMAGE_MODEL` | MiniMax model override (default: `image-01`) |
|
||||
| `REPLICATE_IMAGE_MODEL` | Replicate model override (default: google/nano-banana-pro) |
|
||||
| `JIMENG_IMAGE_MODEL` | Jimeng model override (default: jimeng_t2i_v40) |
|
||||
| `SEEDREAM_IMAGE_MODEL` | Seedream model override (default: doubao-seedream-5-0-260128) |
|
||||
| `OPENAI_BASE_URL` | Custom OpenAI endpoint |
|
||||
| `AZURE_OPENAI_BASE_URL` | Azure resource endpoint or deployment endpoint |
|
||||
| `AZURE_API_VERSION` | Azure image API version (default: `2025-04-01-preview`) |
|
||||
| `OPENROUTER_BASE_URL` | Custom OpenRouter endpoint (default: `https://openrouter.ai/api/v1`) |
|
||||
| `OPENROUTER_HTTP_REFERER` | Optional app/site URL for OpenRouter attribution |
|
||||
| `OPENROUTER_TITLE` | Optional app name for OpenRouter attribution |
|
||||
| `GOOGLE_BASE_URL` | Custom Google endpoint |
|
||||
| `DASHSCOPE_BASE_URL` | Custom DashScope endpoint |
|
||||
| `MINIMAX_BASE_URL` | Custom MiniMax endpoint (default: `https://api.minimax.io`) |
|
||||
| `REPLICATE_BASE_URL` | Custom Replicate endpoint |
|
||||
| `JIMENG_BASE_URL` | Custom Jimeng endpoint (default: `https://visual.volcengineapi.com`) |
|
||||
| `JIMENG_REGION` | Jimeng region (default: `cn-north-1`) |
|
||||
| `SEEDREAM_BASE_URL` | Custom Seedream endpoint (default: `https://ark.cn-beijing.volces.com/api/v3`) |
|
||||
| `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap |
|
||||
| `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Override provider concurrency, e.g. `BAOYU_IMAGE_GEN_REPLICATE_CONCURRENCY` |
|
||||
| `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Override provider start gap, e.g. `BAOYU_IMAGE_GEN_REPLICATE_START_INTERVAL_MS` |
|
||||
|
||||
**Load Priority**: CLI args > EXTEND.md > env vars > `<cwd>/.baoyu-skills/.env` > `~/.baoyu-skills/.env`
|
||||
|
||||
## Model Resolution
|
||||
|
||||
Model priority (highest → lowest), applies to all providers:
|
||||
|
||||
1. CLI flag: `--model <id>`
|
||||
2. EXTEND.md: `default_model.[provider]`
|
||||
3. Env var: `<PROVIDER>_IMAGE_MODEL` (e.g., `GOOGLE_IMAGE_MODEL`)
|
||||
4. Built-in default
|
||||
|
||||
For Azure, `--model` / `default_model.azure` should be the Azure deployment name. `AZURE_OPENAI_DEPLOYMENT` is the preferred env var, and `AZURE_OPENAI_IMAGE_MODEL` remains as a backward-compatible alias.
|
||||
|
||||
**EXTEND.md overrides env vars**. If both EXTEND.md `default_model.google: "gemini-3-pro-image-preview"` and env var `GOOGLE_IMAGE_MODEL=gemini-3.1-flash-image-preview` exist, EXTEND.md wins.
|
||||
|
||||
**Agent MUST display model info** before each generation:
|
||||
- Show: `Using [provider] / [model]`
|
||||
- Show switch hint: `Switch model: --model <id> | EXTEND.md default_model.[provider] | env <PROVIDER>_IMAGE_MODEL`
|
||||
|
||||
### DashScope Models
|
||||
|
||||
Use `--model qwen-image-2.0-pro` or set `default_model.dashscope` / `DASHSCOPE_IMAGE_MODEL` when the user wants official Qwen-Image behavior.
