relay-image-gen

Multi-provider image generation with automatic priority fallback

33 stars

Best use case

relay-image-gen is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Multi-provider image generation with automatic priority fallback

Teams using relay-image-gen should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/relay-image-gen/SKILL.md --create-dirs "https://raw.githubusercontent.com/aAAaqwq/AGI-Super-Team/main/skills/relay-image-gen/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/relay-image-gen/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How relay-image-gen Compares

Feature / Agentrelay-image-genStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Multi-provider image generation with automatic priority fallback

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Relay Image Generation

Multi-provider image generation with automatic priority fallback.

## Priority Chain

```
1. qingyun Gemini (gemini-3-pro-image-preview) ← 首选,质量最佳
   ↓ 失败/不可用
2. OpenClaw image_generate tool ← 官方内置
   ↓ 失败/不可用
3. boluobao (中转API) ← relay fallback 1
   ↓ 失败/不可用
4. xingjiabi (多模型fallback) ← relay fallback 2
   ↓ 失败/不可用
5. 自定义扩展 providers ← 按需添加
```

### 1. qingyun Gemini(首选)

**推荐用于所有内容封面和高质量图片生成。**

```bash
export QINGYUN_API_KEY=$(pass show api/qingyun | head -n 1)
bash ~/clawd/skills/qingyun-api/scripts/qingyun-image-gemini.sh \
  "your prompt" \
  --ratio 3:4 \
  -o "/path/to/output"
```

| 参数 | 说明 | 默认值 |
|------|------|--------|
| `--ratio` | `1:1` / `3:4` / `4:3` / `16:9` / `9:16` | `1:1` |
| `-o` | 输出路径(由调用方指定,不写死) | 必填 |

**优点**:出图质量高、比例控制准确、支持中文提示词
**要求**:`pass show api/qingyun` 需配置 API Key

### 2. OpenClaw image_generate(官方)

直接使用 OpenClaw 内置图片生成工具:

```
image_generate(
  prompt="your prompt",
  size="1024x1024",
  aspectRatio="1:1"
)
```

**优点**:无需额外 API Key,自动路由到最佳可用 provider
**注意**:由 OpenClaw 运行时管理,不在 bash 中调用

### 3-4. Relay Providers(备选)

```bash
uv run ~/.openclaw/skills/relay-image-gen/scripts/relay_image_gen.py \
  -p "your prompt" \
  -f "/path/to/output.jpg" \
  -a "3:4" \
  -r "1k"
```

| Flag | 说明 | 默认值 |
|------|------|--------|
| `-p` | 图片提示词(英文推荐) | 必填 |
| `-f` | 输出文件路径 | 必填 |
| `-r` | 分辨率:`1k` / `2k` / `4k` | `1k` |
| `-a` | 比例:`1:1` / `16:9` / `9:16` / `3:4` 等 | `1:1` |
| `-m` | 覆盖模型名 | Provider默认 |
| `-P` | 强制 Provider:`boluobao` / `xingjiabi` | Auto |

**Relay 内部优先级**:boluobao → xingjiabi

### 各 Provider 配置

| Provider | API Key 来源 | 默认模型 | Fallback |
|----------|-------------|---------|----------|
| **boluobao** | `pass show api/boluobao` | gemini-3-pro-image-preview | — |
| **xingjiabi** | 环境变量 `XINGJIABIAPI_KEY` | dall-e-3 | gpt-image-1 → imagen-4 |

## 输出路径规范

**不写死路径**。由调用方指定,默认遵循:

```
~/clawd/projects/MediaClaw/output/articles/{YYYY-MM-DD}/{topic-slug}.{ext}
```

## 扩展自定义 Provider

添加新的中转 API 只需两步:

### Step 1: 编辑 `PROVIDER_CONFIG`

在 `~/.openclaw/skills/relay-image-gen/scripts/relay_image_gen.py` 中添加:

```python
PROVIDER_CONFIG["my-provider"] = {
    "base_url": "https://api.my-provider.com/v1",
    "default_model": "my-model-name",
    "fallback_models": ["fallback-model-1", "fallback-model-2"],
    "env_key": "MY_PROVIDER_API_KEY",       # 环境变量名
    "pass_path": "api/my-provider",          # 或 pass 路径(二选一)
}
```

