← 返回 Skills 市场
13112
总下载
12
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install image-generation
功能描述
Create AI images with GPT Image, Gemini Nano Banana, FLUX, Imagen, and top providers using prompt engineering, style control, and smart editing.
安全使用建议
Install only if you are comfortable sending prompts and any reference images to the selected image provider. Use environment variables for API keys, avoid sensitive or regulated images unless provider policy allows it, and run the optional pip installs in a dedicated virtual environment with pinned dependencies where possible.
功能分析
Type: OpenClaw Skill
Name: image-generation
Version: 1.0.3
The OpenClaw AgentSkills skill bundle for AI Image Generation is classified as benign. All code snippets and instructions, including shell commands for setup (`mkdir`, `cp`, `test -f`, `test -n` in `setup.md`, `migration.md`) and Python network calls (`requests`, `openai`, `replicate` in `api-patterns.md`, `gpt-image.md`, `replicate.md`), are directly aligned with the stated purpose of interacting with legitimate image generation APIs or managing local configuration files. The `SKILL.md` transparently declares external endpoints and data sent, and explicitly states it does not store API keys or upload files outside chosen provider requests. There is no evidence of intentional harmful behavior, data exfiltration to unauthorized endpoints, persistence mechanisms, obfuscation, or malicious prompt injection attempts against the agent.
能力评估
Credentials
Optional API keys and external provider calls are proportionate for image generation and are disclosed, including the fact that prompts and optional reference images leave the machine.
Install Mechanism
There is no executable installer in the artifact, but provider docs include unpinned pip install examples for Replicate and local Stable Diffusion stacks, which users should run in an isolated environment.
Instruction Scope
Instructions are scoped to choosing models, using provider APIs, managing prompts, and avoiding outdated aliases; I found no prompt hijacking, hidden role changes, destructive commands, or unrelated authority.
Persistence & Privilege
The skill creates or updates local preference memory under ~/image-generation/ and an optional history file; this is disclosed, limited to workflow preferences/project context, and does not store API keys or create background persistence.
Purpose & Capability
The artifacts consistently support AI image generation, provider selection, prompt guidance, edits, and local or hosted model workflows.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install image-generation - 安装完成后，直接呼叫该 Skill 的名称或使用
/image-generation触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.3
Updated for 2026 with benchmark-backed model selection and clearer guidance for modern image generation stacks.
v1.0.2
Added detailed provider endpoints documentation and feedback section
v1.0.1
Preferences now persist across skill updates in ~/image-generation/
v1.0.0
Initial release
元数据
常见问题
AI Image Generation 是什么？
Create AI images with GPT Image, Gemini Nano Banana, FLUX, Imagen, and top providers using prompt engineering, style control, and smart editing. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 13112 次。
如何安装 AI Image Generation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install image-generation」即可一键安装，无需额外配置。
AI Image Generation 是免费的吗？
是的，AI Image Generation 完全免费（开源免费），可自由下载、安装和使用。
AI Image Generation 支持哪些平台？
AI Image Generation 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（linux, darwin, win32）。
谁开发了 AI Image Generation？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.3。
推荐 Skills