|
||||
|
||||
Official DashScope model families:
|
||||
|
||||
- `qwen-image-2.0-pro`, `qwen-image-2.0-pro-2026-03-03`, `qwen-image-2.0`, `qwen-image-2.0-2026-03-03`
|
||||
- Free-form `size` in `宽*高` format
|
||||
- Total pixels must stay between `512*512` and `2048*2048`
|
||||
- Default size is approximately `1024*1024`
|
||||
- Best choice for custom ratios such as `21:9` and text-heavy Chinese/English layouts
|
||||
- `qwen-image-max`, `qwen-image-max-2025-12-30`, `qwen-image-plus`, `qwen-image-plus-2026-01-09`, `qwen-image`
|
||||
- Fixed sizes only: `1664*928`, `1472*1104`, `1328*1328`, `1104*1472`, `928*1664`
|
||||
- Default size is `1664*928`
|
||||
- `qwen-image` currently has the same capability as `qwen-image-plus`
|
||||
- Legacy DashScope models such as `z-image-turbo`, `z-image-ultra`, `wanx-v1`
|
||||
- Keep using them only when the user explicitly asks for legacy behavior or compatibility
|
||||
|
||||
When translating CLI args into DashScope behavior:
|
||||
|
||||
- `--size` wins over `--ar`
|
||||
- For `qwen-image-2.0*`, prefer explicit `--size`; otherwise infer from `--ar` and use the official recommended resolutions below
|
||||
- For `qwen-image-max/plus/image`, only use the five official fixed sizes; if the requested ratio is not covered, switch to `qwen-image-2.0-pro`
|
||||
- `--quality` is a baoyu-imagine compatibility preset, not a native DashScope API field. Mapping `normal` / `2k` onto the `qwen-image-2.0*` table below is an implementation inference, not an official API guarantee
|
||||
|
||||
Recommended `qwen-image-2.0*` sizes for common aspect ratios:
|
||||
|
||||
| Ratio | `normal` | `2k` |
|
||||
|-------|----------|------|
|
||||
| `1:1` | `1024*1024` | `1536*1536` |
|
||||
| `2:3` | `768*1152` | `1024*1536` |
|
||||
| `3:2` | `1152*768` | `1536*1024` |
|
||||
| `3:4` | `960*1280` | `1080*1440` |
|
||||
| `4:3` | `1280*960` | `1440*1080` |
|
||||
| `9:16` | `720*1280` | `1080*1920` |
|
||||
| `16:9` | `1280*720` | `1920*1080` |
|
||||
| `21:9` | `1344*576` | `2048*872` |
|
||||
|
||||
DashScope official APIs also expose `negative_prompt`, `prompt_extend`, and `watermark`, but `baoyu-imagine` does not expose them as dedicated CLI flags today.
|
||||
|
||||
Official references:
|
||||
|
||||
- [Qwen-Image API](https://help.aliyun.com/zh/model-studio/qwen-image-api)
|
||||
- [Text-to-image guide](https://help.aliyun.com/zh/model-studio/text-to-image)
|
||||
- [Qwen-Image Edit API](https://help.aliyun.com/zh/model-studio/qwen-image-edit-api)
|
||||
|
||||
### MiniMax Models
|
||||
|
||||
Use `--model image-01` or set `default_model.minimax` / `MINIMAX_IMAGE_MODEL` when the user wants MiniMax image generation.