### Step 2: 添加到优先级链

```python
RELAY_PRIORITY = [
    {"name": "boluobao", "enabled": True},
    {"name": "my-provider", "enabled": True},  # ← 插入
    {"name": "xingjiabi", "enabled": True},
]
```

### Provider 配置字段说明

| 字段 | 说明 | 必填 |
|------|------|------|
| `base_url` | API endpoint | ✅ |
| `default_model` | 主模型 | ✅ |
| `fallback_models` | 失败后尝试的模型列表 | 可选 |
| `env_key` | 环境变量名 | 与 `pass_path` 二选一 |
| `pass_path` | `pass show` 路径 | 与 `env_key` 二选一 |

## 调用示例

```bash
# 内容封面(首选 qingyun)
export QINGYUN_API_KEY=$(pass show api/qingyun | head -n 1)
bash ~/clawd/skills/qingyun-api/scripts/qingyun-image-gemini.sh \
  "Editorial flat illustration of AI tools comparison..." \
  --ratio 3:4 \
  -o "~/clawd/projects/MediaClaw/output/articles/2026-04-15/ai-tools-cover.png"

# 通用图片(relay fallback)
uv run ~/.openclaw/skills/relay-image-gen/scripts/relay_image_gen.py \
  -p "A serene Japanese garden with cherry blossoms" \
  -f "~/clawd/projects/MediaClaw/output/articles/2026-04-15/garden-bg.jpg" \
  -a "16:9" -r "2k"

# 强制指定 provider
uv run ~/.openclaw/skills/relay-image-gen/scripts/relay_image_gen.py \
  -p "Robot waving hello" \
  -f "robot.jpg" \
  -P xingjiabi -m gpt-image-1

# OpenClaw 内置(无bash)
image_generate(prompt="sunset over mountains", size="1792x1024", aspectRatio="16:9")
```

## 内容封面

生成内容封面时,请先读取 **content-cover-gen** skill 获取完整的视觉隐喻设计方法论和提示词模板:

```
cat ~/clawd/skills/content-cover-gen/SKILL.md
```

**核心原则**:每张封面提示词必须包含文章核心观点的视觉隐喻 + 中文文字,严禁纯风格通用提示词。

## Provider 详细信息

参见 [references/providers.md](references/providers.md) 了解 API 格式、模型列表和添加方法。

Related Skills

relay-video-gen

33
from aAAaqwq/AGI-Super-Team

Multi-provider video generation with async polling and automatic model fallback

image-scraper

33
from aAAaqwq/AGI-Super-Team

Scrape and download all images from a given URL. Takes a URL, extracts image URLs from the page, and downloads them. Uses python3/curl as primary method, falls back to browser automation if needed. Use when user provides a URL and wants to download images from that page.

image-enhancer

33
from aAAaqwq/AGI-Super-Team

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

baoyu-xhs-images

33
from aAAaqwq/AGI-Super-Team

Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.

zimage-skill

33
from aAAaqwq/AGI-Super-Team

Generate images using ModelScope Z-Image-Turbo API. Use when user asks to generate, create, or make images, pictures, or illustrations.

wemp-operator

33
from aAAaqwq/AGI-Super-Team

> 微信公众号全功能运营——草稿/发布/评论/用户/素材/群发/统计/菜单/二维码 API 封装

Content & Documentation

zsxq-smart-publish

33
from aAAaqwq/AGI-Super-Team

Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球.

zoom-automation

33
from aAAaqwq/AGI-Super-Team

Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.

zoho-crm-automation

33
from aAAaqwq/AGI-Super-Team

Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.

ziliu-publisher

33
from aAAaqwq/AGI-Super-Team

字流(Ziliu) - AI驱动的多平台内容分发工具。用于一次创作、智能适配排版、一键分发到16+平台(公众号/知乎/小红书/B站/抖音/微博/X等)。当用户需要多平台发布、内容排版、格式适配时使用。触发词:字流、ziliu、多平台发布、一键分发、内容分发、排版发布。

zhihu-post-skill

33
from aAAaqwq/AGI-Super-Team

> 知乎文章发布——知乎平台内容创作与发布自动化

zendesk-automation

33
from aAAaqwq/AGI-Super-Team

Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.