← 返回 Skills 市场
turbos7

MiniMax Image Generation

作者 Vesper · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
77
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install turbos7-minimax-image
功能描述
MiniMax 图片生成技能。集成文生图和图生图功能,支持从文本描述生成图片,也可基于参考图生成新图片。触发场景:(1) 用户请求生成图片,(2) 用户提供描述并要求生成图片,(3) 用户上传参考图并要求基于该图生成新图,(4) 用户想要生成指定风格的图片。支持的风格:漫画、元气、中世纪、水彩(仅 image-0...
安全使用建议
This skill largely does what it says (text→image and image→image via api.minimaxi.com), but take these precautions before installing or running it: - Expect to provide an API key: the scripts require MINIMAX_API_KEY even though the registry metadata doesn't list it. Do not supply your key until you confirm the API host and trust the skill source. - Privacy: image-to-image sends reference images (base64) to the remote API. Do not upload private or sensitive photos unless you trust the service and understand retention/billing policies. - Source trust: the skill has no homepage and an unknown owner. If you need higher assurance, request the publisher's source/origin or run the scripts in an isolated environment first. - Billing & permissions: using the API may incur costs or require an account; verify quotas and API key scope on the MiniMax platform. - File writes: the tool will save images under ~/.openclaw/workspace/assets/images by default — change the save-dir if you prefer another location. If you plan to proceed: inspect the two included Python scripts yourself, add MINIMAX_API_KEY only after verifying the API endpoint, and consider running the scripts in a sandbox or VM if you have any doubt about the skill's provenance.
功能分析
Type: OpenClaw Skill Name: turbos7-minimax-image Version: 1.1.0 The skill bundle provides a legitimate integration with the MiniMax AI image generation service. The included Python scripts (generate_image.py and image_to_image.py) facilitate text-to-image and image-to-image workflows by communicating with the official MiniMax API (api.minimaxi.com). The code follows standard practices, such as using environment variables for API keys and saving generated assets to a specific workspace directory (~/.openclaw/workspace/assets/images). No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
能力标签
requires-oauth-tokenrequires-sensitive-credentials
能力评估
Purpose & Capability
The code and SKILL.md implement a MiniMax text→image and image→image client and need an API key (MINIMAX_API_KEY). However the registry metadata declares no required environment variables or primary credential — that mismatch is unexpected and likely an oversight. Other than that, requested actions (calling https://api.minimaxi.com and uploading reference images) are coherent with the stated purpose.
Instruction Scope
Instructions and scripts instruct the agent to send prompts and reference images to api.minimaxi.com, download returned image URLs, and save images under ~/.openclaw/workspace/assets/images. Sending local reference images (base64) to a third-party API is required for img2img functionality but is privacy-sensitive and not explicitly highlighted in SKILL.md. The SKILL.md examples also have minor code issues (e.g., a missing import in the quickstart snippet).
Install Mechanism
There is no install spec (instruction-only with included scripts), so nothing is fetched or executed during installation. This lowers install-time risk — all network activity originates from the included scripts at runtime.
Credentials
The scripts require an API key via MINIMAX_API_KEY but the skill metadata does not declare this environment variable or a primary credential. Requiring a bearer API key for the image API is proportionate, but the missing declaration is a significant packaging inconsistency that could mislead users about what secrets are needed.
Persistence & Privilege
The skill is not marked always:true and does not modify other skills or system settings. It writes generated images to the user's workspace directory, which is expected behavior for a generation tool.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install turbos7-minimax-image
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /turbos7-minimax-image 触发
  4. 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
v1.1.0
优化:自动保存图片到本地、支持批量生成、返回本地路径
v1.0.0
文生图+图生图,支持多种风格和宽高比
元数据
Slug turbos7-minimax-image
版本 1.1.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

MiniMax Image Generation 是什么?

MiniMax 图片生成技能。集成文生图和图生图功能,支持从文本描述生成图片,也可基于参考图生成新图片。触发场景:(1) 用户请求生成图片,(2) 用户提供描述并要求生成图片,(3) 用户上传参考图并要求基于该图生成新图,(4) 用户想要生成指定风格的图片。支持的风格:漫画、元气、中世纪、水彩(仅 image-0... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 77 次。

如何安装 MiniMax Image Generation?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install turbos7-minimax-image」即可一键安装,无需额外配置。

MiniMax Image Generation 是免费的吗?

是的,MiniMax Image Generation 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

MiniMax Image Generation 支持哪些平台?

MiniMax Image Generation 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 MiniMax Image Generation?

由 Vesper(@turbos7)开发并维护,当前版本 v1.1.0。

💬 留言讨论