|
||||
|
||||
Official MiniMax image model options currently documented in the API reference:
|
||||
|
||||
- `image-01` (recommended default)
|
||||
- Supports text-to-image and subject-reference image generation
|
||||
- Supports official `aspect_ratio` values: `1:1`, `16:9`, `4:3`, `3:2`, `2:3`, `3:4`, `9:16`, `21:9`
|
||||
- Supports documented custom `width` / `height` output sizes when using `--size <WxH>`
|
||||
- `width` and `height` must both be between `512` and `2048`, and both must be divisible by `8`
|
||||
- `image-01-live`
|
||||
- Lower-latency variant
|
||||
- Use `--ar` for sizing; MiniMax documents custom `width` / `height` as only effective for `image-01`
|
||||
|
||||
MiniMax subject reference notes:
|
||||
|
||||
- `--ref` files are sent as MiniMax `subject_reference`
|
||||
- MiniMax docs currently describe `subject_reference[].type` as `character`
|
||||
- Official docs say `image_file` supports public URLs or Base64 Data URLs; `baoyu-imagine` sends local refs as Data URLs
|
||||
- Official docs recommend front-facing portrait references in JPG/JPEG/PNG under 10MB
|
||||
|
||||
Official references:
|
||||
|
||||
- [MiniMax Image Generation Guide](https://platform.minimax.io/docs/guides/image-generation)
|
||||
- [MiniMax Text-to-Image API](https://platform.minimax.io/docs/api-reference/image-generation-t2i)
|
||||
- [MiniMax Image-to-Image API](https://platform.minimax.io/docs/api-reference/image-generation-i2i)
|
||||
|
||||
### OpenRouter Models
|
||||
|
||||
Use full OpenRouter model IDs, e.g.:
|
||||
|
||||
- `google/gemini-3.1-flash-image-preview` (recommended, supports image output and reference-image workflows)
|
||||
- `google/gemini-2.5-flash-image-preview`
|
||||
- `black-forest-labs/flux.2-pro`
|
||||
- Other OpenRouter image-capable model IDs
|
||||
|
||||
Notes:
|
||||
|
||||
- OpenRouter image generation uses `/chat/completions`, not the OpenAI `/images` endpoints
|
||||
- If `--ref` is used, choose a multimodal model that supports image input and image output
|
||||
- `--imageSize` maps to OpenRouter `imageGenerationOptions.size`; `--size <WxH>` is converted to the nearest OpenRouter size and inferred aspect ratio when possible
|
||||
|
||||
### 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:
|
||||
|
||||
```bash
|
||||
# Use Replicate default model
|
||||
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
|
||||
|
||||
# Override model explicitly
|
||||
${BUN_X} {baseDir}/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 Azure, then OpenRouter, then Replicate, then Seedream, then MiniMax (MiniMax subject reference is more specialized toward character/portrait consistency)
|
||||
2. `--provider` specified → use it (if `--ref`, must be `google`, `openai`, `azure`, `openrouter`, `replicate`, `seedream`, or `minimax`)
|
||||
3. Only one API key available → use that provider
|
||||
4. Multiple available → default to Google
|
||||
|
||||
## Quality Presets
|
||||
|
||||
| Preset | Google imageSize | OpenAI Size | OpenRouter size | Replicate resolution | Use Case |
|
||||
|--------|------------------|-------------|-----------------|----------------------|----------|
|
||||
| `normal` | 1K | 1024px | 1K | 1K | Quick previews |
|
||||
| `2k` (default) | 2K | 2048px | 2K | 2K | Covers, illustrations, infographics |
|
||||
|
||||
**Google/OpenRouter 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`
|
||||
- OpenAI: maps to closest supported size
|
||||
- OpenRouter: sends `imageGenerationOptions.aspect_ratio`; if only `--size <WxH>` is given, aspect ratio is inferred automatically
|
||||
- Replicate: passes `aspect_ratio` to model; when `--ref` is provided without `--ar`, defaults to `match_input_image`
|
||||
- MiniMax: sends official `aspect_ratio` values directly; if `--size <WxH>` is given without `--ar`, `width` / `height` are sent for `image-01`
|
||||
|
||||
## Generation Mode
|
||||
|
||||
**Default**: Sequential generation.
|
||||
|
||||
**Batch Parallel Generation**: When `--batchfile` contains 2 or more pending tasks, the script automatically enables parallel generation.
