image-generation
图像生成辅助。支持通过 OpenRouter 直接调用各种生图模型(如 Seedream),为 OpenClaw 优化,支持提示词、尺寸等参数配置。目前仅限 OpenRouter provider。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/goforu/phoenixclaw-image-gen图像生成辅助
为 OpenClaw 提供原生的图像生成能力,通过文字描述词快速生成高质量图像。
工作流程
用户提示词 (Prompt)
↓
┌─────────────────────────────────────┐
│ 识别参数:模型、尺寸、比例、路径 │
└─────────────────────────────────────┘
↓
┌─────────────────────────────────────┐
│ 调用 OpenRouter 接口 (OpenClaw) │
└─────────────────────────────────────┘
↓
┌─────────────────────────────────────┐
│ 默认模型:seedream-4.5 (Text-to-Image) & Gemini 2.5 (Image-to-Image) │
└─────────────────────────────────────┘
↓
┌─────────────────────────────────────┐
│ 原子化写入本地存储 (Safety First) │
└─────────────────────────────────────┘
↓
返回结构化 JSON (Success Payload)
安装与配置
1. 获取 API Key
本技能需要 OpenRouter API Key 才能调用图像生成服务。
- 访问 OpenRouter 控制台 创建 API Key
- 请根据下方指引手动配置环境变量
2. 配置到环境变量
根据 OpenClaw 官方最佳实践,请通过 ~/.openclaw/openclaw.json 配置环境变量:
{
skills: {
entries: {
"image-generation": {
enabled: true,
env: {
OPENROUTER_API_KEY: "sk-or-v1-xxxxxxxx..."
}
}
}
}
}
或使用 primaryEnv 快捷配置:
{
skills: {
entries: {
"image-generation": {
enabled: true,
apiKey: "sk-or-v1-xxxxxxxx..."
}
}
}
}
配置完成后无需重启,新配置会在下次运行 OpenClaw 时自动生效。
3. 选择默认模型(可选)
本技能默认使用 bytedance-seed/seedream-4.5 作为文本生图模型,google/gemini-2.5-flash-image 作为图生图模型。你可以通过以下方式更改:
方式一:环境变量配置
在 ~/.openclaw/openclaw.json 中添加:
{
skills: {
entries: {
"image-generation": {
enabled: true,
env: {
OPENROUTER_API_KEY: "sk-or-v1-xxx",
IMAGE_GEN_TEXT_TO_IMAGE_MODEL: "bytedance-seed/seedream-4.5",
IMAGE_GEN_IMAGE_TO_IMAGE_MODEL: "google/gemini-2.5-flash-image"
}
}
}
}
}
本技能默认使用 bytedance-seed/seedream-4.5 模型,你可以通过以下方式更改:
方式一:环境变量配置
在 ~/.openclaw/openclaw.json 中添加:
{
skills: {
entries: {
"image-generation": {
enabled: true,
env: {
OPENROUTER_API_KEY: "sk-or-v1-xxx",
IMAGE_GEN_IMAGE_TO_IMAGE_MODEL: "google/gemini-2.5-flash-image",
IMAGE_GEN_TEXT_TO_IMAGE_MODEL: "bytedance-seed/seedream-4.5"
}
}
}
}
方式二:查看可用模型
node skills/image-generation/scripts/cli/openrouter.js --list-models
方式三:生成时指定模型
node skills/image-generation/scripts/generate.js \
--prompt "a futuristic city" \
--model "bytedance-seed/seedream-4.5" \
--i2i-model "google/gemini-2.5-flash-image"
node skills/image-generation/scripts/generate.js \
--prompt "a futuristic city" \
--image "bytedance-seed/seedream-4.5" \
--model "google/gemini-2.5-flash-image"
推荐模型:
bytedance-seed/seedream-4.5- 默认,高质量图像生成anthropic/claude-3.5-sonnet-image- Claude 图像生成openai/dall-e-3- DALL-E 3
4. 验证配置
node skills/image-generation/scripts/cli/openrouter.js --test
预期输出:
{
"success": true,
"message": "OpenRouter API key is configured. Test passed."
}
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-goforu-phoenixclaw-image-gen": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
phoenixclaw-ledger
Passive financial tracking plugin for PhoenixClaw. Automatically detects expenses and income from conversations and payment screenshots. Use when: - User mentions money/spending (any language) - User shares payment screenshots (WeChat Pay, Alipay, etc.) - User asks about finances ("How much did I spend?", "My budget") - User wants expense reports ("Monthly summary", "Spending analysis")
openclaw-visual
将 OpenClaw 中的信息(PhoenixClaw 日志、聊天记录、单条消息等)转换为精美排版的图片, 便于在聊天窗口(Telegram/Slack/Discord 等)中直接展示和分享。 Use when: - 用户要求将内容做成图片 ("帮我把这段话做成图片") - 用户要求生成日志可视化 ("生成今日日志分享图") - 用户要求将聊天记录可视化 ("把今天的对话做成总结图")
founder-coach
AI-powered startup mindset coach that helps founders upgrade their thinking patterns, track mental model progress, and set weekly challenges. Use when: - User is a startup founder seeking to improve their entrepreneurial mindset - User wants to detect and overcome low-level thinking patterns - User needs guidance on applying mental models (PMF, 4Ps, NFX frameworks) - User wants to set and track weekly challenges - User requests a weekly progress report - User is discussing startup challenges and needs Socratic questioning
phoenixclaw
Passive journaling skill that scans daily conversations via cron to generate markdown journals using semantic understanding. Use when: - User requests journaling ("Show me my journal", "What did I do today?") - User asks for pattern analysis ("Analyze my patterns", "How am I doing?") - User requests summaries ("Generate weekly/monthly summary")