菜单
Unified multi-platform AI image generation. Supports Volcengine Seedream, Alibaba Qwen Image, and Google Gemini (Nano Banana). Switch between models with a dropdown selector.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/sangjiexun/openclaw-skill-UniImage --skill uni-image命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | uni-image |
| description | Unified multi-platform AI image generation. Supports Volcengine Seedream, Alibaba Qwen Image, and Google Gemini (Nano Banana). Switch between models with a dropdown selector. |
| homepage | https://github.com/sangjiexun/openclaw-skill-UniImage |
| metadata | {"openclaw":{"emoji":"🖼️","requires":{"env":"[Truncated]"},"primaryEnv":"ARK_API_KEY"}} |
Multi-platform AI image generation skill for OpenClaw. Supports switching between providers via a dropdown model selector on the paint page.
| Model ID | Display Name | Provider | Description |
|---|---|---|---|
doubao-seedream-5-0-260128 | Seedream 5.0 | Volcengine Ark | 多角色超强一致性，中文处理能力极强 |
qwen-image-plus | Qwen Image | Alibaba DashScope | 单图一致性强，适合中文相关的多图处理场景 |
gemini-3-pro-image-preview | 香蕉 Pro | Google Gemini | 最强修图模型，适合电商和专业设计 |
gemini-3.1-flash-image-preview | 香蕉 V2 | Google Gemini | 最新香蕉模型，极致速度和超高性价比 |
Renderer (paint page)
↓ fetch(/v1/images/generations)
↓ [fetch interceptor rewrites URL + model]
UniImage Proxy (port 18800)
├── Volcengine Ark API (Seedream)
├── DashScope API (Qwen Image, async poll)
└── Google Gemini API (Nano Banana)
uni-image-proxy.js — HTTP proxy server with multi-provider routinguni-image-inject.js — Renderer injection script (fetch wrapper + model selector UI)SKILL.md — This skill manifestConfigure API keys via the 🔑 button on the paint page, or set environment variables:
# Volcengine Ark (Seedream)
ARK_API_KEY=your-volcengine-key
# Alibaba DashScope (Qwen Image)
DASHSCOPE_IMAGE_KEY=your-dashscope-key
# Google AI (Nano Banana / Gemini)
GOOGLE_API_KEY=your-google-api-key
Keys are stored in ~/.openclaw-dev/uni-image-config.json.
# Seedream (default)
node uni-image-proxy.js &
curl -X POST http://127.0.0.1:18800/v1/images/generations \
-H "Content-Type: application/json" \
-d '{"model":"doubao-seedream-5-0-260128","prompt":"a cute cat","size":"1024x1024"}'
# Qwen Image
curl -X POST http://127.0.0.1:18800/v1/images/generations \
-H "Content-Type: application/json" \
-d '{"model":"qwen-image-plus","prompt":"a cute cat","size":"1024*1024"}'
# Google Gemini (Nano Banana)
curl -X POST http://127.0.0.1:18800/v1/images/generations \
-H "Content-Type: application/json" \
-d '{"model":"gemini-3.1-flash-image-preview","prompt":"a cute cat"}'