|
||||
|
||||
| Mode | When to Use |
|
||||
|------|-------------|
|
||||
| Sequential (default) | Normal usage, single images, small batches |
|
||||
| Parallel batch | Batch mode with 2+ tasks |
|
||||
|
||||
Execution choice:
|
||||
|
||||
| Situation | Preferred approach | Why |
|
||||
|-----------|--------------------|-----|
|
||||
| One image, or 1-2 simple images | Sequential | Lower coordination overhead and easier debugging |
|
||||
| Multiple images already have saved prompt files | Batch (`--batchfile`) | Reuses finalized prompts, applies shared throttling/retries, and gives predictable throughput |
|
||||
| Each image still needs separate reasoning, prompt writing, or style exploration | Subagents | The work is still exploratory, so each image may need independent analysis before generation |
|
||||
| Output comes from `baoyu-article-illustrator` with `outline.md` + `prompts/` | Batch (`build-batch.ts` -> `--batchfile`) | That workflow already produces prompt files, so direct batch execution is the intended path |
|
||||
|
||||
Rule of thumb:
|
||||
|
||||
- Prefer batch over subagents once prompt files are already saved and the task is "generate all of these"
|
||||
- Use subagents only when generation is coupled with per-image thinking, rewriting, or divergent creative exploration
|
||||
|
||||
Parallel behavior:
|
||||
|
||||
- Default worker count is automatic, capped by config, built-in default 10
|
||||
- Provider-specific throttling is applied only in batch mode, and the built-in defaults are tuned for faster throughput while still avoiding obvious RPM bursts
|
||||
- You can override worker count with `--jobs <count>`
|
||||
- Each image retries automatically up to 3 attempts
|
||||
- Final output includes success count, failure count, and per-image failure reasons
|
||||
|
||||
## Error Handling
|
||||
|
||||
- Missing API key → error with setup instructions
|
||||
- Generation failure → auto-retry up to 3 attempts per image
|
||||
- Invalid aspect ratio → warning, proceed with default
|
||||
- Reference images with unsupported provider/model → error with fix hint
|
||||
|
||||
## Extension Support
|
||||
|
||||
Custom configurations via EXTEND.md. See **Preferences** section for paths and supported options.
|
||||
+5
-5
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: first-time-setup
|
||||
description: First-time setup and default model selection flow for baoyu-image-gen
|
||||
description: First-time setup and default model selection flow for baoyu-imagine
|
||||
---
|
||||
|
||||
# First-Time Setup
|
||||
@@ -147,8 +147,8 @@ options:
|
||||
|
||||
| Choice | Path | Scope |
|
||||
|--------|------|-------|
|
||||
| Project | `.baoyu-skills/baoyu-image-gen/EXTEND.md` | Current project |
|
||||
| User | `$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md` | All projects |
|
||||
| Project | `.baoyu-skills/baoyu-imagine/EXTEND.md` | Current project |
|
||||
| User | `$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md` | All projects |
|
||||
|
||||
### EXTEND.md Template
|
||||
|
||||
@@ -214,7 +214,7 @@ options:
|
||||
|
||||
Notes for Azure setup:
|
||||
|
||||
- In `baoyu-image-gen`, Azure `--model` / `default_model.azure` should be the Azure deployment name, not just the underlying model family.
|
||||
- In `baoyu-imagine`, Azure `--model` / `default_model.azure` should be the Azure deployment name, not just the underlying model family.
|
||||
- If the deployment name is custom, save that exact deployment name in `default_model.azure`.
|
||||
|
||||
### OpenRouter Model Selection
|
||||
@@ -255,7 +255,7 @@ Notes for DashScope setup:
|
||||
|
||||
- Prefer `qwen-image-2.0-pro` when the user needs custom `--size`, uncommon ratios like `21:9`, or strong Chinese/English text rendering.
|
||||
- `qwen-image-max` / `qwen-image-plus` / `qwen-image` only support five fixed sizes: `1664*928`, `1472*1104`, `1328*1328`, `1104*1472`, `928*1664`.
|
||||
- In `baoyu-image-gen`, `quality` is a compatibility preset. It is not a native DashScope parameter.
|
||||
- In `baoyu-imagine`, `quality` is a compatibility preset. It is not a native DashScope parameter.
