← 返回 Skills 市场
netyingxiao

ModelScope AI Image Generator

作者 netyingxiao · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
178
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install modelscope-img-gen
功能描述
魔搭(ModelScope)AI 图片生成。支持多种模型、LoRA 微调。触发词:生成图片、AI绘画、文生图、image generation、generate image。当用户要求生成图片、画图、AI 作画,或提到魔搭、ModelScope、通义万象时使用。
安全使用建议
This skill's behavior is consistent with a ModelScope image generator, but the registry metadata omitted the API-key requirement. Before installing, review the included scripts/generate.py yourself and confirm you trust the source. If you use it, provide a dedicated ModelScope API key (avoid using any high-privilege or shared keys), and consider running the script in an isolated environment. Note that the script can save the key to ~/.modelscope/api_key — verify the file path and permissions, and remove the file if you later revoke the key. Finally, install the minimal dependencies (requests, pillow) and prefer passing the key via CLI or an ephemeral environment variable rather than storing it permanently if you have concerns.
功能分析
Type: OpenClaw Skill Name: modelscope-img-gen Version: 1.0.0 The skill is a legitimate tool for generating images using the ModelScope API. The core logic in `scripts/generate.py` handles API authentication, asynchronous task polling, and image downloading in a standard manner. API keys are managed through environment variables or a local configuration file (`~/.modelscope/api_key`) with basic permission handling. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
The skill claims to be a ModelScope image generator and the code/SKILL.md implement that exactly (calls ModelScope inference endpoints, supports LoRA). However, the registry metadata lists no required environment variables or primary credential while both the script and SKILL.md require an API key (MODELSCOPE_API_KEY or config file). That mismatch is an incoherence in the manifest.
Instruction Scope
SKILL.md and the script stay within the stated purpose: they instruct how to supply an API key, call ModelScope endpoints, poll for task completion, download the generated image and save it locally. There is no instruction to read unrelated system state or transmit unrelated data.
Install Mechanism
There is no install spec (instruction-only), which reduces risk. The package includes a Python script that requires requests and pillow (noted in SKILL.md). No external archives or obscure download URLs are used. The presence of an executable script without an install step is acceptable but SKILL metadata could list these dependencies.
Credentials
The script expects an API key via CLI/env/config (~/.modelscope/api_key) and can save that key to a local file. Requesting a single ModelScope API credential is proportionate to the stated purpose, but the skill metadata does not declare it (missing required env/primary credential). The ability to write the API key to ~/.modelscope/api_key should be noted by users.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or global agent settings. It does write a per-user config file (~/.modelscope/api_key) when asked to save a key, which is expected behavior for a CLI client.
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 modelscope-img-gen
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /modelscope-img-gen 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
v1.0.0
Initial release: AI image generation with LoRA support
元数据
Slug modelscope-img-gen
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

ModelScope AI Image Generator 是什么?

魔搭(ModelScope)AI 图片生成。支持多种模型、LoRA 微调。触发词:生成图片、AI绘画、文生图、image generation、generate image。当用户要求生成图片、画图、AI 作画,或提到魔搭、ModelScope、通义万象时使用。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 178 次。

如何安装 ModelScope AI Image Generator?

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

ModelScope AI Image Generator 是免费的吗?

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

ModelScope AI Image Generator 支持哪些平台?

ModelScope AI Image Generator 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 ModelScope AI Image Generator?

由 netyingxiao(@netyingxiao)开发并维护,当前版本 v1.0.0。

💬 留言讨论