|
||||
|
||||
### Replicate Model Selection
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: preferences-schema
|
||||
description: EXTEND.md YAML schema for baoyu-image-gen user preferences
|
||||
description: EXTEND.md YAML schema for baoyu-imagine user preferences
|
||||
---
|
||||
|
||||
# Preferences Schema
|
||||
+58
-2
@@ -13,6 +13,7 @@ import {
|
||||
getWorkerCount,
|
||||
isRetryableGenerationError,
|
||||
loadBatchTasks,
|
||||
loadExtendConfig,
|
||||
mergeConfig,
|
||||
normalizeOutputImagePath,
|
||||
parseArgs,
|
||||
@@ -69,7 +70,7 @@ async function makeTempDir(prefix: string): Promise<string> {
|
||||
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
|
||||
}
|
||||
|
||||
test("parseArgs parses the main image-gen CLI flags", () => {
|
||||
test("parseArgs parses the main baoyu-imagine CLI flags", () => {
|
||||
const args = parseArgs([
|
||||
"--promptfiles",
|
||||
"prompts/system.md",
|
||||
@@ -170,6 +171,61 @@ batch:
|
||||
});
|
||||
});
|
||||
|
||||
test("loadExtendConfig renames legacy EXTEND.md when the new path is missing", async () => {
|
||||
const root = await makeTempDir("baoyu-imagine-extend-");
|
||||
const cwd = path.join(root, "project");
|
||||
const home = path.join(root, "home");
|
||||
const legacyPath = path.join(cwd, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md");
|
||||
const currentPath = path.join(cwd, ".baoyu-skills", "baoyu-imagine", "EXTEND.md");
|
||||
|
||||
await fs.mkdir(path.dirname(legacyPath), { recursive: true });
|
||||
await fs.mkdir(home, { recursive: true });
|
||||
await fs.writeFile(legacyPath, `---
|
||||
default_provider: google
|
||||
default_quality: 2k
|
||||
---
|
||||
`);
|
||||
|
||||
const config = await loadExtendConfig(cwd, home);
|
||||
|
||||
assert.equal(config.default_provider, "google");
|
||||
assert.equal(config.default_quality, "2k");
|
||||
await fs.access(currentPath);
|
||||
await assert.rejects(() => fs.access(legacyPath));
|
||||
});
|
||||
|
||||
test("loadExtendConfig leaves legacy EXTEND.md untouched when both paths exist", async () => {
|
||||
const root = await makeTempDir("baoyu-imagine-extend-dual-");
|
||||
const cwd = path.join(root, "project");
|
||||
const home = path.join(root, "home");
|
||||
const legacyPath = path.join(cwd, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md");
|
||||
const currentPath = path.join(cwd, ".baoyu-skills", "baoyu-imagine", "EXTEND.md");
|
||||
|
||||
await fs.mkdir(path.dirname(legacyPath), { recursive: true });
|
||||
await fs.mkdir(path.dirname(currentPath), { recursive: true });
|
||||
await fs.mkdir(home, { recursive: true });
|
||||
await fs.writeFile(legacyPath, `---
|
||||
default_provider: google
|
||||
---
|
||||
`);
|
||||
await fs.writeFile(currentPath, `---
|
||||
default_provider: openai
|
||||
---
|
||||
`);
|
||||
|
||||
const config = await loadExtendConfig(cwd, home);
|
||||
|
||||
assert.equal(config.default_provider, "openai");
|
||||
assert.equal(await fs.readFile(legacyPath, "utf8"), `---
|
||||
default_provider: google
|
||||
---
|
||||
`);
|
||||
assert.equal(await fs.readFile(currentPath, "utf8"), `---
|
||||
default_provider: openai
|
||||
---
|
||||
`);
|
||||
});
|
||||
|
||||
test("mergeConfig only fills values missing from CLI args", () => {
|
||||
const merged = mergeConfig(
|
||||
makeArgs({
|
||||
@@ -349,7 +405,7 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
|
||||
});
|
||||
|
||||
test("loadBatchTasks and createTaskArgs resolve batch-relative paths", async (t) => {
|
||||
const root = await makeTempDir("baoyu-image-gen-batch-");
|
||||
const root = await makeTempDir("baoyu-imagine-batch-");
|
||||
t.after(() => fs.rm(root, { recursive: true, force: true }));
|
||||
|
||||
const batchFile = path.join(root, "jobs", "batch.json");
|
||||
@@ -2,7 +2,7 @@ import path from "node:path";
|
||||
import process from "node:process";
|
||||
import { homedir } from "node:os";
|
||||
import { fileURLToPath } from "node:url";
|
||||
import { access, mkdir, readFile, writeFile } from "node:fs/promises";
|
||||
import { access, mkdir, readFile, rename, writeFile } from "node:fs/promises";
|
||||
import type {
|
||||
BatchFile,
|
||||
BatchTaskInput,
|
||||
@@ -471,14 +471,49 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
|
||||
return config;
|
||||
}
|
||||
|
||||
async function loadExtendConfig(): Promise<Partial<ExtendConfig>> {
|
||||
const home = homedir();
|
||||
const cwd = process.cwd();
|
||||
type ExtendConfigPathPair = {
|
||||
current: string;
|
||||
legacy: string;
|
||||
};
|
||||
|
||||
const paths = [
|
||||
path.join(cwd, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md"),
|
||||
path.join(home, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md"),
|
||||
function getExtendConfigPathPairs(cwd: string, home: string): ExtendConfigPathPair[] {
|
||||
return [
|
||||
{
|
||||
current: path.join(cwd, ".baoyu-skills", "baoyu-imagine", "EXTEND.md"),
|
||||
legacy: path.join(cwd, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md"),
|
||||
},
|
||||
{
|
||||
current: path.join(home, ".baoyu-skills", "baoyu-imagine", "EXTEND.md"),
|
||||
legacy: path.join(home, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md"),
|
||||
},
|
||||
];
|
||||
}
|
||||
|
||||
async function exists(filePath: string): Promise<boolean> {
|
||||
try {
|
||||
await access(filePath);
|
||||
return true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
async function migrateLegacyExtendConfig(cwd: string, home: string): Promise<void> {
|
||||
for (const { current, legacy } of getExtendConfigPathPairs(cwd, home)) {
|
||||
const [hasCurrent, hasLegacy] = await Promise.all([exists(current), exists(legacy)]);
|
||||
if (hasCurrent || !hasLegacy) continue;
|
||||
await mkdir(path.dirname(current), { recursive: true });
|
||||
await rename(legacy, current);
|
||||
}
|
||||
}
|
||||
|
||||
export async function loadExtendConfig(
|
||||
cwd = process.cwd(),
|
||||
home = homedir(),
|
||||
): Promise<Partial<ExtendConfig>> {
|
||||
await migrateLegacyExtendConfig(cwd, home);
|
||||
|
||||
const paths = getExtendConfigPathPairs(cwd, home).map(({ current }) => current);
|
||||
|
||||
for (const p of paths) {
|
||||
try {
|
||||
+1
-1
@@ -136,7 +136,7 @@ test("Azure image generation routes model to deployment and sends mapped quality
|
||||
});
|
||||
|
||||
test("Azure image edits include quality in multipart requests", async (t) => {
|
||||
const root = await makeTempDir("baoyu-image-gen-azure-");
|
||||
const root = await makeTempDir("baoyu-imagine-azure-");
|
||||
t.after(() => fs.rm(root, { recursive: true, force: true }));
|
||||
|
||||
const pngPath = path.join(root, "ref.png");
|
||||
+1
-1
@@ -421,7 +421,7 @@ export async function generateImage(
|
||||
|
||||
if (args.referenceImages.length > 0) {
|
||||
throw new Error(
|
||||
"Reference images are not supported with DashScope provider in baoyu-image-gen. Use --provider google with a Gemini multimodal model."
|
||||
"Reference images are not supported with DashScope provider in baoyu-imagine. Use --provider google with a Gemini multimodal model."
|
||||
);
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user